CN115358441A - New energy cluster consumption intelligent control method and device based on federal learning - Google Patents
New energy cluster consumption intelligent control method and device based on federal learning Download PDFInfo
- Publication number
- CN115358441A CN115358441A CN202210805292.0A CN202210805292A CN115358441A CN 115358441 A CN115358441 A CN 115358441A CN 202210805292 A CN202210805292 A CN 202210805292A CN 115358441 A CN115358441 A CN 115358441A
- Authority
- CN
- China
- Prior art keywords
- new energy
- potential
- power
- adjustable
- scheduling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000004044 response Effects 0.000 claims abstract description 97
- 238000011156 evaluation Methods 0.000 claims abstract description 49
- 238000010248 power generation Methods 0.000 claims abstract description 48
- 238000005457 optimization Methods 0.000 claims description 38
- 239000002245 particle Substances 0.000 claims description 38
- 238000009826 distribution Methods 0.000 claims description 20
- 230000005611 electricity Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000013210 evaluation model Methods 0.000 claims description 17
- 238000005265 energy consumption Methods 0.000 claims description 12
- 230000029087 digestion Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 229920000642 polymer Polymers 0.000 claims description 5
- 238000010521 absorption reaction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 9
- 238000003860 storage Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000005284 excitation Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 238000012847 principal component analysis method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 3
- 229910052739 hydrogen Inorganic materials 0.000 description 3
- 239000001257 hydrogen Substances 0.000 description 3
- 125000004435 hydrogen atom Chemical class [H]* 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012887 quadratic function Methods 0.000 description 2
- 241001652065 Trigonopeltastes delta Species 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a new energy cluster consumption intelligent regulation and control method and a device based on federal learning, wherein the method comprises the following steps: collecting data of different new energy power generation equipment and power users, and establishing a multi-time scale index set, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets with different time scales; based on the multi-time scale index set, evaluating the potential of the adjustable resource participating in response scheduling to obtain a potential evaluation result of the adjustable resource; and aiming at the potential evaluation result of the adjustable resources, intelligently scheduling the resources of the whole network based on federal learning. According to the method, under the influence of uncertain factors, the cluster regulation potential evaluation of the new energy equipment and the user is realized, the data privacy of each area in the subsequent resource regulation process is protected based on the federal learning thought, and the safety of the overall intelligent regulation is improved.
Description
Technical Field
The invention relates to the field of source-load resource regulation, in particular to a new energy cluster consumption intelligent regulation method and device based on federal learning.
Background
Uncertain influencing factors influencing the response potential of the adjustable resource comprise temperature, meteorological environment, the running state of the adjustable resource, response behavior, response incentive price and the like. The uncertainty factors reduce the reliability of the adjustable resource participating in the adjustment output of the power grid balancing service, and aggravate the fluctuation of the adjustable resource responding to the adjustment output. Therefore, the accuracy in the response potential evaluation process is limited by a large number of uncertain factors in the adjustable resource cluster, and proper description and processing of various uncertainties are crucial to response potential evaluation. The current research mainly considers the influence of market, environment and self electricity utilization characteristics of the adjustable resources on response potential based on various types of adjustable resource aggregation response models, and considers the fluctuation of multi-cluster coordinated response output of the adjustable resources. However, the research aiming at the response potential of the adjustable resource cluster mainly focuses on the research of the response capacity of the adjustable resource, the dynamic process of the internal resource in time when the cluster participates in the response is not considered, and the dynamic performance change of the adjustable resource cluster under the complementary coordination operation is not further analyzed. Therefore, it is necessary to consider the dynamic process of cluster participation in response, and evaluate the response potential of complementarily and coordinately running large-scale regional adjustable resource clusters from different time scales.
When source load resource regulation and control are carried out based on the potential evaluation result, different areas have respective data and need to be used for training, updating and optimizing regulation and control calculation of an actual model. However, the data amount of a single area is insufficient, and the model training effect is rough. If the data of different areas are integrated together to carry out integral model training, the data are limited by the privacy protection of the user data in practice, and the user data cannot be freely revealed to a third party by each area center in principle. Distributed computing can be used to solve this problem. Federal learning is a new computing philosophy developed by distributed learning. Compared with distributed computing, the advantage of federal learning is mainly embodied in the following five aspects:
1. in the aspect of control degree, in the traditional distributed learning, a center server has absolute control on workers in each subarea; in federal learning, a user has absolute control right on equipment and data, and can stop participating in calculation at any time.
2. In the aspect of node stability, the distributed worker nodes are very stable, almost the same in performance and too ideal; the worker nodes in federal learning are unstable and different, for example, mobile phones with different network speeds or different device devices have different calculated speed performances, and are more suitable for actual equipment and user conditions.
3. In the aspect of data properties, the data of each traditional distributed node is similar, and the random scrambling and the calculation have no great influence; the data learned by the federation are not independently and uniformly distributed, the data of each node is different in nature, and the practical problem that the habits of users are different is considered.
4. In the aspect of node data load, load balance needs to be ensured in the traditional distributed computation; the data load of the federal node can be unbalanced, electric energy of different units has different weights, and the calculation speed can be flexibly adjusted according to the node data.
5. In the aspect of regulating and controlling cost, distributed computing is mainly the computing cost of each worker node; the federal learning cost is mainly concentrated on the communication cost between the worker node and the server node.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a new energy cluster consumption intelligent control method and device based on federal learning, which realize cluster control potential evaluation of new energy equipment and users under the influence of uncertain factors, protect data privacy of each area in the subsequent resource control process based on the idea of federal learning, and improve the safety of overall intelligent control.
A new energy cluster consumption intelligent control method based on federal learning comprises the following steps:
collecting data of different new energy power generation equipment and power users, and establishing a multi-time scale index set, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets with different time scales;
based on the multi-time scale index set, evaluating the potential of the adjustable resource participating in response scheduling to obtain a potential evaluation result of the adjustable resource;
and aiming at the potential evaluation result of the adjustable resources, intelligently scheduling the resources of the whole network based on federal learning.
Further, collecting data of different new energy power generation equipment and power users, considering source load resource regulation uncertainty, and establishing a multi-time scale index set, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets of different time scales, and the method specifically comprises the following steps:
determining external influence factors of scheduling potential uncertainty of new energy output resources, collecting daily data, and establishing power generation characteristic index sets of different time scales;
the external influence factors of the scheduling potential uncertainty comprise weather factors and climate factors, the weather factors comprise wind speed, solar radiation degree, temperature and humidity, the climate factors comprise rain, sunny days and snow, and the power generation characteristic index sets of different time scales are obtained through statistical calculation of daily power generation data; the power utilization characteristic index set establishing module is used for determining internal influence factors of scheduling potential uncertainty of user demand response resources, collecting data and establishing power utilization characteristic index sets with different time scales;
the internal influence factors of the uncertainty of the scheduling potential comprise the equivalent heat capacity C, the equivalent heat resistance R, the energy efficiency ratio eta and the set temperature T of the polymer set Allowable temperature adjustment quantity delta T, regulation duration time delta T and user water consumption m n Ambient temperature T out And the market electricity price TOU, wherein the electricity utilization characteristic index sets of different time scales are obtained by statistical calculation of daily electricity generation data.
Further, based on the multi-time scale index set, the potential of the adjustable resource participating in response scheduling is evaluated in consideration of source load resource uncertainty, and a potential evaluation result of the adjustable resource is obtained, specifically comprising the following steps:
establishing an adjustable resource response potential evaluation model:
wherein r is 1 、r 2 、r 3 Known deterministic model parameters; r is 4 To satisfy a regular normal distribution, wherein the mean of the distribution is
Standard deviation of
Parameter mu 0 And σ 0 Is according to r 4 Carrying out point estimation on the historical response data set to obtain a probability estimation value;
the resulting probability estimate is taken as r 4 Satisfied normal distribution parameters, thereby obtaining adjustable resource participationResponding to the potential evaluation result of the scheduling:
wherein, the mean value reference value mu and the variance reference value sigma 2 Mean fuzzy value μ e And variance ambiguity value σ e The model indexes are model indexes for describing uncertainty parameters of user response potential, and the 4 indexes comprehensively reflect the uncertainty of the adjustable potential of the adjustable resource participation response service.
Further, for the potential evaluation result of the adjustable resource, intelligently scheduling the resources of the whole network based on federal learning specifically includes:
establishing a particle swarm optimization model by taking the optimal total effect of new energy consumption as a target:
the specific optimization target is shown in formula (6) and comprises reducing power fluctuation and reducing new energy power abandon, the limiting condition is shown in formula (8) and comprises equipment output limit and power fluctuation rate limit,
wherein T is new Indicating the number of periods during which the power fluctuation is calculated, λ o,t For purchase price of electric energy, λ flu For power fluctuation loss cost factor, P G,t For actual output of new energy, P Go,t For new energy possible capacity, P Gmax,t 、P Gmin,t Represents the upper and lower limit of the new energy equipment output in the t period, delta t Representing the new energy output power fluctuation, delta, over a period of t rise As an upper limit of the power increase rate, δ drop To lower the power reduction rate, Δ t is the time interval between two periods.
Further, the total regulation and control center server uses the federal learning idea to regulate and control the resources of the whole network, and specifically comprises the following steps:
the method comprises the following steps that (a) a master control center server transmits parameters w of a fixed particle swarm optimization algorithm model to each regional center;
step (b) based on the potential evaluation result of the adjustable resources, the worker in each regional center obtains power data of local adjustable resources participating in demand response, local conventional particle swarm optimization is respectively carried out on the worker in each regional center by utilizing the source charge power data information and the model parameter w transmitted from the total regulation center, and the adjustment quantity of new energy output or user load energy consumption in each region is calculated;
step (c), each regional center worker performs gradient descent for multiple times locally by using local data to obtain an updated gradient g, calculates a new parameter w and returns the new parameter w to the general control center server,
w←w-α·g (8)
w is a particle swarm optimization model parameter, alpha is a specific weight coefficient updating step length, and g is a gradient;
the master control center server collects new parameters w returned by each regional worker, carries out weighted average on the parameters, updates particle swarm model parameters, and then sends the parameters to each regional center worker;
and (e) repeating the steps (b) to (d) until the controllable source load resource scheduling in each area is completed.
The utility model provides a new forms of energy cluster consumption intelligent control device based on federal study, includes:
the characteristic index set establishing module is used for collecting data of different new energy power generation equipment and power users and establishing a multi-time scale index set, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets with different time scales;
the potential evaluation module is used for evaluating the potential of the adjustable resource participating in response scheduling based on the multi-time scale index set to obtain a potential evaluation result of the adjustable resource;
and the intelligent scheduling module is used for intelligently scheduling the resources of the whole network based on federal learning aiming at the potential evaluation result of the adjustable resources.
The characteristic index set establishing module comprises a power generation characteristic index set establishing module and a power utilization characteristic index set establishing module;
the power generation characteristic index set establishing module is used for determining external influence factors of scheduling potential uncertainty of the new energy output resources, collecting daily data and establishing power generation characteristic index sets with different time scales;
the external influence factors of the uncertainty of the scheduling potential comprise weather factors and climate factors, the weather factors comprise wind speed, solar radiation degree, temperature and humidity, the climate factors comprise rain, sunny days and snow, and the power generation characteristic index sets of different time scales are obtained through statistical calculation of daily power generation data;
the power utilization characteristic index set establishing module is used for determining internal influence factors of scheduling potential uncertainty of user demand response resources, collecting data and establishing power utilization characteristic index sets with different time scales.
The internal influence factors of the scheduling potential uncertainty comprise the equivalent heat capacity C, the equivalent heat resistance R, the energy efficiency ratio eta and the set temperature T of the polymer set Allowable temperature adjustment quantity delta T, regulation duration time delta T and user water consumption m n Ambient temperature T out And the electricity utilization characteristic index sets of different time scales are obtained by daily electricity generation data statistics and calculation.
Further, the potential evaluation module comprises a potential evaluation model establishing module and a potential evaluation result obtaining module; wherein,
the potential evaluation model establishing module is used for establishing an adjustable resource response potential evaluation model:
wherein r is 1 、r 2 、r 3 Known deterministic model parameters; r is a radical of hydrogen 4 To satisfy a regular normal distribution, the mean value of the distribution is
Standard deviation of
Parameter mu 0 And σ 0 Is according to r 4 Carrying out point estimation on the historical response data set to obtain a probability estimation value;
a potential evaluation result acquisition module for considering the obtained probability estimation value as r 4 And (3) satisfying the normal distribution parameters, thereby obtaining a potential evaluation result of the adjustable resource participating in response scheduling:
wherein, the mean value reference value mu and the variance reference value sigma 2 Mean fuzzy value μ e And the variance blur value σ e The model indexes are model indexes for describing uncertainty parameters of user response potential, and the 4 indexes comprehensively reflect the uncertainty of the adjustable potential of the adjustable resource participating response service.
Furthermore, the intelligent scheduling module comprises a particle swarm optimization model establishing module and a whole network resource regulating and controlling module;
and the particle swarm optimization model establishing module is used for establishing a particle swarm optimization model by taking the optimal total effect of new energy consumption as a target.
Further, the whole network resource regulation and control module comprises a main regulation and control center server and a regional center worker;
the general regulation and control center server is used for using the federal learning idea to regulate and control resources of the whole network, and specifically comprises the following steps:
the method comprises the following steps that (a) a master control center server transmits a parameter w of a fixed particle swarm optimization algorithm model to each regional center;
step (b) based on the potential evaluation result of the adjustable resources, the worker in each regional center obtains power data of local adjustable resources participating in demand response, local conventional particle swarm optimization is respectively carried out on the worker in each regional center by utilizing the source charge power data information and the model parameter w transmitted from the total regulation center, and the adjustment quantity of new energy output or user load energy consumption in each region is calculated;
step (c), each regional center worker locally performs multiple gradient descent by using local data to obtain an updated gradient g, calculates a new parameter w and returns the new parameter w to the general control center server,
w←w-α·g (9)
w is a particle swarm optimization model parameter, alpha is a specific weight coefficient updating step length, and g is a gradient;
the general control center server collects new parameters w returned by the worker in each area, carries out weighted average on the parameters, updates the particle swarm model parameters, and then sends the parameters to the worker in each area;
and (e) repeating the steps (b) to (d) until the controllable source load resource scheduling in each area is completed.
Further, the specific optimization target of the particle swarm optimization model is shown as a formula (6) and comprises the steps of reducing power fluctuation and reducing new energy power curtailment, the limiting conditions are shown as a formula (8) and comprise equipment output limit and power fluctuation rate limit,
wherein T is new Indicating the number of periods during which the power fluctuation is calculated, λ o,t For purchase of electric energyPrice, λ flu For power fluctuation loss cost factor, P G,t For actual contribution of new energy, P Go,t Capability of new energy to output, P Gmax,t 、 P Gmin,t Represents the upper and lower limit of the new energy equipment output in the t period, delta t Representing the new energy output power fluctuation, delta, over a period of t rise As an upper limit of the power increase rate, δ drop To lower the power reduction rate, Δ t is the time interval between two periods.
A new energy cluster consumption intelligent control system based on federal learning comprises: a computer-readable storage medium and a processor;
the computer-readable storage medium is used for storing executable instructions;
the processor is used for reading executable instructions stored in the computer-readable storage medium and executing the new energy cluster consumption intelligent regulation and control method based on the federal learning.
A non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the intelligent new energy cluster digestion control method based on federal learning.
The invention has the following beneficial effects:
(1) According to the new energy cluster consumption intelligent control method based on federal learning, an adjustable index set with multiple time scales can be established, the influence of uncertainty factors of source load resources is considered, and the control potential of cluster resources is evaluated, so that an energy company can make an ordered management strategy for different cluster source load resources according to the controllable characteristics of different source load resource clusters, and the energy management efficiency is improved;
(2) According to the new energy cluster absorption intelligent regulation and control method based on federal learning, the local utilization and protection of data can be realized without uploading to other regulation and control centers, and the update of model parameters is realized at the same time, so that on one hand, the transmission process of actual data of a user can be effectively reduced, the actual data of the user can be protected locally, and the privacy and the safety of the user data are improved; on the other hand, the method only transmits parameters but not direct data, and disperses the optimized calculation pressure of the control center to each branch pipe center, so that the communication cost can be reduced, and the updating efficiency of the optimized model parameters can be improved.
Drawings
FIG. 1 is a graph of the relationship between tunable resource response and excitation strength under the influence of uncertainty factors according to the present invention;
FIG. 2 is a diagram of the parameter delivery process for the federated learning approach employed in the present invention;
fig. 3 is a flowchart of one embodiment of the new energy cluster consumption intelligent control method based on federal learning according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 3, an embodiment of the present invention provides a new energy cluster consumption intelligent control method based on federal learning, which includes establishing a multi-time scale index set, considering scheduling potential evaluation of uncertainty of source and load resources, and intelligently scheduling based on federal learning, and specifically includes the following steps:
step 1: collecting data of different new energy power generation equipment and power users, and establishing a multi-time scale index set by considering source load resource regulation uncertainty, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets with different time scales. The step 1 specifically comprises the following steps:
step 1.1: determining external influence factors of scheduling potential uncertainty of the new energy output resources, collecting daily data, and establishing power generation characteristic index sets with different time scales.
The external influence factors of the intelligent regulation of the new energy power generation resources mainly refer to weather factors such as wind speed, solar radiation degree, temperature, humidity and the like. Weather factors such as rain, sunny days and snowing can also influence the power consumption of system equipment and the power generation amount of a power plant. The detailed indexes are shown in table 1, and these indexes can be obtained by statistical calculation of daily power generation data.
TABLE 1 Power Generation feature index set for different time scales
Step 1.2: determining internal influence factors of scheduling potential uncertainty of user demand response resources, collecting data, and establishing power utilization characteristic index sets with different time scales.
Uncertainty in the load model parameters is an important contributor to response potential. For example, the response potential of the user equipment can be accurately obtained by performing refined modeling on adjustable resources such as temperature control loads and electric vehicles, so that accurate differential control is realized, but in many cases, equivalent parameters of the user equipment and parameters of a charging model of the electric vehicle are difficult to directly measure, and the model parameters change along with changes of factors such as environment, market and user behaviors.
Therefore, the study of these load models cannot be limited to the study of static load models, and the uncertainty of model parameters due to various influencing factors is considered. For example: model parameters of an equivalent heat capacity C, an equivalent heat resistance R, an energy efficiency ratio eta and the like of the aggregate of the aggregation model of the air-conditioning adjustable resources are influenced by various uncertain factors, and the equivalent model parameters of the adjustable resource cluster under each time node are changed. In addition, the influence factor of the adjustable potential of the temperature control load also has the set temperature T set Allowable temperature adjustment amount delta T, regulation duration delta T and water consumption m of user n (Water heater load), ambient temperature T out Market TOU, etc.
The detailed indexes are shown in table 2, and these indexes can be obtained by statistical calculation of daily power generation data.
TABLE 2 Power utilization characteristic index set at different time scales
Step 2: and based on the multi-time scale index set, the potential of the adjustable resource participating in response scheduling is evaluated by considering source load resource uncertainty, and a potential evaluation result of the adjustable resource is obtained. The step 2 comprises the following steps:
step 2.1: and (4) considering the influence of the uncertainty factors in the step (1) and establishing an adjustable resource response potential evaluation model.
As shown in fig. 1, the relationship between the response of the adjustable resource and the excitation strength under the influence of the uncertainty factors, and considering the influence of various uncertainty factors in the estimation of the response potential of the adjustable resource, the linear region is generally considered to be represented by a region surrounded by the black solid line in fig. 1, that is, under a certain excitation strength of the linear region, the user response rate is not a unique point but changes within a possible region.
Ignoring the randomness of the response of the adjustable resources in the dead zone and the saturation zone, mainly solving relevant parameter modeling of the linear zone, specifically including a dead zone inflection point r 1 Inflection point r of saturation region 2 And its ordinate r 3 . Because the influence of uncertainty factors is considered, a linear function cannot be used for modeling a linear area, and a response curve of the linear area is represented by a quadratic function:
η＝r 4 (δ-a)(δ-b) (1)
in the formula: r is 4 A and b are related parameters of the quadratic model; eta is the user response rate; δ is the excitation intensity.
Step 2.2: and converting the adjustable resource response potential evaluation model into a solvable form according to the known key parameters of the power generation equipment and the user response model.
If the key of a model of a certain user participating in a response is knownParameter, i.e. inflection point (r) 1 0) and (r) 2 ，r 3 ) If known, the user response load shedding rate can be obtained by the following formula:
r in the formula 4 The parameters are random parameters considering the influence of uncertainty, and are defined by r 4 Can characterize the randomness of the participation of the tunable resource in the response process. Certainty parameter r of a user 1 、r 2 、r 3 With inter-individual variability and random parameter r 4 The influence on the response potential of the same type of adjustable resources has similarity. Random parameter r of adjustable resource cluster with electricity utilization behavior similarity can be analyzed 4 Therefore, the cluster adjustable resource response potential under the influence of uncertain factors is obtained.
Step 2.3: and (3) mining the daily data such as the power utilization capacity and the production power utilization characteristics of the users in the index set obtained in the step (1) to obtain the determined parameters r1, r2 and r3 in the adjustable resource response potential evaluation model.
Considering that the indexes in the characteristic set are more and part of the indexes have repeated characteristic information, reducing the dimension of the index set obtained in the step 1 by using a principal component analysis method, mining key parameters of the user adjustable potential model by using least square fitting on the basis, and finally obtaining the following relational expression:
in the formula: b 1j 、b 2j 、b 3j Coefficients of principal components that are key parameter influencing factors; u shape j A principal component representing a jth user electricity utilization characteristic index extracted by a principal component analysis method; a is ij Coefficients for an ith index in the jth principal component formation; x is the number of i Is the value of the ith index. The relation in the formula is used as the common characteristic of the users and can be directly used for oneThe user response characteristics typically determine the parameters sought.
Step 2.4: substituting the historical response data of the user-adjustable resources into the formula (2) to reversely solve the corresponding random parameter r 4 Thereby forming a random parametric historical data set based on the user historical response data.
Assuming the random parameter r 4 Normal distribution is satisfied within a certain range, so that a box type method can be adopted to determine a distributed robust fuzzy set of the random parameters:
wherein r is 1 、r 2 、r 3 Known deterministic model parameters; r is a radical of hydrogen 4 A normal distribution satisfying a certain rule, wherein the mean value of the distribution is
Standard deviation of
Parameter mu 0 And σ 0 Is according to r 4 The historical response data set of (a) is point estimated to obtain an estimate.
Step 2.5: the resulting estimate is taken as r 4 And (4) satisfying the normal distribution parameters, thereby obtaining a potential evaluation result of the adjustable resource participating in response scheduling.
Wherein, the mean value reference value mu and the variance reference value sigma 2 Mean fuzzy value μ e And variance ambiguity value σ e The model indexes are model indexes for describing uncertainty parameters of user response potential, and the 4 indexes comprehensively reflect the uncertainty of the adjustable potential of the adjustable resource participating response service.
And 3, step 3: and aiming at the potential evaluation result of the adjustable resources, intelligently scheduling the resources of the whole network based on federal learning. The step 3 specifically comprises the following steps:
step 3.1: and establishing a particle swarm optimization model by taking the optimal total effect of new energy consumption as a target.
The specific optimization target is shown as a formula (6) and comprises the steps of reducing power fluctuation and reducing new energy power abandon, and the limiting condition is shown as a formula (8) and comprises equipment output limit and power fluctuation rate limit;
wherein, T new Indicating the number of periods during which the power fluctuation is calculated. Period t, λ o,t For purchase price of electric energy, λ flu The cost factor is lost for power fluctuation. P G,t And actually exerting power for new energy. P is Go,t The capacity of new energy can be provided. P Gmax,t 、P Gmin,t Representing the upper and lower limit limits of the new energy equipment output in the period t. By delta t Representing the new energy output power fluctuation in the period t. Delta rise As an upper limit of the power increase rate, δ drop The lower limit of the power reduction rate. Δ t is the time interval between two periods.
Step 3.2: and the master control center server uses the federal learning idea to regulate and control the resources of the whole network. The specific implementation steps are as follows:
and (a) the master control center server transmits the parameter w of the fixed particle swarm optimization algorithm model to each regional center.
And (b) based on the potential evaluation probability result of the tunable resource participation response scheduling obtained in the step (2), the worker in each regional center obtains power data of local tunable resource participation demand response. And respectively carrying out local conventional particle swarm optimization by using the source load power data information and the model parameter w transmitted by the main control center and the regional center worker, and calculating the adjustment quantity of the new energy output or the user load energy consumption of each region.
A step (c): and each regional center worker locally performs gradient descent for multiple times by using local data to obtain an updated gradient g, and calculates a new parameter w and returns the new parameter w to the general control center server.
w←w-α·g (8)
Wherein w is a particle swarm optimization model parameter, alpha is a specific weight coefficient updating step length, and g is a gradient.
Step (d): and the master control center server collects new parameters w (shown in figure 2) returned by each regional worker, performs weighted average on the parameters, updates the particle swarm model parameters, and then sends the parameters to each regional center worker.
A step (e): and (d) repeating the steps (b) to (d) until the controllable source load resource scheduling in each area is completed.
The embodiment of the invention also provides a new energy cluster consumption intelligent control device based on federal learning, which comprises:
the characteristic index set establishing module is used for collecting data of different new energy power generation equipment and power users, considering source load resource regulation uncertainty and establishing a multi-time scale index set, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets with different time scales;
the potential evaluation module is used for evaluating the potential of the adjustable resource participating in response scheduling by considering source load resource uncertainty based on the multi-time scale index set to obtain a potential evaluation result of the adjustable resource;
and the intelligent scheduling module is used for intelligently scheduling the resources of the whole network based on federal learning aiming at the potential evaluation result of the adjustable resources.
The characteristic index set establishing module comprises a power generation characteristic index set establishing module and a power utilization characteristic index set establishing module;
the power generation characteristic index set establishing module is used for determining external influence factors of scheduling potential uncertainty of the new energy output resources, collecting daily data and establishing power generation characteristic index sets with different time scales;
the external influence factors of the scheduling potential uncertainty comprise weather factors and climate factors, the weather factors comprise wind speed, solar radiation degree, temperature and humidity, the climate factors comprise rain, sunny days and snow, the power generation characteristic index sets of different time scales are shown in table 1, and the external influence factors are obtained through daily power generation data statistics calculation:
TABLE 1 Power Generation feature index set for different time scales
The power utilization characteristic index set establishing module is used for determining internal influence factors of scheduling potential uncertainty of user demand response resources, collecting data and establishing power utilization characteristic index sets with different time scales.
The internal influence factors of the scheduling potential uncertainty comprise the equivalent heat capacity C, the equivalent heat resistance R, the energy efficiency ratio eta and the set temperature T of the polymer set Allowable temperature adjustment amount delta T, regulation duration delta T and water consumption m of user n Ambient temperature T out The market electricity price TOU, the electricity utilization characteristic index set of different time scales is as shown in Table 2, and the electricity utilization characteristic index set is obtained by daily electricity generation data statistics calculation:
TABLE 2 Power consumption characteristic index set at different time scales
The potential evaluation module comprises a potential evaluation model establishing module and a potential evaluation result obtaining module; wherein,
the potential evaluation model establishing module is used for establishing an adjustable resource response potential evaluation model; considering the influence of various uncertain factors during the response potential evaluation of the adjustable resource, under certain excitation intensity of a linear region, the user response rate is not a unique point but changes in a possible region;
ignoring the randomness of the response of the adjustable resources in a dead zone and a saturation zone, and carrying out modeling solution on related parameters of a linear zone, specifically comprising a dead zone inflection point r 1 Inflection point r of saturation region 2 And its ordinate r 3 And expressing the response curve of the linear region by a quadratic function:
η＝r 4 (δ-a)(δ-b) (1)
in the formula: r is 4 A and b are related parameters of the quadratic model; eta is the user response rate; delta is the excitation intensity;
the potential evaluation model conversion module is used for converting the adjustable resource response potential evaluation model into a solvable form according to the known key parameters of the power generation equipment and the user response model:
r in the formula 4 The parameters are random parameters considering the influence of uncertainty, and are defined by r 4 The random change of the user can describe the random characteristics of the adjustable resource participating in the response process, and the deterministic parameter r of the user is considered 1 、r 2 、r 3 With inter-individual variability and random parameter r 4 The method has similarity on the influence of the same type of adjustable resource response potential, and the random parameter r of the adjustable resource cluster with electricity utilization behavior similarity is analyzed 4 Therefore, the cluster adjustable resource response potential under the influence of uncertain factors is obtained;
and mining information through the day data in the multi-time scale index set to obtain the determining parameters r1, r2 and r3 in the adjustable resource response potential evaluation model:
reducing the dimension of the multi-time scale index set by using a principal component analysis method, and mining key parameters of the user adjustable potential model by using least square fitting on the basis to finally obtain the following relational expression:
in the formula: b 1j 、b 2j 、b 3j Coefficients of principal components that are key parameter influencing factors; u shape j A principal component representing a jth user electricity usage characteristic index extracted by a principal component analysis method; a is ij Coefficients for the ith index in the jth principal component formation; x is the number of i The value of the ith index is obtained;
substituting the historical response data of the user adjustable resources into the formula (2) to reversely solve the corresponding r 4 Values, thereby forming a random parametric historical data set based on the user historical response data; assuming that the random parameter satisfies normal distribution in a certain range, determining a distributed robust fuzzy set of the random parameter by a box type method:
wherein r is 1 、r 2 、r 3 Known deterministic model parameters; r is a radical of hydrogen 4 To satisfy a regular normal distribution, the mean value of the distribution is
Standard deviation of
Parameter mu 0 And σ 0 Is according to r 4 Carrying out point estimation on the historical response data set to obtain a probability estimation value;
a potential evaluation result acquisition module for considering the obtained probability estimation value as r 4 And (3) satisfying the normal distribution parameters, thereby obtaining a potential evaluation result of the adjustable resource participating in response scheduling:
wherein, the mean value reference value mu and the variance reference value sigma 2 Mean fuzzy value μ e And the variance blur value σ e The model indexes are model indexes for describing uncertainty parameters of user response potential, and the 4 indexes comprehensively reflect the uncertainty of the adjustable potential of the adjustable resource participation response service.
The intelligent scheduling module comprises a particle swarm optimization model establishing module and a whole network resource regulating and controlling module;
the particle swarm optimization model establishing module is used for establishing a particle swarm optimization model by taking the optimal total effect of new energy consumption as a target:
the specific optimization target is shown in formula (6) and comprises reducing power fluctuation and reducing new energy power abandon, the limiting conditions are shown in formula (8) and comprise equipment output limit and power fluctuation rate limit,
wherein T is new Indicating the number of periods during which the power fluctuation is calculated, lambda o,t For purchase price of electric energy, λ flu For power fluctuation loss cost factor, P G,t For actual contribution of new energy, P Go,t Capability of new energy to output, P Gmax,t 、 P Gmin,t Represents the upper and lower limit of the new energy equipment output in the t period, delta t Representing the new energy output power fluctuation, delta, over a period of t rise As an upper limit of the power increase rate, δ drop Δ t is the time interval between two periods, which is the lower limit of the power reduction rate;
the whole network resource regulation and control module comprises a main regulation and control center server and a regional center worker;
the general regulation and control center server is used for using the federal learning idea to regulate and control resources of the whole network, and specifically comprises the following steps:
the method comprises the following steps that (a) a master control center server transmits parameters w of a fixed particle swarm optimization algorithm model to each regional center;
step (b) based on the potential evaluation result of the adjustable resource, the worker in each regional center obtains power data of local adjustable resource participation demand response, local conventional particle swarm optimization is respectively carried out on the worker in each regional center by utilizing the source load power data information and a model parameter w transmitted by a general control center, and the adjustment quantity of new energy output or user load energy consumption of each region is calculated;
step (c), each regional center worker locally performs multiple gradient descent by using local data to obtain an updated gradient g, calculates a new parameter w and returns the new parameter w to the general control center server,
w←w-α·g (9)
w is a particle swarm optimization model parameter, alpha is a specific weight coefficient updating step length, and g is a gradient;
the master control center server collects new parameters w returned by each regional worker, carries out weighted average on the parameters, updates particle swarm model parameters, and then sends the parameters to each regional center worker;
and (e) repeating the steps (b) to (d) until the controllable source load resource scheduling in each area is completed.
According to the method, under the influence of uncertain factors, the cluster regulation potential evaluation of new energy equipment and users is realized, the data privacy of each area in the subsequent resource regulation process is protected based on the federal learning thought, and the safety of overall intelligent regulation is improved.
In another aspect, the present invention provides a new energy cluster consumption intelligent control system based on federal learning, including: a computer-readable storage medium and a processor;
the computer readable storage medium is used for storing executable instructions;
the processor is configured to read executable instructions stored in the computer-readable storage medium, and execute the new energy cluster digestion intelligent control method based on federated learning according to the first aspect.
In another aspect, the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the new energy cluster digestion intelligent control method based on federal learning in the first aspect.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (11)
1. A new energy cluster consumption intelligent control method based on federal learning is characterized in that: the method comprises the following steps:
collecting data of different new energy power generation equipment and power users, and establishing a multi-time scale index set, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets with different time scales;
based on the multi-time scale index set, evaluating the potential of the adjustable resource participating in response scheduling to obtain a potential evaluation result of the adjustable resource;
and aiming at the potential evaluation result of the adjustable resources, intelligently scheduling the resources of the whole network based on federal learning.
2. The new energy cluster digestion intelligent control method based on federal learning according to claim 1, characterized in that: the method comprises the following steps of collecting data of different new energy power generation equipment and power users, establishing a multi-time scale index set, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets with different time scales, and specifically comprises the following steps:
determining external influence factors of scheduling potential uncertainty of new energy output resources, collecting daily data, and establishing power generation characteristic index sets of different time scales;
the external influence factors of the scheduling potential uncertainty comprise weather factors and climate factors, the weather factors comprise wind speed, solar radiation degree, temperature and humidity, the climate factors comprise rain, sunny days and snow, and the power generation characteristic index sets of different time scales are obtained through statistical calculation of daily power generation data;
determining internal influence factors of scheduling potential uncertainty of user demand response resources, collecting data, and establishing power utilization characteristic index sets with different time scales;
the internal influence factors of the scheduling potential uncertainty comprise the equivalent heat capacity C, the equivalent heat resistance R, the energy efficiency ratio eta and the set temperature T of the polymer set Allowable temperature adjustment quantity delta T, regulation duration time delta T and user water consumption m n Ambient temperature T out And the electricity utilization characteristic index sets of different time scales are obtained by daily electricity generation data statistics and calculation.
3. The new energy cluster consumption intelligent control method based on federal learning according to claim 1, characterized in that: based on the multi-time scale index set, the potential of the adjustable resource participating in response scheduling is evaluated to obtain a potential evaluation result of the adjustable resource, and the method specifically comprises the following steps:
establishing an adjustable resource response potential evaluation model:
wherein r is 1 、r 2 、r 3 Is a known deterministic model parameter; r is 4 To satisfy a regular normal distribution, the mean value of the distribution is
Standard deviation of
Parameter mu 0 And σ 0 Is according to r 4 Carrying out point estimation on the historical response data set to obtain a probability estimation value;
the resulting probability estimate is taken as r 4 And (3) meeting the normal distribution parameters, thereby obtaining a potential evaluation result of the adjustable resource participating in response scheduling:
wherein, the mean value reference value mu and the variance reference value sigma 2 Mean fuzzy value μ e And variance ambiguity value σ e The model indexes are model indexes for describing uncertainty parameters of user response potential, and the 4 indexes comprehensively reflect the uncertainty of the adjustable potential of the adjustable resource participating response service.
4. The intelligent new energy cluster absorption regulation and control method based on federal learning according to claim 1, which is characterized in that: aiming at the potential evaluation result of the adjustable resources, intelligently scheduling the resources of the whole network based on federal learning, specifically comprising the following steps:
establishing a particle swarm optimization model by taking the optimal total effect of new energy consumption as a target:
the specific optimization target is shown in formula (6) and comprises reducing power fluctuation and reducing new energy power abandon, the limiting conditions are shown in formula (8) and comprise equipment output limit and power fluctuation rate limit,
wherein T is new Indicating the number of periods during which the power fluctuation is calculated, λ o,t For purchase price of electric energy, λ flu For power fluctuation loss cost factor, P G,t For actual output of new energy, P Go,t Capability of new energy to output, P Gmax,t 、P Gmin,t Represents the upper and lower limit of the new energy equipment output in the t period, delta t Representing the new energy output power fluctuation, delta, over a period of t rise As an upper limit of the power increase rate, δ drop To lower the power reduction rate, Δ t is the time interval between two periods.
5. The new energy cluster consumption intelligent control method based on federal learning according to claim 4, characterized in that: the method comprises the following steps that a general control center server uses a federal learning idea to regulate and control resources of the whole network, and specifically comprises the following steps:
the method comprises the following steps that (a) a master control center server transmits a parameter w of a fixed particle swarm optimization algorithm model to each regional center;
step (b) based on the potential evaluation result of the adjustable resources, the worker in each regional center obtains power data of local adjustable resources participating in demand response, local conventional particle swarm optimization is respectively carried out on the worker in each regional center by utilizing the source charge power data information and the model parameter w transmitted from the total regulation center, and the adjustment quantity of new energy output or user load energy consumption in each region is calculated;
step (c), each regional center worker locally performs multiple gradient descent by using local data to obtain an updated gradient g, calculates a new parameter w and returns the new parameter w to the general control center server,
w←w-α·g (8)
wherein w is a particle swarm optimization model parameter, alpha is a specific weight coefficient updating step length, and g is a gradient;
the master control center server collects new parameters w returned by each regional worker, carries out weighted average on the parameters, updates particle swarm model parameters, and then sends the parameters to each regional center worker;
and (e) repeating the steps (b) to (d) until the controllable source load resource scheduling in each area is completed.
6. The utility model provides a new forms of energy cluster consumption intelligent control device based on federal study which characterized in that includes:
the characteristic index set establishing module is used for collecting data of different new energy power generation equipment and power users and establishing a multi-time scale index set, wherein the multi-time scale index set comprises power generation and power utilization characteristic index sets with different time scales;
the potential evaluation module is used for evaluating the potential of the adjustable resource participating in response scheduling based on the multi-time scale index set to obtain a potential evaluation result of the adjustable resource;
and the intelligent scheduling module is used for intelligently scheduling the resources of the whole network based on federal learning aiming at the potential evaluation result of the adjustable resources.
7. The intelligent new energy cluster digestion regulation and control device based on federal learning of claim 6, wherein the characteristic index set establishment module comprises a power generation characteristic index set establishment module and a power utilization characteristic index set establishment module;
the power generation characteristic index set establishing module is used for determining external influence factors of scheduling potential uncertainty of the new energy output resources, collecting daily data and establishing power generation characteristic index sets with different time scales;
the external influence factors of the scheduling potential uncertainty comprise weather factors and climate factors, the weather factors comprise wind speed, solar radiation degree, temperature and humidity, the climate factors comprise rain, sunny days and snow, and the power generation characteristic index sets of different time scales are obtained through statistical calculation of daily power generation data;
the power utilization characteristic index set establishing module is used for determining internal influence factors of scheduling potential uncertainty of user demand response resources, collecting data and establishing power utilization characteristic index sets with different time scales.
The internal influence factors of the scheduling potential uncertainty comprise the equivalent heat capacity C, the equivalent heat resistance R, the energy efficiency ratio eta and the set temperature T of the polymer set Allowable temperature adjustment quantity delta T, regulation duration time delta T and user water consumption m n Ambient temperature T out And the market electricity price TOU, wherein the electricity utilization characteristic index sets of different time scales are obtained by statistical calculation of daily electricity generation data.
8. The intelligent regulation and control device of new energy cluster consumption based on federal learning of claim 7, comprising: the potential evaluation module comprises a potential evaluation model establishing module and a potential evaluation result obtaining module; wherein,
the potential evaluation model establishing module is used for establishing an adjustable resource response potential evaluation model:
wherein r is 1 、r 2 、r 3 Is a known deterministic model parameter; r is 4 To satisfy a regular normal distribution, wherein the mean of the distribution is
Standard deviation of
Parameter mu 0 And σ 0 Is according to r 4 Carrying out point estimation on the historical response data set to obtain a probability estimation value;
a potential evaluation result acquisition module for considering the obtained probability estimation value as r 4 And (3) satisfying the normal distribution parameters, thereby obtaining a potential evaluation result of the adjustable resource participating in response scheduling:
wherein, the mean value reference value mu and the variance reference value sigma 2 Mean fuzzy value μ e And variance ambiguity value σ e The model indexes are model indexes for describing uncertainty parameters of user response potential, and the 4 indexes comprehensively reflect the uncertainty of the adjustable potential of the adjustable resource participating response service.
9. The intelligent new energy cluster digestion regulation and control device based on federal learning of claim 7, wherein the intelligent scheduling module comprises a particle swarm optimization model building module and a whole network resource regulation and control module;
and the particle swarm optimization model establishing module is used for establishing a particle swarm optimization model by taking the optimal total effect of new energy consumption as a target.
10. The intelligent new energy cluster digestion regulation and control device based on federal learning of claim 9,
the whole network resource regulation and control module comprises a main regulation and control center server and a regional center worker;
the general regulation and control center server is used for using the federal learning idea to regulate and control resources of the whole network, and specifically comprises the following steps:
the method comprises the following steps that (a) a master control center server transmits a parameter w of a fixed particle swarm optimization algorithm model to each regional center;
step (b) based on the potential evaluation result of the adjustable resources, the worker in each regional center obtains power data of local adjustable resources participating in demand response, local conventional particle swarm optimization is respectively carried out on the worker in each regional center by utilizing the source charge power data information and the model parameter w transmitted from the total regulation center, and the adjustment quantity of new energy output or user load energy consumption in each region is calculated;
step (c), each regional center worker performs gradient descent for multiple times locally by using local data to obtain an updated gradient g, calculates a new parameter w and returns the new parameter w to the general control center server,
w←w-α·g (9)
w is a particle swarm optimization model parameter, alpha is a specific weight coefficient updating step length, and g is a gradient;
and (d) the master control center server collects new parameters w returned by each regional worker, performs weighted average on the parameters, updates the particle swarm model parameters, and then sends the parameters to each regional center worker.
And (e) repeating the steps (b) to (d) until the controllable source load resource scheduling in each area is completed.
11. The Federal learning-based intelligent new energy cluster absorption regulation and control device as claimed in claim 9, wherein the specific optimization objective of the particle swarm optimization model is shown in formula (6) and includes reducing power fluctuation and reducing new energy electricity abandonment, and the limiting conditions are shown in formula (8) and include equipment output limit and power fluctuation rate limit,
wherein T is new Indicating the number of periods during which the power fluctuation is calculated, lambda o,t For purchase price of electric energy, λ flu For power fluctuation loss cost factor, P G,t For actual contribution of new energy, P Go,t For new energy possible capacity, P Gmax,t 、P Gmin,t Represents the upper and lower limit of the new energy equipment output in the t period, delta t Represents t timeNew energy output power fluctuation of the segment, delta rise As an upper limit of the power increase rate, δ drop To lower the power reduction rate, Δ t is the time interval between two periods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210805292.0A CN115358441A (en) | 2022-07-08 | 2022-07-08 | New energy cluster consumption intelligent control method and device based on federal learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210805292.0A CN115358441A (en) | 2022-07-08 | 2022-07-08 | New energy cluster consumption intelligent control method and device based on federal learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115358441A true CN115358441A (en) | 2022-11-18 |
Family
ID=84032512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210805292.0A Pending CN115358441A (en) | 2022-07-08 | 2022-07-08 | New energy cluster consumption intelligent control method and device based on federal learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115358441A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117239739A (en) * | 2023-11-13 | 2023-12-15 | 国网冀北电力有限公司 | Method, device and equipment for predicting user side load by knowledge big model |
-
2022
- 2022-07-08 CN CN202210805292.0A patent/CN115358441A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117239739A (en) * | 2023-11-13 | 2023-12-15 | 国网冀北电力有限公司 | Method, device and equipment for predicting user side load by knowledge big model |
| CN117239739B (en) * | 2023-11-13 | 2024-02-02 | 国网冀北电力有限公司 | Method, device and equipment for predicting user side load by knowledge big model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Random forest solar power forecast based on classification optimization | |
| CN109462231B (en) | Load optimization scheduling method, system and storage medium for residential micro-grid | |
| Dong et al. | Wind power day-ahead prediction with cluster analysis of NWP | |
| US9639642B2 (en) | Time series forecasting ensemble | |
| CN108593990B (en) | Electricity stealing detection method based on electricity consumption behavior mode of electric energy user and application | |
| CN102999791A (en) | Power load forecasting method based on customer segmentation in power industry | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| CN105069525A (en) | All-weather 96-point daily load curve prediction and optimization correction system | |
| CN110380444B (en) | Capacity planning method for distributed wind power orderly access to power grid under multiple scenes based on variable structure Copula | |
| CN102509027B (en) | Wind powder combined predication method based on cross entropy theory | |
| CN105303250A (en) | Wind power combination prediction method based on optimal weight coefficient | |
| CN108429256A (en) | Operation of Electric Systems optimization method and terminal device | |
| CN112101689A (en) | Day-ahead intra-day scheduling method considering multi-type demand response uncertainty | |
| CN105224997A (en) | A kind of planning load forecasting method containing multiple uncertain factor impact | |
| Ahmadi et al. | A fuzzy inference model for short-term load forecasting | |
| CN104573857A (en) | Power grid load rate prediction method based on intelligent algorithm optimization and combination | |
| CN114372360A (en) | Method, terminal and storage medium for power load prediction | |
| CN109598408A (en) | A kind of year water regulation planning device for taking into account fair exploitation and importance | |
| Zhao et al. | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression | |
| CN116862551A (en) | New energy consumption price decision method considering user privacy protection | |
| CN115358441A (en) | New energy cluster consumption intelligent control method and device based on federal learning | |
| Souhe et al. | Forecasting of electrical energy consumption of households in a smart grid | |
| CN113139698A (en) | Load prediction method, device and equipment | |
| CN112330017A (en) | Power load prediction method, power load prediction device, electronic device, and storage medium | |
| He et al. | An Improved Coupling Model of Grey-System and Multivariate Linear Regression for Water Consumption Forecasting. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |