CN112418950A - Photovoltaic-related microgrid short-term load prediction and control method - Google Patents
Photovoltaic-related microgrid short-term load prediction and control method Download PDFInfo
- Publication number
- CN112418950A CN112418950A CN202011441602.2A CN202011441602A CN112418950A CN 112418950 A CN112418950 A CN 112418950A CN 202011441602 A CN202011441602 A CN 202011441602A CN 112418950 A CN112418950 A CN 112418950A
- Authority
- CN
- China
- Prior art keywords
- power generation
- load
- microgrid
- cost
- neural network
- 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 25
- 238000010248 power generation Methods 0.000 claims abstract description 199
- 238000013528 artificial neural network Methods 0.000 claims abstract description 71
- 238000012549 training Methods 0.000 claims abstract description 49
- 238000005457 optimization Methods 0.000 claims abstract description 38
- 239000002245 particle Substances 0.000 claims abstract description 11
- 238000009826 distribution Methods 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 24
- 238000003860 storage Methods 0.000 claims description 23
- 239000000446 fuel Substances 0.000 claims description 17
- 238000012423 maintenance Methods 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 15
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 12
- 230000003993 interaction Effects 0.000 claims description 10
- 230000005611 electricity Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 239000013256 coordination polymer Substances 0.000 claims description 6
- 239000003345 natural gas Substances 0.000 claims description 6
- 230000009194 climbing Effects 0.000 claims description 5
- 239000007789 gas Substances 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 4
- FGXWKSZFVQUSTL-UHFFFAOYSA-N domperidone Chemical compound C12=CC=CC=C2NC(=O)N1CCCN(CC1)CCC1N1C2=CC=C(Cl)C=C2NC1=O FGXWKSZFVQUSTL-UHFFFAOYSA-N 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 238000010977 unit operation Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 8
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 238000013486 operation strategy Methods 0.000 abstract description 2
- 238000011160 research Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000011418 maintenance treatment Methods 0.000 description 1
- 239000013589 supplement Substances 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a photovoltaic microgrid short-term load prediction and control method, which is characterized in that a power generation neural network and a load neural network are obtained by establishing a power generation training data set and a load training data set; and constructing each cost in the cost optimization target by using a power generation neural network and a load neural network, finally obtaining the optimal control parameters of the microgrid under the premise of the cost optimization target by using an artificial bee colony and particle optimization algorithm, and controlling the microgrid according to the control parameters. The method optimally controls the operation strategy of the microgrid, reduces the total operation cost of the microgrid, improves the environmental protection property, and can obviously improve the economic benefit of the microgrid while protecting the environment.
Description
Technical Field
The invention belongs to the technical field of intelligent power grids, and particularly relates to a photovoltaic-related micro-grid short-term load prediction and control method.
Background
With the increasing consumption of global non-renewable energy and the increasing demand of society for electric energy, increasing the utilization rate of energy and developing renewable energy become important directions for the development of smart grids. The microgrid has the advantages of full utilization of renewable energy sources such as solar energy, flexible configuration of a distributed power supply, reliable supply of nearby loads, flexible off-grid switching and the like, so that the microgrid is essential supplement for a large power grid and is widely applied to remote mountainous areas, islands, enterprises and other areas.
The photovoltaic power generation is widely applied as an important power generation unit of a microgrid due to the characteristics of cleanness, high efficiency and sustainability, but the photovoltaic power generation seriously depends on meteorological conditions such as solar radiation intensity, temperature, humidity and the like, and the power generation power cannot be artificially controlled, so that the power generation characteristic of the photovoltaic power generation has the characteristics of obvious intermittence, volatility and randomness.
The power load in the micro-grid system also has larger fluctuation, and compared with the characteristics of large load base number and obvious power load regularity of a large power grid, the load base number in the micro-grid is smaller, so that the micro-grid system is more easily influenced by factors such as production life, work shift and weather conditions of people to generate larger fluctuation.
The intermittency and randomness of photovoltaic power generation power of the micro-grid and the fluctuation of power load can greatly affect the stable operation of the micro-grid system, so that the energy exchange between a power generation end and a power utilization end in the micro-grid becomes extremely complex. In order to ensure the safe and stable operation of the microgrid, a power generation plan, a start-stop plan and a maintenance plan of a microgrid power generation unit are economically and reasonably arranged, unnecessary storage capacity of a storage battery is reduced, normal production and life of users are guaranteed, power generation cost is effectively reduced, economic benefits are improved, and accurate and reliable short-term prediction needs to be made on future power generation power and power utilization load of the microgrid system.
The short-term prediction of photovoltaic power generation and power load of the micro-grid is not only an important content when the micro-grid is operated off-grid, but also needs to be carried out when the micro-grid is operated in a grid-connected mode in order to ensure that the micro-grid does not have great influence on the large-grid and ensure the electric energy quality when the micro-grid is connected with the grid. According to the requirements of Q/GDW1617-2015 number 'technical specification of photovoltaic power station access power system', published by the national energy agency of China, a photovoltaic power generation power prediction system is required to be configured for photovoltaic power stations operated in a grid-connected mode, short-term photovoltaic power generation power prediction for 0-72 hours in the future is provided, meanwhile, DL/T1711-2017 number 'technical specification of power grid short-term and ultra-short-term load prediction' published by the energy agency also stipulates related technical specifications of short-term load prediction, the load of the power grid system is required to be provided mainly in the next day and can be extended to the short-term prediction in the multiple days, and related requirements are respectively made on the time resolution and the prediction precision of prediction results.
In addition to the short-term prediction of the microgrid and the photovoltaic, load optimization scheduling should also be the first problem to be solved. As a new type of power system network, micro-grids are no exception. The energy balance of the micro-grid is required to ensure that the output power of each power supply element in the micro-grid meets the load requirement in the power grid under the condition of a set control strategy, and the safe, stable and economic operation of the micro-grid is realized. Compared with the traditional research on optimization and scheduling strategies of the power grid, the research on the optimization scheduling model of the micro-grid is very complex. Since the micro-grid increases the thermal load and the electrical load in the corresponding area, it should be ensured that the supply and demand of the thermal load can be balanced, in addition to the consideration of the electrical power balance of the system. Meanwhile, different distributed power generation modes in the micro-grid are different, so that the micro-grid has different operation characteristics. And because the power capacity of the distributed power supply is small, the power balance of the microgrid can be obviously influenced by the change of the individual load. In addition, the optimization scheduling research of the micro-grid needs to fully pay attention to the environmental influence of the distributed power supply after grid connection while calculating the economic cost of power generation. These considerations change the optimal scheduling problem of the microgrid from a single-objective optimization problem to a multi-objective optimization problem.
Therefore, the optimal scheduling of the microgrid should fully consider the economic impact and the environmental impact in the operation process of the microgrid in an integral mode, and a photovoltaic microgrid short-term load prediction and control method is provided for the purpose.
Disclosure of Invention
The invention aims to provide a photovoltaic-related microgrid short-term load prediction and control method, and solves the technical problems that the microgrid power generation, operation cost and grid benefit are too small on the basis of safety and stability in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a photovoltaic-related microgrid short-term load prediction and control method comprises the following steps:
step 1: establishing a power generation training data set according to historical photovoltaic power generation data, historical solar radiation intensity, historical temperature, historical humidity and historical meteorological types;
establishing a load training data set according to historical load data, historical temperature, historical humidity and day type;
step 2: rejecting abnormal data in the historical photovoltaic power generation data, taking a meteorological type as a clustering type, and establishing a power generation similar day screening model of the optimized historical photovoltaic power generation data;
rejecting abnormal data in the historical load data, taking a day type as a clustering type, and establishing a load similarity day screening model of the optimized historical load data;
and step 3:
and (3) generating capacity neural network training:
selecting historical photovoltaic power generation data clustered by corresponding weather types from the power generation similar day screening model according to the weather types of the days to be predicted; selecting training data of corresponding weather types in the power generation training data set according to the weather types of the days to be predicted; training the power generation neural network by taking the obtained historical photovoltaic power generation data and training data as a data set for training the power generation neural network;
the weather type of the day to be predicted is used as the input of the power generation neural network, and the photovoltaic power generation amount of the day to be predicted is obtained;
training a load neural network:
selecting historical load data of corresponding day type clusters from the load similar day screening model according to the day type of the day to be predicted; selecting training data of a corresponding day type in the load training data set according to the day type of the day to be predicted; training the load neural network by taking the acquired historical load data and training data as a data set for training the load neural network;
taking the day type of the day to be predicted as the input of the power generation neural network, and acquiring the load of the day to be predicted;
and 4, step 4: obtaining a current-day cost optimization target and constraint conditions, wherein the current-day cost optimization target comprises the following steps: the method comprises the following steps of fuel consumption cost, power generation unit operation management cost, maintenance cost and interaction cost of a micro-grid and a power distribution network, wherein the constraint conditions comprise: electric power balance constraint, cold or thermal power balance constraint, and power generation capacity limit constraint;
and 5: according to the estimated current day power generation amount of the power generation amount neural network training, the estimated current day load of the load neural network, the optimization target and the constraint condition, solving each control parameter of the microgrid corresponding to the lowest total cost of the current day and the lowest total cost of the current day, and controlling each parameter of the microgrid according to each control parameter of the microgrid.
Further, the obtaining formula of the cost optimization target in the step 4 is as follows:
min C1＝CG，i+COM，i+CDP，i+CGrid
wherein, minC1Optimizing the objective for cost; cG，iThe fuel consumption cost of the ith power generation unit in the microgrid; cOM，iManaging the operation cost of the ith power generation unit in the microgrid; cDP，iDepreciation maintenance cost of the ith power generation unit in the microgrid; cGridThe interaction cost of the micro-grid and the power distribution network is obtained;
the calculation formula of the fuel consumption cost is as follows:
wherein, CiFuel cost for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; cngIs the natural gas price; LHVngIs natural gas with low heat value; etaitFor the ith power generation unit type at time point PitThe corresponding unit efficiency;
the calculation formula of the operation management cost is as follows:
therein, OMiAn operational management cost for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; kOMitThe operation and maintenance cost coefficient of the ith power generation unit type at the time t;
the depreciation maintenance cost calculation formula is as follows:
ADCCi＝ins costi·CFRi
wherein DPiDepreciation maintenance costs for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; ADCCiAnnual depreciation capital for the ith power generation unit type; pN，iMaximum output power for the ith power generation unit type; cfiA capacity factor for the ith power generation unit type; ins costiInstallation cost per unit capacity for the ith power generation unit type; CFRiA capital recovery factor for the ith power generation unit type; diAn age rate for the ith power generation unit type; l isiDepreciation age for the ith power generation unit type;
the calculation formula of the interaction cost of the micro-grid and the power distribution network is as follows:
CGrid＝CPt·CGPt-CSt·CSPt
wherein, CPtPurchasing electricity price from the power distribution network for the microgrid at the time t; CGPtThe electric quantity purchased from the microgrid to the power distribution network at the moment t; CStSelling electricity to the power distribution network for the microgrid at the moment t; CSPtSelling electricity from the microgrid to the power distribution network at the moment t; CGPtAnd CSPtAnd (3) calculating the photovoltaic power generation output by the power generation neural network in the step (3) and the load output by the load neural network.
Further, the calculation formula of the electric power balance constraint in the step 4 is as follows:
wherein, PLoadCalculating all the electric loads of the whole microgrid system by the photovoltaic power generation output by the power generation neural network in the step 3 and the load output by the load neural network; pDNSupplying power to the distribution network; n is N generating unit types; pDG，iCalculating the output power of the ith power generation unit type according to the photovoltaic power generation output by the power generation neural network in the step 3;
the cold/thermal power balance constraint is calculated as follows:
WLoad＝WMT+WFC
in the formula, WLoadCalculating all heat/cold loads of the whole microgrid system according to the photovoltaic power generation output by the power generation neural network and the load output by the load neural network in the step 3; wMTSupplying heat/cold for the micro gas turbine; wFCHeat supply for the fuel cell;
the calculation formula of the power generation capacity limit constraint is as follows:
wherein, PDG，iCalculating the output power of the ith power generation unit type according to the photovoltaic power generation output by the power generation neural network in the step 3;
the minimum safe output for the ith power generation unit type;
the maximum safe output of the ith power generation unit type.
Furthermore, the constraint conditions further comprise controllable micro-source climbing rate constraint, tie line transmission capacity constraint and storage battery storage capacity constraint;
the calculation formula of the controllable micro-source climbing rate constraint is as follows:
wherein, Pup，m(t) the active power output of the mth controllable micro source increased at the time t; pup，m(t-1) the active power output increased by the mth controllable micro source at the time of t-1; pdown，m(t) the active power output of the mth controllable micro source reduced at the moment t; pdown，m(t-1) the active power output of the mth controllable micro source reduced at the time of t-1; rup，mAn increased active power output limit value for the mth controllable micro-source; rdown，mA reducible active power output limit value for the mth controllable micro-source;
the equation for the tie line transmission capacity constraint is as follows:
wherein, Pline，tThe transmission capacity of the microgrid and the power distribution network at the moment t;
the lower limit of the transmission capacity on a connecting line between the micro-grid and the distribution network;
the transmission capacity upper limit on a connecting line between the micro-grid and the power distribution network;
the calculation formula of the storage capacity constraint of the storage battery is as follows:
SOCmin≤SOCt≤SOCmax
therein, SOCtThe state of charge of the storage battery at the moment t; SOCminThe minimum value allowed by the state of charge of the storage battery; SOCmaxThe maximum value allowed by the state of charge of the storage battery.
Further, the specific steps of step 5 are as follows:
step 51: establishing a Pareto optimal point set, wherein the point set formula is as follows:
wherein F (x) is the individual cost of the cost optimization objective of the day;
step 52: using the microgrid control parameters and the constraint conditions as input parameters and constraint conditions of an artificial bee colony algorithm and a particle swarm optimization algorithm;
step 53: respectively solving the optimal solution of the Pareto optimal point set by using an artificial bee colony algorithm and a particle swarm optimization algorithm, and when the termination condition of the artificial bee colony algorithm is not met, exchanging the optimal solutions of the artificial bee colony algorithm and the particle swarm optimization algorithm, and continuously iterating by using the exchanged optimal solutions;
and when the current iteration times exceed the preset maximum iteration times, ending the iteration process, outputting the optimal solution of the artificial bee colony algorithm as the optimal microgrid control parameter, and controlling each parameter of the microgrid according to the optimal microgrid control parameter.
Compared with the prior art, the invention has the following beneficial effects:
1. designing and realizing a photovoltaic power generation short-term prediction model based on an LSTM neural network, performing short-term prediction on future photovoltaic power generation power, and simultaneously predicting the photovoltaic power generation power in rainfall weather; a micro-grid load short-term prediction model based on an LSTM neural network is designed and realized, the future load is predicted in a short term, meanwhile, the load of a holiday type is predicted, and certain accuracy is achieved.
2. The method has the advantages that a micro-grid optimization control model based on a multi-objective optimization function and an artificial bee colony algorithm is established, the operation strategy of the micro-grid is optimally controlled, the operation total cost of the micro-grid is reduced, the environmental protection performance is improved, and the economic benefit of the micro-grid can be obviously improved while the environment is protected.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and not to be construed as limiting the invention in any way, and in which:
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a flow chart of a neural network training for power generation in an embodiment of the present invention;
FIG. 3 is a flow chart of load neural network training in an embodiment of 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for predicting and controlling a short-term load of a photovoltaic-related microgrid, including:
step 1: establishing a power generation training data set according to historical photovoltaic power generation data, historical solar radiation intensity, historical temperature, historical humidity and historical meteorological types;
establishing a load training data set according to historical load data, historical temperature, historical humidity and day type;
step 2: rejecting abnormal data in the historical photovoltaic power generation data, taking a meteorological type as a clustering type, and establishing a power generation similar day screening model of the optimized historical photovoltaic power generation data;
rejecting abnormal data in the historical load data, taking a day type as a clustering type, and establishing a load similarity day screening model of the optimized historical load data;
as shown in fig. 2-3, step 3:
and (3) generating capacity neural network training:
selecting historical photovoltaic power generation data clustered by corresponding weather types from the power generation similar day screening model according to the weather types of the days to be predicted; selecting training data of corresponding weather types in the power generation training data set according to the weather types of the days to be predicted; training the power generation neural network by taking the obtained historical photovoltaic power generation data and training data as a data set for training the power generation neural network;
the weather type of the day to be predicted is used as the input of the power generation neural network, and the photovoltaic power generation amount of the day to be predicted is obtained;
training a load neural network:
selecting historical load data of corresponding day type clusters from the load similar day screening model according to the day type of the day to be predicted; selecting training data of a corresponding day type in the load training data set according to the day type of the day to be predicted; training the load neural network by taking the acquired historical load data and training data as a data set for training the load neural network;
taking the day type of the day to be predicted as the input of the power generation neural network, and acquiring the load of the day to be predicted;
and 4, step 4: obtaining a current-day cost optimization target and constraint conditions, wherein the current-day cost optimization target comprises the following steps: the method comprises the following steps of fuel consumption cost, power generation unit operation management cost, maintenance cost and interaction cost of a micro-grid and a power distribution network, wherein the constraint conditions comprise: electric power balance constraint, cold or heat power balance constraint, power generation capacity limit constraint, controllable micro-source climbing rate constraint, tie line transmission capacity constraint and storage battery storage capacity constraint;
the cost optimization objective is obtained by the following formula:
min C1＝CG，i+COM，i+CDP，i+CGrid
wherein, minC1Optimizing the objective for cost; cG，iThe fuel consumption cost of the ith power generation unit in the microgrid; cOM，iManaging the operation cost of the ith power generation unit in the microgrid; cDP，iDepreciation maintenance cost of the ith power generation unit in the microgrid; cGridThe interaction cost of the micro-grid and the power distribution network is obtained;
the fuel consumption cost mainly refers to the fuel consumption cost required by the operation of a micro gas turbine and a fuel cell in a micro power grid, and the calculation formula is as follows:
wherein, CiFuel cost for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; cngIs the natural gas price; LHVngIs natural gas with low heat value; etaitFor the ith power generation unit type at time point PitThe corresponding unit efficiency;
the operation management cost refers to the management cost of equipment and personnel in the micro-grid system, and the calculation formula is as follows:
therein, OMiAn operational management cost for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; kOMitThe operation and maintenance cost coefficient of the ith power generation unit type at the time t;
depreciation maintenance cost refers to the phenomenon that abrasion and aging of a unit inevitably occur in the continuous operation process of a distributed power supply, when the problem occurs, maintenance treatment needs to be carried out on the corresponding unit, the generated cost is converted into depreciation maintenance cost of a power generation unit, and the calculation formula is as follows:
ADCCi＝ins costi·CFRi
wherein DPiDepreciation maintenance costs for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; ADCCiAnnual depreciation capital for the ith power generation unit type; pN，iMaximum output power for the ith power generation unit type; cfiA capacity factor for the ith power generation unit type; ins costiInstallation cost per unit capacity for the ith power generation unit type; CFRiA capital recovery factor for the ith power generation unit type; diAn age rate for the ith power generation unit type; l isiDepreciation age for the ith power generation unit type;
the interaction cost of the micro-grid and the power distribution network is low, and the micro-grid and the power distribution network are sometimes operated in a grid-connected mode in order to ensure that a system can work reliably. The electric energy exchange cost brought by the process is called the interaction cost of the micro-grid and the power distribution network, and the calculation formula is as follows:
CGrid＝CPt·CGPt-CSt·CSPt
wherein, CPtPurchasing electricity price from the power distribution network for the microgrid at the time t; CGPtThe electric quantity purchased from the microgrid to the power distribution network at the moment t; CStSelling electricity to the power distribution network for the microgrid at the moment t; CSPtSelling electricity from the microgrid to the power distribution network at the moment t; CGPtAnd CSPtAccording to the photovoltaic power generation output by the power generation neural network in the step 3 and the load output by the load neural network, calculating to obtain the photovoltaic power generation output;
the safety of the power grid is ensured while the operation economy of the micro power grid is ensured, so that the conditions of power balance, power generation unit capacity limitation and the like in the micro power grid system need to be restrained;
the calculation formula of the electric power balance constraint is as follows:
wherein, PLoadCalculating all the electric loads of the whole microgrid system by the photovoltaic power generation output by the power generation neural network in the step 3 and the load output by the load neural network; pDNSupplying power to the distribution network; n is N generating unit types; pDG，iCalculating the output power of the ith power generation unit type according to the photovoltaic power generation output by the power generation neural network in the step 3;
the cold/thermal power balance constraint is calculated as follows:
WLoad＝WMT+WFC
in the formula, WLoadCalculating all heat/cold loads of the whole microgrid system according to the photovoltaic power generation output by the power generation neural network and the load output by the load neural network in the step 3; wMTHeating/cooling for micro gas turbineAn amount; wFCHeat supply for the fuel cell;
the calculation formula of the power generation capacity limit constraint is as follows:
wherein, PDG，iCalculating the output power of the ith power generation unit type according to the photovoltaic power generation output by the power generation neural network in the step 3;
the minimum safe output for the ith power generation unit type;
the maximum safe output of the ith power generation unit type.
The calculation formula of the controllable micro-source climbing rate constraint is as follows:
wherein, Pup，m(t) the active power output of the mth controllable micro source increased at the time t; pup，m(t-1) the active power output increased by the mth controllable micro source at the time of t-1; pdown，m(t) the active power output of the mth controllable micro source reduced at the moment t; pdown，m(t-1) the active power output of the mth controllable micro source reduced at the time of t-1; rup，mAn increased active power output limit value for the mth controllable micro-source; rdown，mA reducible active power output limit value for the mth controllable micro-source;
the equation for the tie line transmission capacity constraint is as follows:
wherein, Pline，tThe transmission capacity of the microgrid and the power distribution network at the moment t;
the lower limit of the transmission capacity on a connecting line between the micro-grid and the distribution network;
the transmission capacity upper limit on a connecting line between the micro-grid and the power distribution network;
the calculation formula of the storage capacity constraint of the storage battery is as follows:
SOCmin≤SOCt≤SOCmax
therein, SOCtThe state of charge of the storage battery at the moment t; SOCminThe minimum value allowed by the state of charge of the storage battery; SOCmaxThe maximum value allowed by the state of charge of the storage battery;
and 5: according to the estimated current day power generation amount of the power generation amount neural network training, the estimated current day load of the load neural network, an optimization target and constraint conditions, solving each control parameter of the microgrid corresponding to the lowest total cost of the current day and the lowest total cost of the current day, and controlling each parameter of the microgrid according to each control parameter of the microgrid, the specific steps are as follows:
the artificial bee colony algorithm has good robustness and wide applicability, can be applied to various optimization solving problems, can perform global search elegantly by a Particle Swarm Optimization (PSO), is high in convergence speed, can expand a field when the algorithm has a problem of local extremum, sets the field as a new optimization range, and helps the algorithm to accelerate the speed of contacting local constraint. The optimal values of the two are interchanged in the iteration process, so that the selection accuracy of the optimal value can be improved on the basis of checking whether the optimal value is correct or not.
Step 51: establishing a Pareto optimal point set, wherein the point set formula is as follows:
wherein F (x) is the individual cost of the cost optimization objective of the day;
step 52: using the microgrid control parameters and the constraint conditions as input parameters and constraint conditions of an artificial bee colony algorithm and a particle swarm optimization algorithm;
step 53: respectively solving the optimal solution of the Pareto optimal point set by using an artificial bee colony algorithm and a particle swarm optimization algorithm, and when the termination condition of the artificial bee colony algorithm is not met, exchanging the optimal solutions of the artificial bee colony algorithm and the particle swarm optimization algorithm, and continuously iterating by using the exchanged optimal solutions;
and when the current iteration times exceed the preset maximum iteration times, ending the iteration process, outputting the optimal solution of the artificial bee colony algorithm as the optimal microgrid control parameter, and controlling each parameter of the microgrid according to the optimal microgrid control parameter.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (5)
1. A photovoltaic-related microgrid short-term load prediction and control method is characterized by comprising the following steps:
step 1: establishing a power generation training data set according to historical photovoltaic power generation data, historical solar radiation intensity, historical temperature, historical humidity and historical meteorological types;
establishing a load training data set according to historical load data, historical temperature, historical humidity and day type;
step 2: rejecting abnormal data in the historical photovoltaic power generation data, taking a meteorological type as a clustering type, and establishing a power generation similar day screening model of the optimized historical photovoltaic power generation data;
rejecting abnormal data in the historical load data, taking a day type as a clustering type, and establishing a load similarity day screening model of the optimized historical load data;
and step 3:
and (3) generating capacity neural network training:
selecting historical photovoltaic power generation data clustered by corresponding weather types from the power generation similar day screening model according to the weather types of the days to be predicted; selecting training data of corresponding weather types in the power generation training data set according to the weather types of the days to be predicted; training the power generation neural network by taking the obtained historical photovoltaic power generation data and training data as a data set for training the power generation neural network;
the weather type of the day to be predicted is used as the input of the power generation neural network, and the photovoltaic power generation amount of the day to be predicted is obtained;
training a load neural network:
selecting historical load data of corresponding day type clusters from the load similar day screening model according to the day type of the day to be predicted; selecting training data of a corresponding day type in the load training data set according to the day type of the day to be predicted; training the load neural network by taking the acquired historical load data and training data as a data set for training the load neural network;
taking the day type of the day to be predicted as the input of the power generation neural network, and acquiring the load of the day to be predicted;
and 4, step 4: obtaining a current-day cost optimization target and constraint conditions, wherein the current-day cost optimization target comprises the following steps: the method comprises the following steps of fuel consumption cost, power generation unit operation management cost, maintenance cost and interaction cost of a micro-grid and a power distribution network, wherein the constraint conditions comprise: electric power balance constraint, cold or thermal power balance constraint, and power generation capacity limit constraint;
and 5: according to the estimated current day power generation amount of the power generation amount neural network training, the estimated current day load of the load neural network, the optimization target and the constraint condition, solving each control parameter of the microgrid corresponding to the lowest total cost of the current day and the lowest total cost of the current day, and controlling each parameter of the microgrid according to each control parameter of the microgrid.
2. The photovoltaic-related microgrid short-term load prediction and control method as claimed in claim 1, characterized in that the cost optimization objective in step 4 is obtained by the following formula:
minC1＝CG，i+COM，i+CDP，i+CGrid
wherein, minC1Optimizing the objective for cost; cG，iThe fuel consumption cost of the ith power generation unit in the microgrid; cOM，iManaging the operation cost of the ith power generation unit in the microgrid; cDP，iDepreciation maintenance cost of the ith power generation unit in the microgrid; cGridThe interaction cost of the micro-grid and the power distribution network is obtained;
the calculation formula of the fuel consumption cost is as follows:
wherein, CiFuel cost for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; cngIs the natural gas price; LHVngIs natural gas with low heat value; etaitFor the ith power generation unit type at time point PitThe corresponding unit efficiency;
the calculation formula of the operation management cost is as follows:
therein, OMiAn operational management cost for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; kOMitThe operation and maintenance cost coefficient of the ith power generation unit type at the time t;
the depreciation maintenance cost calculation formula is as follows:
ADCCi＝ins costi·CFRi
wherein DPiDepreciation maintenance costs for the ith power generation unit type; n is N generating unit types; pitCalculating the output power of the ith power generation unit type at the time t according to the photovoltaic power generation output by the power generation neural network in the step 3; ADCCiAnnual depreciation capital for the ith power generation unit type; pN，iMaximum output power for the ith power generation unit type; cfiA capacity factor for the ith power generation unit type; ins costiInstallation cost per unit capacity for the ith power generation unit type; CFRiA capital recovery factor for the ith power generation unit type; diAn age rate for the ith power generation unit type; l isiDepreciation age for the ith power generation unit type;
the calculation formula of the interaction cost of the micro-grid and the power distribution network is as follows:
CGrid＝CPt·CGPt-CSt·CSPt
wherein, CPtPurchasing electricity price from the power distribution network for the microgrid at the time t; CGPtThe electric quantity purchased from the microgrid to the power distribution network at the moment t; CStSelling electricity to the power distribution network for the microgrid at the moment t; CSPtSelling electricity from the microgrid to the power distribution network at the moment t; CGPtAnd CSPtAnd (3) calculating the photovoltaic power generation output by the power generation neural network in the step (3) and the load output by the load neural network.
3. The photovoltaic-related microgrid short-term load prediction and control method as claimed in claim 1 or 2, characterized in that the calculation formula of the electric power balance constraint in the step 4 is as follows:
wherein, PLoadCalculating all the electric loads of the whole microgrid system by the photovoltaic power generation output by the power generation neural network in the step 3 and the load output by the load neural network; pDNSupplying power to the distribution network; n is N generating unit types; pDG，iCalculating the output power of the ith power generation unit type according to the photovoltaic power generation output by the power generation neural network in the step 3;
the cold/thermal power balance constraint is calculated as follows:
WLoad＝WMT+WFC
in the formula, WLoadCalculating all heat/cold loads of the whole microgrid system according to the photovoltaic power generation output by the power generation neural network and the load output by the load neural network in the step 3; wMTSupplying heat/cold for the micro gas turbine; wFCHeat supply for the fuel cell;
the calculation formula of the power generation capacity limit constraint is as follows:
wherein, PDG，iCalculating the output power of the ith power generation unit type according to the photovoltaic power generation output by the power generation neural network in the step 3;
the minimum safe output for the ith power generation unit type;
the maximum safe output of the ith power generation unit type.
4. The photovoltaic-related microgrid short-term load prediction and control method as claimed in claim 3, characterized in that the constraint conditions further include a controllable microgrid ramp rate constraint, a tie line transmission capacity constraint, a storage battery storage capacity constraint;
the calculation formula of the controllable micro-source climbing rate constraint is as follows:
wherein, Pup，m(t) the active power output of the mth controllable micro source increased at the time t; pup，m(t-1) the active power output increased by the mth controllable micro source at the time of t-1; pdown，m(t) the active power output of the mth controllable micro source reduced at the moment t; pdown，m(t-1) the active power output of the mth controllable micro source reduced at the time of t-1; rup，mAn increased active power output limit value for the mth controllable micro-source; rdown，mA reducible active power output limit value for the mth controllable micro-source;
the equation for the tie line transmission capacity constraint is as follows:
wherein, Pline，tThe transmission capacity of the microgrid and the power distribution network at the moment t;
the lower limit of the transmission capacity on a connecting line between the micro-grid and the distribution network;
the transmission capacity upper limit on a connecting line between the micro-grid and the power distribution network;
the calculation formula of the storage capacity constraint of the storage battery is as follows:
SOCmin≤SOCt≤SOCmax
therein, SOCtThe state of charge of the storage battery at the moment t; SOCminIn the form of a charge for a storage batteryMinimum allowed state; SOCmaxThe maximum value allowed by the state of charge of the storage battery.
5. The photovoltaic-related microgrid short-term load forecasting and control method as claimed in claim 1, characterized in that the specific steps of the step 5 are as follows:
step 51: establishing a Pareto optimal point set, wherein the point set formula is as follows:
wherein F (x) is the individual cost of the cost optimization objective of the day;
step 52: using the microgrid control parameters and the constraint conditions as input parameters and constraint conditions of an artificial bee colony algorithm and a particle swarm optimization algorithm;
step 53: respectively solving the optimal solution of the Pareto optimal point set by using an artificial bee colony algorithm and a particle swarm optimization algorithm, and when the termination condition of the artificial bee colony algorithm is not met, exchanging the optimal solutions of the artificial bee colony algorithm and the particle swarm optimization algorithm, and continuously iterating by using the exchanged optimal solutions;
and when the current iteration times exceed the preset maximum iteration times, ending the iteration process, outputting the optimal solution of the artificial bee colony algorithm as the optimal microgrid control parameter, and controlling each parameter of the microgrid according to the optimal microgrid control parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011441602.2A CN112418950A (en) | 2020-12-08 | 2020-12-08 | Photovoltaic-related microgrid short-term load prediction and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011441602.2A CN112418950A (en) | 2020-12-08 | 2020-12-08 | Photovoltaic-related microgrid short-term load prediction and control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112418950A true CN112418950A (en) | 2021-02-26 |
Family
ID=74776080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011441602.2A Pending CN112418950A (en) | 2020-12-08 | 2020-12-08 | Photovoltaic-related microgrid short-term load prediction and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112418950A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191575A (en) * | 2021-06-16 | 2021-07-30 | 广东电网有限责任公司 | Power distribution network maintenance power failure mode optimization method and device, terminal and storage medium |
| CN115145983A (en) * | 2022-08-04 | 2022-10-04 | 陕西理工大学 | Method for determining daily generated energy of photovoltaic power generation system of new energy user |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104065072A (en) * | 2014-06-16 | 2014-09-24 | 四川大学 | Micro-grid operation optimization method based on dynamic electricity price |
| CN104269849A (en) * | 2014-10-17 | 2015-01-07 | 国家电网公司 | Energy managing method and system based on building photovoltaic micro-grid |
| CN106058914A (en) * | 2016-05-27 | 2016-10-26 | 国电南瑞科技股份有限公司 | Voltage optimization method of distribution network generation predication technology based on Elman algorithm |
| CN107590607A (en) * | 2017-09-19 | 2018-01-16 | 合肥工业大学 | A kind of micro-capacitance sensor Optimal Scheduling and method based on photovoltaic prediction |
-
2020
- 2020-12-08 CN CN202011441602.2A patent/CN112418950A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104065072A (en) * | 2014-06-16 | 2014-09-24 | 四川大学 | Micro-grid operation optimization method based on dynamic electricity price |
| CN104269849A (en) * | 2014-10-17 | 2015-01-07 | 国家电网公司 | Energy managing method and system based on building photovoltaic micro-grid |
| CN106058914A (en) * | 2016-05-27 | 2016-10-26 | 国电南瑞科技股份有限公司 | Voltage optimization method of distribution network generation predication technology based on Elman algorithm |
| CN107590607A (en) * | 2017-09-19 | 2018-01-16 | 合肥工业大学 | A kind of micro-capacitance sensor Optimal Scheduling and method based on photovoltaic prediction |
Non-Patent Citations (1)
| Title |
|---|
| 王琪玮: "（"微电网负荷预测及运行控制方法研究"", 中国优秀硕士学位论文全文数据库 工程科技II辑》, no. 01, 15 January 2019 (2019-01-15), pages 042 - 2100 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191575A (en) * | 2021-06-16 | 2021-07-30 | 广东电网有限责任公司 | Power distribution network maintenance power failure mode optimization method and device, terminal and storage medium |
| CN115145983A (en) * | 2022-08-04 | 2022-10-04 | 陕西理工大学 | Method for determining daily generated energy of photovoltaic power generation system of new energy user |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Integrated size and energy management design of battery storage to enhance grid integration of large-scale PV power plants | |
| CN110119886B (en) | Active distribution network dynamic planning method | |
| Chen et al. | Smart energy management system for optimal microgrid economic operation | |
| Begovic et al. | Impact of renewable distributed generation on power systems | |
| CN111293691A (en) | Micro-grid multi-time scale optimization scheduling method based on model predictive control | |
| Villarreal et al. | Designing a sustainable and distributed generation system for semiconductor wafer fabs | |
| CN116151436B (en) | Household-user-oriented photovoltaic building energy planning method and system | |
| Li et al. | Optimal configuration of photovoltaic energy storage capacity for large power users | |
| Jahanbani et al. | Optimum design of a hybrid renewable energy system | |
| CN112688328B (en) | Time coordination energy optimal configuration method for AC/DC hybrid micro-grid | |
| CN112699562B (en) | Method and terminal for constructing power distribution network architecture | |
| KR20130074045A (en) | A control method for controlling energy of building based ob microgrid and system for same | |
| CN112418950A (en) | Photovoltaic-related microgrid short-term load prediction and control method | |
| CN115693652A (en) | Power distribution network frame optimization method and device based on power balance and performance cost | |
| CN108667071B (en) | Accurate control calculation method for load of active power distribution network | |
| CN117748622A (en) | Micro-grid polymorphic coordination control method and system | |
| CN113746105A (en) | Optimal control method, device, equipment and storage medium for power demand response | |
| CN117578449A (en) | Multi-energy micro-energy network optimization scheduling method considering uncertainty of renewable energy sources | |
| Ciornei et al. | Real-time optimal scheduling for prosumers resilient to regulatory changes | |
| CN115693793B (en) | Regional micro-grid energy optimization control method | |
| Elkazaz et al. | Optimizing distributed generation operation for residential application based on automated systems | |
| Morawski et al. | Balancing energy budget in prosumer water plant installations with explicit consideration of flow delay | |
| Zhao et al. | Multi-objective Optimal Operation of Microgrid Based on NSGA-III Algorithm | |
| Liu et al. | Micro grid energy management based on two-stage robust optimization | |
| CN113783213B (en) | Centralized energy storage power station site selection and volume fixation two-stage optimization method |
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 |