CN118572778B - Deep learning-based intelligent micro-grid cooperative control system and method - Google Patents
Deep learning-based intelligent micro-grid cooperative control system and method Download PDFInfo
- Publication number
- CN118572778B CN118572778B CN202411010368.6A CN202411010368A CN118572778B CN 118572778 B CN118572778 B CN 118572778B CN 202411010368 A CN202411010368 A CN 202411010368A CN 118572778 B CN118572778 B CN 118572778B
- Authority
- CN
- China
- Prior art keywords
- power generation
- power
- data
- wind
- cooperative control
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000013135 deep learning Methods 0.000 title claims abstract description 26
- 238000010248 power generation Methods 0.000 claims abstract description 183
- 238000012795 verification Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims description 31
- 238000005286 illumination Methods 0.000 claims description 27
- 238000012360 testing method Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 16
- 230000005540 biological transmission Effects 0.000 claims description 9
- 239000002131 composite material Substances 0.000 claims description 9
- 230000005611 electricity Effects 0.000 claims description 8
- 238000004146 energy storage Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000007599 discharging Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 10
- 230000000295 complement effect Effects 0.000 abstract description 5
- 230000002079 cooperative effect Effects 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241001672018 Cercomela melanura Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 150000001875 compounds Chemical group 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
- H02J2300/26—The renewable source being solar energy of photovoltaic origin involving maximum power point tracking control for photovoltaic sources
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention belongs to the technical field of intelligent micro-grid cooperative control systems, and particularly relates to an intelligent micro-grid cooperative control system and method based on deep learning, which are used for acquiring historical weather data, power generation and power generation operation cost of a power generation area; acquiring weather forecast data of a power generation area, and calibrating the weather forecast data through historical weather data; constructing a micro-grid cooperative control system power cost model, sequentially inputting a data set into the model, judging whether a verification result meets the requirement, if so, inputting the calibrated weather forecast data into the model, and outputting predicted wind power generation power, predicted photovoltaic power generation power and predicted operation cost; and collecting current weather data and current running cost of the power generation region in real time, and running the intelligent micro-grid cooperative control system with the corrected wind power generation power and photovoltaic power generation power. The intelligent micro-grid cooperative control system for wind power generation and photovoltaic power generation can complement the cooperative effect, and the power generation efficiency and the economic benefit are improved.
Description
Technical Field
The invention belongs to the technical field of intelligent micro-grid cooperative control systems, and particularly relates to an intelligent micro-grid cooperative control system and method based on deep learning.
Background
With the development of renewable energy power generation technologies such as photovoltaic, wind power and the like, distributed power generation is becoming an effective way for meeting load growth demands, improving comprehensive energy utilization efficiency and improving power supply reliability, and is widely applied to power distribution networks. However, the large-scale penetration of the distributed power generation also has some negative effects, such as higher single-machine access cost, complex control, impact on the voltage and frequency of a large system, and the like, which limits the operation mode of the distributed power generation and weakens the advantages and potential of the distributed power generation.
The micro-grid technology provides a flexible and efficient platform for integrating and utilizing the distributed power generation technology and the renewable energy power generation technology. The micro-grid control system is regarded as the most important ring of the future intelligent grid, and can effectively realize the transfer of electric power energy at the side of the grid and realize peak clipping and valley filling of the energy. The micro-grid control system has the characteristics of various power supply types, complex control modes and variable operation modes, so that a centralized control center is difficult to quickly react to the whole system and correspondingly control the whole system, such as distributed power supply output power fluctuation, voltage drop, faults, power failure and the like. The micro-grid control system should make each distributed power supply capable of making a fast autonomous reaction to an event in the grid based on local information, such as adjusting power flow and interface voltage, fast load sharing, off-grid seamless switching, automatic frequency control, automatic stability control, black start, etc., so as to jointly maintain the basic operation of the micro-grid system. However, the existing micro-grid control system does not fully consider various characteristics of wind-light power in different time and space scales, and exerts complementary characteristics and synergistic effects of wind power and photovoltaic power generation, so that the power generation efficiency and economic benefit of the micro-grid control system are low.
Therefore, how to make the micro-grid control system for wind power generation and photovoltaic power generation complement each other under different time-space scales based on the power of wind power generation and photovoltaic power generation, so as to improve the power generation efficiency and economic benefit of the micro-grid control system is a technical problem to be solved at present.
Disclosure of Invention
The invention aims to provide a deep learning-based intelligent micro-grid cooperative control system and a deep learning-based intelligent micro-grid cooperative control method, which are used for enabling a micro-grid control system for wind power generation and photovoltaic power generation to complement and cooperate under different time space scales based on power of the wind power generation and the photovoltaic power generation, and improving power generation efficiency and economic benefits of the micro-grid control system.
In order to solve the technical problems, the invention adopts the following technical scheme:
In a first aspect, a smart micro-grid cooperative control method based on deep learning is provided, including the following steps:
S1: acquiring historical weather data of a power generation area, historical wind power generation power and historical photovoltaic power generation power corresponding to the historical weather data and wind power and photovoltaic power generation operation cost, constructing a data set, and dividing the data set into a training set, a test set and a verification set;
s2: acquiring weather forecast data of a power generation area, and calibrating the weather forecast data through the historical weather data;
S3: constructing a micro-grid cooperative control system power cost model, sequentially dividing the data set into a training set, a testing set and a verification set, inputting the training set, the testing set and the verification set into the model, training, testing and verifying the model, judging whether a verification result meets the requirements, if so, executing the step S4, and if not, re-executing the step S1;
S4: inputting the calibrated weather forecast data into a power cost model of the intelligent micro-grid cooperative control system, and outputting predicted wind power generation power, predicted photovoltaic power generation power and predicted running cost;
s5: collecting current weather data and current running cost of a power generation area in real time, and correcting predicted wind power generation power and predicted photovoltaic power generation power according to the current weather data and the current running cost;
s6: and the intelligent micro-grid cooperative control system based on deep learning operates with the corrected wind power generation power and photovoltaic power generation power.
Preferably, the weather data includes wind data and illumination data, the wind data including: wind speed and wind direction, the illumination data comprising: illumination intensity and light irradiation angle.
Preferably, step S2 comprises the following specific procedures:
s21: acquiring weather forecast data in a designated period of a power generation region;
s22: extracting contemporaneous weather data from historical weather data of a power generation region;
S23: and compensating and calibrating the wind speed and the illumination intensity in the weather forecast data in the corresponding period according to the extracted wind speed and the illumination intensity in the contemporaneous weather data and the designated proportion.
Preferably, step S3 includes the following specific procedures:
S31: constructing a micro-grid cooperative control system power cost model;
S32: inputting a training set into the intelligent micro-grid cooperative control system power cost model, and training the model;
S33: inputting a test set into the intelligent micro-grid cooperative control system power cost model, testing the trained model, judging whether corresponding indexes of a test result meet requirements, and if so, executing a step S34; if not, inputting a new training set again, and training the model;
S34: and (3) inputting the verification set into the tested intelligent micro-grid cooperative control system power cost model, verifying the test result, judging whether the verification result meets the requirement, if so, executing the step S4, and if not, re-executing the step S1.
Preferably, in step S5, the process of correcting the predicted wind power generation power and the predicted photovoltaic power generation power according to the current weather data and the current running cost is as follows:
S51: calculating theoretical maximum power of the wind power generation system and theoretical maximum power of the photovoltaic power generation system based on the calibrated weather forecast data;
s52: creating a composite function that balances power and operating costs;
s53: calculating an optimal solution for creating a composite function that balances power and running cost;
S54: and correcting the predicted wind power generation power and the predicted photovoltaic power generation power according to the specified proportion through the optimal solution.
Preferably, the formula for creating a composite function that balances power and operating cost in step S52 is:
f（x）=f1（x）+f2（x）；
f1（x）=（Pft-Pwt-Pvt）2；
f2（x）=(kwt·Pwt+kvt·Pvt-ω·kt|Pwt+Pvt-Lt|)
Wherein f 1 (x) is a balance power function, f 2 (x) is an operation cost function, P ft is t moment load power, P wt is t moment wind power generation power, P vt is t moment photovoltaic power generation power, k wt is t moment wind power on-grid electricity price, k vt is t moment photovoltaic on-grid electricity price, ω is t moment power deviation coefficient, ω is related to corresponding power generation equipment, k t is electricity price deviation coefficient, and L t is t moment power plan value.
In a second aspect, a smart micro-grid cooperative control system based on deep learning is provided, which is used for implementing any one of the smart micro-grid cooperative control methods based on deep learning, and comprises a wind power generation system, a photovoltaic power generation system and a control management system, wherein the wind power generation system and the photovoltaic power generation system are connected with the control management system;
The wind power generation system comprises a transmission system and a generator, wherein the transmission system comprises a wind wheel, a main shaft, a speed-increasing gearbox and a coupler, the transmission system is used for converting the rotating speed and torque of the wind wheel into the rotating speed and torque matched with the generator, and the generator is used for converting wind energy into electric energy;
The photovoltaic power generation system comprises a photovoltaic module, a controller, an inverter and an energy storage system, wherein the photovoltaic module is a solar panel and is used for converting solar energy into electric energy; the controller is used for preventing the storage battery from overdischarging and protecting the storage battery from charging and discharging; the energy storage system is used for storing the converted electric energy so as to supply power when needed;
The control management system is used for controlling the wind power generation system and the photovoltaic power generation system.
Preferably, the wind power generation system further comprises a wind power data acquisition device and a first driving device for driving the wind wheel to rotate, and the wind power data acquisition device is used for acquiring wind speed and wind direction data in real time.
Preferably, the photovoltaic power generation system further comprises an illumination data acquisition device and a second driving device for driving the photovoltaic module to rotate, and the illumination data acquisition device is used for acquiring illumination intensity and light irradiation angle in real time.
The beneficial effects of the invention include:
according to the intelligent micro-grid cooperative control system and method based on deep learning, historical weather data, power generation power and power generation operation cost of a power generation area are obtained, and a data set is constructed; acquiring weather forecast data of a power generation area, and calibrating the weather forecast data through historical weather data; constructing a micro-grid cooperative control system power cost model, sequentially inputting the data set into the model, training, testing and verifying the model, judging whether a verification result meets the requirement, and if so, inputting the calibrated weather forecast data into the model, and outputting predicted wind power generation power, predicted photovoltaic power generation power and predicted running cost; and collecting current weather data and current running cost of the power generation region in real time, and running the intelligent micro-grid cooperative control system based on deep learning with the corrected wind power generation power and photovoltaic power generation power.
On the one hand, through the intelligent micro-grid cooperative control system based on deep learning, wind power generation and photovoltaic power generation can be complementarily and synergistically acted, and stable electric energy output is realized. On the other hand, the power generation efficiency of the intelligent micro-grid cooperative control system is improved, the operation cost is effectively reduced, and the economic benefit is improved.
Drawings
Fig. 1 is a schematic flow chart of a smart micro-grid cooperative control system method based on deep learning.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
The present application will present various aspects, embodiments, or features about a system that may include a plurality of devices, components, modules, etc. It is to be understood and appreciated that the various systems may include additional devices, components, modules, etc. and/or may not include all of the devices, components, modules etc. discussed in connection with the figures. Furthermore, combinations of these schemes may also be used.
In addition, in the embodiments of the present application, words such as "exemplary," "for example," and the like are used to indicate an example, instance, or illustration. Any embodiment or design described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of the term "exemplary" is intended to present concepts in a concrete fashion.
The invention is described in further detail below with reference to fig. 1:
Referring to fig. 1, the intelligent micro-grid cooperative control system and method based on deep learning comprises the following steps:
S1: acquiring historical weather data of a power generation area, historical wind power generation power and historical photovoltaic power generation power corresponding to the historical weather data and wind power and photovoltaic power generation operation cost, constructing a data set, and dividing the data set into a training set, a test set and a verification set;
s2: acquiring weather forecast data of a power generation area, and calibrating the weather forecast data through the historical weather data;
S3: constructing a micro-grid cooperative control system power cost model, sequentially dividing the data set into a training set, a testing set and a verification set, inputting the training set, the testing set and the verification set into the model, training, testing and verifying the model, judging whether a verification result meets the requirements, if so, executing the step S4, and if not, re-executing the step S1;
S4: inputting the calibrated weather forecast data into a power cost model of the intelligent micro-grid cooperative control system, and outputting predicted wind power generation power, predicted photovoltaic power generation power and predicted running cost;
s5: collecting current weather data and current running cost of a power generation area in real time, and correcting predicted wind power generation power and predicted photovoltaic power generation power according to the current weather data and the current running cost;
s6: and the intelligent micro-grid cooperative control system based on deep learning operates with the corrected wind power generation power and photovoltaic power generation power.
Step S1 is mainly to provide a data basis for subsequent model training, testing and verification, so that the model has learning ability meeting corresponding requirements. In the preparation process of the data, the comprehensive historical weather data, wind power generation power and photovoltaic power generation power in each period and the running cost of the whole intelligent micro-grid cooperative control system of the corresponding wind power generation power and photovoltaic power generation power are required to be acquired. After the related data is acquired, the acquired data needs to be preprocessed, and the preprocessing process comprises data cleaning, data conversion and data normalization. The data cleaning process is mainly used for removing invalid data, abnormal data, repeated data or noise data and the like in the data. The purpose of data conversion is to convert data in which analysis is inconvenient to data that is more convenient to analyze. The purpose of the data normalization process is to limit the processed data to a certain range and to induce the statistical distribution of the unified data sample.
In step S2, weather forecast data of the power generation area is obtained to know future weather data within a specified period, and because the weather data is critical to the power generation system, weather conditions are known in advance, so that wind power generation power and photovoltaic power generation power can be predicted, and the intelligent micro-grid cooperative control system can operate stably. However, the weather forecast is not completely accurate, and the weather data in the same region have certain regularity in the same period of a long time, so that the correction of the weather data of the weather forecast by the acquired historical weather data has great significance.
In steps S3 and S4, a machine learning model for predicting the power cost of the intelligent micro-grid cooperative control system is constructed, and the constructed model is trained, tested and verified through acquired related historical data, so that the model has learning capability meeting certain requirements, wind power generation power and photovoltaic power generation power can be predicted based on operation cost, higher wind power generation power and photovoltaic power generation power can be provided under lower operation cost, lower operation cost and higher economic benefit are provided, or wind power generation power and photovoltaic power generation power can be predicted according to weather data, and the intelligent micro-grid cooperative control system can have stable power output.
The constructed power cost model of the micro-grid cooperative control system is a convolutional neural network model, the process of constructing the convolutional neural network model comprises the steps of constructing a convolutional layer, a pooling layer and a full-connection layer, setting corresponding parameters including the size and the step length of a convolutional kernel for each constructed layer, selecting an activation function and a loss function, and setting an optimizer.
In one embodiment, the input channel of the first layer of convolution layer is 3, the output channel is 6, the filter/kernel sliding step size in the convolution layer is 1, during convolution operation adds additional data at the edge of the input data is 0, the maximum pooling size is 5, the input channel of the second layer of convolution layer is 6, the output channel is 16, the filter/kernel sliding step size in the convolution layer is 1, during convolution operation adds additional data at the edge of the input data is 0, and the maximum pooling size is 5. The third layer of full-connection layer has 256 input channels and 120 output channels. The fourth layer of full-connection layer has an input channel of 120, an output channel of 84, an output layer of full-connection channel of 84 and an output channel of 10. The activation function selects a Sigmoid activation function, and the loss function selects a manhattan distance loss function.
In the process of model training on the convolutional neural network model, the output of the model is calculated through forward propagation, and the error between the predicted value and the true value is calculated according to the loss function. Gradients are then calculated by a back-propagation algorithm and network parameters are updated using an optimizer to minimize the loss function. This process is iterated a number of times until a preset number of iterations is reached or the loss function reaches a lower value. simultaneously, super parameters such as learning rate and the like need to be adjusted in the training process so as to balance the training speed and generalization capability of the model. The learning rate determines the magnitude of parameter updates, an excessive learning rate may cause the model to be unstable during the training process, and an excessive learning rate may cause the training process to be too slow. The optimizer selects Adam optimization algorithm to update model parameters.
Since weather data of weather forecast and actual weather data are different in general, such as illumination intensity in different time periods, wind speed and wind direction in different time periods, and the like. Therefore, it is required to collect current weather data and current running cost of the power generation region in real time, and correct the predicted wind power generation power and the predicted photovoltaic power generation power according to the current weather data and the current running cost, so that the intelligent micro-grid cooperative control system can work with better wind power generation power and photovoltaic power generation power, and can run with relatively lower cost. And finally, the intelligent micro-grid cooperative control system operates with the corrected wind power generation power and photovoltaic power generation power.
In the above scheme, the weather data includes wind power data and illumination data, and the wind power data includes: wind speed and wind direction, the illumination data comprising: illumination intensity and light irradiation angle.
Step S2 comprises the following specific processes:
s21: acquiring weather forecast data in a designated period of a power generation region;
s22: extracting contemporaneous weather data from historical weather data of a power generation region;
S23: according to the wind speed and the illumination intensity in the extracted contemporaneous weather data, and the wind speed and the illumination intensity in the weather forecast data in the corresponding period are compensated and calibrated according to the specified proportion, so that the calibrated weather forecast data can be used as the calculation parameters of the wind power generation power and the photovoltaic power generation power more accurately.
Step S3 comprises the following specific processes:
S31: constructing a micro-grid cooperative control system power cost model;
S32: inputting a training set into the intelligent micro-grid cooperative control system power cost model, and training the model;
S33: inputting a test set into the intelligent micro-grid cooperative control system power cost model, testing the trained model, judging whether corresponding indexes of a test result meet requirements, and if so, executing a step S34; if not, inputting a new training set again, and training the model;
S34: and (3) inputting the verification set into the tested intelligent micro-grid cooperative control system power cost model, verifying the test result, judging whether the verification result meets the requirement, if so, executing the step S4, and if not, re-executing the step S1.
In step S5, the process of correcting the predicted wind power generation power and the predicted photovoltaic power generation power according to the current weather data and the current running cost is as follows:
S51: calculating theoretical maximum power of the wind power generation system and theoretical maximum power of the photovoltaic power generation system based on the calibrated weather forecast data;
s52: creating a composite function that balances power and operating costs;
s53: calculating an optimal solution for creating a composite function that balances power and running cost;
S54: and correcting the predicted wind power generation power and the predicted photovoltaic power generation power according to the specified proportion through the optimal solution.
The formula for creating the composite function balancing power and running cost in step S52 is:
f（x）=f1（x）+f2（x）；
f1（x）=（Pft-Pwt-Pvt）2；
f2（x）=(kwt·Pwt+kvt·Pvt-ω·kt|Pwt+Pvt-Lt|)
Wherein f 1 (x) is a balance power function, f 2 (x) is an operation cost function, P ft is t moment load power, P wt is t moment wind power generation power, P vt is t moment photovoltaic power generation power, k wt is t moment wind power on-grid electricity price, k vt is t moment photovoltaic on-grid electricity price, ω is t moment power deviation coefficient, ω is related to corresponding power generation equipment, k t is electricity price deviation coefficient, and L t is t moment power plan value. Through the compound function formula, the intelligent micro-grid cooperative control system can further have higher wind power generation power and photovoltaic power generation power under lower operation cost, and economic benefit of the system is effectively improved.
The intelligent micro-grid cooperative control system based on deep learning comprises a wind power generation system, a photovoltaic power generation system and a control management system, wherein the wind power generation system and the photovoltaic power generation system are connected with the control management system; the wind power generation system comprises a transmission system and a generator, wherein the transmission system comprises a wind wheel, a main shaft, a speed-increasing gearbox and a coupler, the transmission system is used for converting the rotating speed and torque of the wind wheel into the rotating speed and torque matched with the generator, and the generator is used for converting wind energy into electric energy; the photovoltaic power generation system comprises a photovoltaic module, a controller, an inverter and an energy storage system, wherein the photovoltaic module is a solar panel and is used for converting solar energy into electric energy; the controller is used for preventing the storage battery from overdischarging and protecting the storage battery from charging and discharging; the energy storage system is used for storing the converted electric energy so as to supply power when needed; the control management system is used for controlling the wind power generation system and the photovoltaic power generation system.
The wind power generation system further comprises a wind power data acquisition device and a first driving device for driving the wind wheel to rotate, and the wind power data acquisition device is used for acquiring wind speed and wind direction data in real time. The photovoltaic power generation system further comprises an illumination data acquisition device and a second driving device for driving the photovoltaic module to rotate, and the illumination data acquisition device is used for acquiring illumination intensity and light irradiation angle in real time.
The first driving device and the second driving device in the wind power generation system and the photovoltaic power generation system are mainly arranged because the wind direction or the light irradiation angle is changed in different time, and in order to enable the power which can be generated by the wind power generation system and the photovoltaic power generation system to be higher respectively, the wind direction is required to be perpendicular to the blade surface of the wind wheel or the light irradiation direction is required to be perpendicular to the light receiving surface of the photovoltaic module as far as possible. Therefore, the direction of the wind wheel is required to be rotationally adjusted through the first driving device according to the wind direction value acquired by the wind power data acquisition device, so that the wind direction is perpendicular to the blade surface of the wind wheel under the real-time condition. And rotating the photovoltaic module, namely the solar panel, according to the illumination data acquired by the illumination data acquisition device, so that the light irradiation direction is perpendicular to the light receiving surface of the solar panel of the photovoltaic module.
In summary, the intelligent micro-grid cooperative control system and the intelligent micro-grid cooperative control method based on deep learning acquire historical weather data, power generation and power generation operation cost of a power generation area, and construct a data set; acquiring weather forecast data of a power generation area, and calibrating the weather forecast data through historical weather data; constructing a micro-grid cooperative control system power cost model, sequentially inputting the data set into the model, training, testing and verifying the model, judging whether a verification result meets the requirement, and if so, inputting the calibrated weather forecast data into the model, and outputting predicted wind power generation power, predicted photovoltaic power generation power and predicted running cost; and collecting current weather data and current running cost of the power generation region in real time, and running the intelligent micro-grid cooperative control system based on deep learning with the corrected wind power generation power and photovoltaic power generation power. Through the intelligent micro-grid cooperative control system based on deep learning, wind power generation and photovoltaic power generation can complement each other in a cooperative effect, and stable electric energy output is realized. Meanwhile, the power generation efficiency of the intelligent micro-grid cooperative control system is improved, the operation cost is effectively reduced, and the economic benefit is improved.
The above examples merely illustrate specific embodiments of the application, which are described in more detail and are not to be construed as limiting the scope of the application. It should be noted that it is possible for a person skilled in the art to make several variants and modifications without departing from the technical idea of the application, which fall within the scope of protection of the application.
Claims (5)
1. The intelligent micro-grid cooperative control method based on deep learning is characterized by comprising the following steps of:
S1: acquiring historical weather data of a power generation area, historical wind power generation power and historical photovoltaic power generation power corresponding to the historical weather data and wind power and photovoltaic power generation operation cost, constructing a data set, and dividing the data set into a training set, a test set and a verification set;
s2: acquiring weather forecast data of a power generation area, and calibrating the weather forecast data through the historical weather data;
S3: constructing a power cost model of the intelligent micro-grid cooperative control system, sequentially inputting the training set, the testing set and the verification set into the model, training, testing and verifying the model, judging whether a verification result meets the requirements, if so, executing the step S4, and if not, re-executing the step S1;
S4: inputting the calibrated weather forecast data into a power cost model of the intelligent micro-grid cooperative control system, and outputting predicted wind power generation power, predicted photovoltaic power generation power and predicted running cost;
s5: collecting current weather data and current running cost of a power generation area in real time, and correcting predicted wind power generation power and predicted photovoltaic power generation power according to the current weather data and the current running cost;
s6: the intelligent micro-grid cooperative control system operates with the corrected wind power generation power and photovoltaic power generation power;
Step S2 comprises the following specific processes:
s21: acquiring weather forecast data in a designated period of a power generation region;
s22: extracting contemporaneous weather data from historical weather data of a power generation region;
S23: according to the wind speed and the illumination intensity in the extracted contemporaneous weather data, compensating and calibrating the wind speed and the illumination intensity in the weather forecast data in the corresponding period according to the designated proportion;
Step S3 comprises the following specific processes:
s31: constructing a power cost model of the intelligent micro-grid cooperative control system;
S32: inputting a training set into the intelligent micro-grid cooperative control system power cost model, and training the model;
S33: inputting a test set into the intelligent micro-grid cooperative control system power cost model, testing the trained model, judging whether corresponding indexes of a test result meet requirements, and if so, executing a step S34; if not, inputting a new training set again, and training the model;
S34: inputting the verification set into the tested intelligent micro-grid cooperative control system power cost model, verifying the test result, judging whether the verification result meets the requirement, if so, executing the step S4, and if not, re-executing the step S1;
In step S5, the process of correcting the predicted wind power generation power and the predicted photovoltaic power generation power according to the current weather data and the current running cost is as follows:
s51: calculating theoretical maximum power of the wind power generation system and theoretical maximum power of the photovoltaic power generation system based on current weather data;
s52: creating a composite function that balances power and operating costs;
s53: calculating an optimal solution for creating a composite function that balances power and running cost;
s54: correcting the predicted wind power generation power and the predicted photovoltaic power generation power according to the specified proportion through the optimal solution;
The formula for creating the composite function balancing power and running cost in step S52 is:
f（x）= f1（x）+ f2（x）；
f1（x）=（Pft- Pwt- Pvt）2；
；
Wherein f 1 (x) is a balance power function, f 2 (x) is an operation cost function, P ft is t moment load power, P wt is t moment wind power generation power, P vt is t moment photovoltaic power generation power, k wt is t moment wind power on-grid electricity price, k vt is t moment photovoltaic on-grid electricity price, Is the power deviation coefficient at the moment t,In relation to the corresponding power generation device, k t is a power price deviation coefficient, and L t is a power schedule value at time t.
2. The smart micro grid cooperative control method based on deep learning according to claim 1, wherein the weather data includes wind power data and illumination data, the wind power data includes: wind speed and wind direction, the illumination data comprising: illumination intensity and light irradiation angle.
3. A deep learning-based intelligent micro-grid cooperative control system for realizing the deep learning-based intelligent micro-grid cooperative control method according to any one of claims 1-2, which is characterized by comprising a wind power generation system, a photovoltaic power generation system and a control management system, wherein the wind power generation system and the photovoltaic power generation system are connected with the control management system;
The wind power generation system comprises a transmission system and a generator, wherein the transmission system comprises a wind wheel, a main shaft, a speed-increasing gearbox and a coupler, the transmission system is used for converting the rotating speed and torque of the wind wheel into the rotating speed and torque matched with the generator, and the generator is used for converting wind energy into electric energy;
The photovoltaic power generation system comprises a photovoltaic module, a controller, an inverter and an energy storage system, wherein the photovoltaic module is a solar panel and is used for converting solar energy into electric energy; the controller is used for preventing the storage battery from overdischarging and protecting the storage battery from charging and discharging; the energy storage system is used for storing the converted electric energy so as to supply power when needed;
The control management system is used for controlling the wind power generation system and the photovoltaic power generation system.
4. The intelligent micro-grid cooperative control system based on deep learning according to claim 3, wherein the wind power generation system further comprises a wind power data acquisition device and a first driving device for driving the wind wheel to rotate, and the wind power data acquisition device is used for acquiring wind speed and wind direction data in real time.
5. The intelligent micro-grid cooperative control system based on deep learning according to claim 3, wherein the photovoltaic power generation system further comprises an illumination data acquisition device and a second driving device for driving the photovoltaic module to rotate, and the illumination data acquisition device is used for acquiring illumination intensity and light irradiation angle in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411010368.6A CN118572778B (en) | 2024-07-26 | 2024-07-26 | Deep learning-based intelligent micro-grid cooperative control system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411010368.6A CN118572778B (en) | 2024-07-26 | 2024-07-26 | Deep learning-based intelligent micro-grid cooperative control system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118572778A CN118572778A (en) | 2024-08-30 |
| CN118572778B true CN118572778B (en) | 2024-10-29 |
Family
ID=92479440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411010368.6A Active CN118572778B (en) | 2024-07-26 | 2024-07-26 | Deep learning-based intelligent micro-grid cooperative control system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118572778B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114006369A (en) * | 2021-10-28 | 2022-02-01 | 华北电力大学 | Regional wind and light station power joint prediction method and device, electronic equipment and storage medium |
| CN117543543A (en) * | 2023-10-30 | 2024-02-09 | 广东省风力发电有限公司内蒙古分公司 | Optimal complementary operation method of wind-solar complementary power generation system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102269124B (en) * | 2011-06-30 | 2013-04-03 | 内蒙古电力勘测设计院 | Ultra-short term wind power station generated power forecasting system |
| CN114418180B (en) * | 2021-12-16 | 2023-01-20 | 广东电网有限责任公司 | Ultra-short-term prediction method and device for wind power and storage medium |
| CN116402203A (en) * | 2023-03-23 | 2023-07-07 | 中国电力科学研究院有限公司 | Method, system and medium for predicting short-time photovoltaic power generation capacity considering weather conditions |
-
2024
- 2024-07-26 CN CN202411010368.6A patent/CN118572778B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114006369A (en) * | 2021-10-28 | 2022-02-01 | 华北电力大学 | Regional wind and light station power joint prediction method and device, electronic equipment and storage medium |
| CN117543543A (en) * | 2023-10-30 | 2024-02-09 | 广东省风力发电有限公司内蒙古分公司 | Optimal complementary operation method of wind-solar complementary power generation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118572778A (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107069814B (en) | Fuzzy opportunity constraint planning method and system for distribution network distributed power capacity distribution | |
| CN102684201B (en) | Voltage threshold probability-based reactive power optimizing method for grid containing wind power plant | |
| CN104734195A (en) | Monitoring method of wind, photovoltaic and storage-integrated micro-grid capable of being operated in a grid-connected manner | |
| CN108695857B (en) | Automatic voltage control method, device and system for wind power plant | |
| CN103944175A (en) | Wind-solar-storage combined power generation system output characteristic optimization method | |
| CN104734196A (en) | Monitoring device of wind, photovoltaic and storage-integrated micro-grid capable of being operated in a grid-connected manner | |
| CN104682436B (en) | Energy storage system micro-grid capable of inhibiting power fluctuation | |
| CN104734194A (en) | Wind, photovoltaic and storage-integrated micro-grid capable of being operated in a grid-connected manner | |
| Natsheh | Hybrid power systems energy management based on artificial intelligence | |
| Zangeneh et al. | A survey: Fuzzify parameters and membership function in electrical applications | |
| CN107832869A (en) | A kind of generated power forecasting method of wind-power electricity generation and photovoltaic generation | |
| CN110994632A (en) | Opportunity constraint planning-based distributed power supply distribution point constant volume optimization calculation method considering voltage and environmental protection indexes | |
| CN103560533B (en) | The method and system of the level and smooth wind light generation fluctuation of energy-accumulating power station are controlled based on rate of change | |
| CN104682449B (en) | Monitoring device for micro-grid with energy storage system capable of stabilizing power fluctuation | |
| CN118572778B (en) | Deep learning-based intelligent micro-grid cooperative control system and method | |
| CN116760109B (en) | Comprehensive regulation and control system for distributed photovoltaic power grid connection | |
| CN111311032A (en) | Micro-grid system capacity optimal configuration method based on sector radar map model | |
| CN110380419A (en) | It is a kind of to mix random and interval variable uncertain tidal current computing method | |
| CN116885840A (en) | Distributed new energy online monitoring method and system based on real-time data | |
| CN115800306A (en) | Wind-solar-storage reactive power compensation method, device and medium considering fan faults | |
| CN116191555A (en) | Distributed new energy peak shaving response optimization operation method based on flexible boundary prediction | |
| CN114649822A (en) | Micro-grid hybrid energy storage double-layer capacity configuration method considering three states of wind and light | |
| JP2019187022A (en) | Power generation system and control method therefor | |
| Li et al. | Research on Distributed Photovoltaic Day-ahead Scheduling and Consumption Strategy | |
| CN108233378B (en) | New energy power generation field harmonic control 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 | ||
| GR01 | Patent grant |