Energy storage charging and discharging strategy optimization method in optical storage integrated system

Abstract

The present application relates to a kind of energy storage charging and discharging strategy optimization method in optical storage integrated system, belong to the technical field of discharge optimization of energy storage equipment, the present application obtains the historical discharge performance variation characteristic data of optical storage integrated system under each charging strategy data, and according to the historical discharge performance variation characteristic data of optical storage integrated system under each charging strategy data, the performance prediction model of optical storage integrated system is constructed, finally, the discharge performance characteristic data of optical storage integrated system within the preset time is predicted by the performance prediction model of optical storage integrated system, and the discharge optimization is carried out according to the discharge performance characteristic data of optical storage integrated system within the preset time by genetic algorithm.The present application configures the electric energy capacity of optical storage integrated system according to the power supply demand information of target area, and dynamically adjusts the charging and discharging strategy of optical storage integrated system according to the discharge performance of optical storage integrated system, improves the service life of optical storage integrated system.

Description

Technical Field

[0001] This invention relates to the field of power grid charging and discharging optimization technology, and in particular to a method for optimizing energy storage charging and discharging strategies in an integrated photovoltaic-storage system. Background Technology

[0002] Clean energy generation from sources like wind, solar, and hydrogen exhibits volatility, and energy storage technology can effectively address this instability. Energy storage technology converts different forms of energy, such as electrical, thermal, and chemical energy, into other forms, stores them through equipment or physical media, and releases them when necessary. Integrated photovoltaic (PV) and energy storage systems offer advantages such as low cost, reliable power supply, and minimal environmental pollution, and have become an important development direction in global energy applications in recent years, with wide applicability in industrial and commercial areas, residential areas, campuses, and islands. However, during operation, the performance of the battery cells and electrode materials in the energy storage system degrades. Maintaining the original charging and discharging characteristics continuously will reduce the lifespan of the integrated PV and energy storage system. Summary of the Invention

[0003] This invention overcomes the shortcomings of the prior art and provides an optimization method for energy storage charging and discharging strategies in an integrated photovoltaic-energy storage system.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention provides a method for optimizing the energy storage charging and discharging strategy in an integrated photovoltaic-energy storage system, specifically including:

[0006] Construct a power demand forecasting model, and use the power demand forecasting model to predict the power demand information of the target area;

[0007] Configure the power capacity of the photovoltaic-storage integrated system according to the power demand information of the target area, configure the power according to the power capacity of the photovoltaic-storage integrated system, obtain the power configuration strategy, and configure the charging strategy of the photovoltaic-storage integrated system according to the power configuration strategy.

[0008] Acquire historical discharge performance variation characteristics of the photovoltaic-storage integrated system under various charging strategy data, and construct a performance prediction model of the photovoltaic-storage integrated system based on the historical discharge performance variation characteristics of the photovoltaic-storage integrated system under various charging strategy data.

[0009] The discharge performance characteristics of the integrated photovoltaic and energy storage system are predicted by the performance prediction model of the integrated photovoltaic and energy storage system within a preset time period, and the discharge is optimized by a genetic algorithm based on the discharge performance characteristics of the integrated photovoltaic and energy storage system within the preset time period.

[0010] Furthermore, in this method, a power demand prediction model is constructed to predict the power demand information of the target area, specifically including:

[0011] A power demand prediction model is built based on deep neural networks, and power demand information of the target area is obtained through big data under various factors. The data of each factor and the power demand information are used as nodes to build a directed descriptive relationship.

[0012] The nodes are connected based on the directed description relationship to form a topology graph. The relevant adjacency matrix is ​​obtained based on the topology graph. The relevant adjacency matrix is ​​input into the power demand prediction model for training to obtain the trained power demand prediction model.

[0013] Data on influencing factors in the target area within a preset time period is obtained, and this data is input into the trained power demand prediction model to make predictions and obtain power demand information for the target area.

[0014] Furthermore, in this method, the power capacity of the photovoltaic-storage integrated system is configured according to the power demand information of the target area, the power is configured according to the power capacity of the photovoltaic-storage integrated system, a power configuration strategy is obtained, and a charging strategy is configured for the photovoltaic-storage integrated system according to the power configuration strategy, specifically as follows:

[0015] Obtain the maximum power capacity information of each photovoltaic-storage integrated system in the target area, and calculate the required number of photovoltaic-storage integrated systems based on the power supply demand information of the target area and the maximum power capacity information of each photovoltaic-storage integrated system in the target area.

[0016] Based on the quantity information of the required integrated photovoltaic and energy storage systems, randomly select the working integrated photovoltaic and energy storage systems to determine the working combination of the integrated photovoltaic and energy storage systems;

[0017] Configure the power capacity of the integrated photovoltaic and energy storage system according to the working combination of the integrated photovoltaic and energy storage system and the power supply demand information of the target area.

[0018] The power configuration is performed according to the power capacity of the photovoltaic-storage integrated system, a power configuration strategy is obtained, and a charging strategy is configured for the photovoltaic-storage integrated system according to the power configuration strategy.

[0019] Furthermore, in this method, historical discharge performance variation characteristic data of the integrated photovoltaic-energy storage system under various charging strategy data are obtained, and a performance prediction model of the integrated photovoltaic-energy storage system is constructed based on the historical discharge performance variation characteristic data of the integrated photovoltaic-energy storage system under various charging strategy data, specifically as follows:

[0020] Construct timestamps and statistically analyze the discharge performance change characteristics of the photovoltaic-storage integrated system under various charging strategy data at each timestamp, thus forming historical discharge performance change characteristics data of the photovoltaic-storage integrated system under various charging strategy data.

[0021] A performance prediction model for the integrated photovoltaic and energy storage system is constructed based on a deep neural network. The historical discharge performance change characteristics of the integrated photovoltaic and energy storage system under various charging strategies are input into the performance prediction model of the integrated photovoltaic and energy storage system for training.

[0022] When the loss function of the performance prediction model of the integrated photovoltaic and energy storage system converges to a preset value, the model parameters of the performance prediction model of the integrated photovoltaic and energy storage system are saved, and the performance prediction model of the integrated photovoltaic and energy storage system is output.

[0023] Furthermore, in this method, the discharge performance characteristic data of the integrated photovoltaic-energy storage system within a preset time period is predicted using the performance prediction model of the integrated photovoltaic-energy storage system, specifically as follows:

[0024] Acquire discharge performance change characteristic data of each photovoltaic-storage integrated system within a preset time period, and input the discharge performance change characteristic data of each photovoltaic-storage integrated system within the preset time period into the performance prediction model of the photovoltaic-storage integrated system for prediction.

[0025] By prediction, discharge performance characteristic data of the integrated photovoltaic and energy storage system within a preset time period are obtained, and the discharge performance characteristic data of the integrated photovoltaic and energy storage system within the preset time period are output.

[0026] Furthermore, in this method, discharge optimization is performed using a genetic algorithm based on the discharge performance characteristic data of the integrated photovoltaic-energy storage system within the preset time period, specifically including:

[0027] Based on the discharge performance characteristic data of the photovoltaic-storage integrated system within the preset time, a discharge performance characteristic threshold for each photovoltaic-storage integrated system is set, and the real-time discharge amount data of each photovoltaic-storage integrated system is initialized.

[0028] A genetic algorithm is introduced, the number of generations is set based on the genetic algorithm, and it is determined whether the real-time discharge data of each photovoltaic-storage integrated system is less than the discharge performance characteristic threshold.

[0029] When the real-time discharge data of each photovoltaic-storage integrated system is not all less than the discharge performance characteristic threshold, the real-time discharge data of the photovoltaic-storage integrated system is readjusted based on the genetic generation until they are all less than the discharge performance characteristic threshold.

[0030] When the real-time discharge data of each photovoltaic-storage integrated system is less than the discharge performance characteristic threshold, the real-time discharge data of each photovoltaic-storage integrated system is output, and discharge optimization is performed according to the real-time discharge data of the photovoltaic-storage integrated system.

[0031] A second aspect of the present invention provides an energy storage charging and discharging strategy optimization system for a photovoltaic-energy storage integrated system. The system includes a memory and a processor. The memory includes a program for optimizing the energy storage charging and discharging strategy in the photovoltaic-energy storage integrated system. When the program for optimizing the energy storage charging and discharging strategy in the photovoltaic-energy storage integrated system is executed by the processor, it implements the steps of the energy storage charging and discharging strategy optimization method for any of the claims.

[0032] A third aspect of the present invention provides a terminal device, comprising:

[0033] The power demand forecasting module constructs a power demand forecasting model and uses the power demand forecasting model to predict the power demand information of the target area.

[0034] The charging strategy configuration module configures the power capacity of the photovoltaic-storage integrated system according to the power demand information of the target area, performs power configuration according to the power capacity of the photovoltaic-storage integrated system, obtains the power configuration strategy, and configures the charging strategy of the photovoltaic-storage integrated system according to the power configuration strategy.

[0035] The performance prediction model construction module acquires historical discharge performance change characteristic data of the photovoltaic-storage integrated system under various charging strategy data, and constructs a performance prediction model of the photovoltaic-storage integrated system based on the historical discharge performance change characteristic data of the photovoltaic-storage integrated system under various charging strategy data.

[0036] The discharge optimization module predicts the discharge performance characteristics of the integrated photovoltaic and energy storage system within a preset time period using the performance prediction model of the integrated photovoltaic and energy storage system, and performs discharge optimization based on the discharge performance characteristics of the integrated photovoltaic and energy storage system within the preset time period using a genetic algorithm.

[0037] A fourth aspect of the present invention provides a computer-readable storage medium comprising a method program for optimizing energy storage charging and discharging strategies in an integrated photovoltaic and energy storage system. When the method program is executed by a processor, it implements the steps of the method program for optimizing energy storage charging and discharging strategies in an integrated photovoltaic and energy storage system as described in any one of the present invention.

[0038] This invention addresses the shortcomings of the prior art and has the following beneficial effects:

[0039] This invention constructs a power demand prediction model to predict the power demand information of a target area. Based on this model, it configures the power capacity of an integrated photovoltaic (PV) and energy storage (ESS) system, allocates power according to the system's capacity, obtains a power allocation strategy, and configures a charging strategy for the PV-ESS system based on this strategy. This yields historical discharge performance variation data of the PV-ESS system under various charging strategies. A performance prediction model for the PV-ESS system is then constructed based on this historical discharge performance variation data. Finally, the performance prediction model predicts the discharge performance characteristics of the PV-ESS system within a preset time period, and a genetic algorithm optimizes the discharge performance based on this data. This invention improves the lifespan of the integrated PV-ESS system by configuring its power capacity according to the power demand information of the target area and dynamically adjusting its charging and discharging strategies based on its discharge performance. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0041] Figure 1 The overall flowchart of the energy storage charging and discharging strategy optimization method in the photovoltaic-energy storage integrated system is shown;

[0042] Figure 2 This shows a partial flowchart of the optimization method for energy storage charging and discharging strategies in an integrated photovoltaic and energy storage system;

[0043] Figure 3 The system block diagram of the energy storage charging and discharging strategy optimization system in the photovoltaic-energy storage integrated system is shown.

[0044] Figure 4 A schematic diagram of the terminal device is shown. Detailed Implementation

[0045] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0046] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0047] like Figure 1 As shown, the first aspect of the present invention provides a method for optimizing the energy storage charging and discharging strategy in a photovoltaic-energy storage integrated system, specifically including:

[0048] S102: Construct a power demand forecasting model to predict the power demand information of the target area.

[0049] S104: Configure the power capacity of the photovoltaic-storage integrated system according to the power demand information of the target area, configure the power according to the power capacity of the photovoltaic-storage integrated system, obtain the power configuration strategy, and configure the charging strategy of the photovoltaic-storage integrated system according to the power configuration strategy.

[0050] S106: Obtain historical discharge performance change characteristic data of the photovoltaic-storage integrated system under various charging strategy data, and construct a performance prediction model of the photovoltaic-storage integrated system based on the historical discharge performance change characteristic data of the photovoltaic-storage integrated system under various charging strategy data.

[0051] S108: Predict the discharge performance characteristics of the integrated photovoltaic and energy storage system within a preset time period using a performance prediction model, and optimize the discharge performance based on the discharge performance characteristics of the integrated photovoltaic and energy storage system within the preset time period using a genetic algorithm.

[0052] It should be noted that this invention improves the lifespan of the integrated photovoltaic and energy storage system by configuring the power capacity of the integrated photovoltaic and energy storage system according to the power supply demand information of the target area, and by dynamically adjusting the charging and discharging strategy of the integrated photovoltaic and energy storage system according to the discharge performance of the integrated photovoltaic and energy storage system.

[0053] Furthermore, in this method, a power demand prediction model is constructed to predict the power demand information of the target area, specifically including:

[0054] A power demand prediction model is built based on deep neural networks, and power demand information of the target area is obtained through big data under various factors. The data of each factor and the power demand information are used as nodes to build a directed descriptive relationship.

[0055] Nodes are connected based on directed descriptive relationships to form a topology graph. The relevant adjacency matrix is ​​obtained based on the topology graph. The relevant adjacency matrix is ​​input into the power demand prediction model for training, and the trained power demand prediction model is obtained.

[0056] Data on influencing factors in the target area within a preset time period is obtained, and this data is then input into the trained power demand prediction model to make predictions and obtain power demand information for the target area.

[0057] It should be noted that the factor data includes meteorological characteristics, environmental characteristics, seasonal characteristics, etc. Because the power supply demand information of the target area is different under different factor data, such as summer and winter, or cloudy, sunny and rainy days, etc.

[0058] Furthermore, in this method, the power capacity of the photovoltaic-storage integrated system is configured according to the power demand information of the target area, the power is configured according to the power capacity of the photovoltaic-storage integrated system, a power configuration strategy is obtained, and a charging strategy is configured for the photovoltaic-storage integrated system according to the power configuration strategy, specifically as follows:

[0059] Obtain the maximum power capacity information of each photovoltaic-storage integrated system in the target area, and calculate the required number of photovoltaic-storage integrated systems based on the power supply demand information of the target area and the maximum power capacity information of each photovoltaic-storage integrated system in the target area.

[0060] Based on the quantity information of the required integrated photovoltaic and energy storage systems, randomly select the working integrated photovoltaic and energy storage systems to determine the working combination of the integrated photovoltaic and energy storage systems;

[0061] Configure the power capacity of the integrated photovoltaic and energy storage system according to the working combination of the integrated photovoltaic and energy storage system and the power supply demand information of the target area.

[0062] Power allocation is performed according to the power capacity of the photovoltaic-storage integrated system, power allocation strategy is obtained, and charging strategy is configured for the photovoltaic-storage integrated system according to the power allocation strategy.

[0063] It should be noted that the power demand information includes descriptions such as the amount of power supplied per unit time and the power supplied per unit time. This method enables the dynamic setting of the charging strategy for the photovoltaic-storage integrated system based on the power demand.

[0064] Furthermore, in this method, historical discharge performance variation characteristic data of the photovoltaic-energy storage integrated system under various charging strategy data are obtained, and a performance prediction model of the photovoltaic-energy storage integrated system is constructed based on the historical discharge performance variation characteristic data of the photovoltaic-energy storage integrated system under various charging strategy data, specifically as follows:

[0065] Construct timestamps and statistically analyze the discharge performance change characteristics of the photovoltaic-storage integrated system under various charging strategy data at each timestamp, thus forming historical discharge performance change characteristics data of the photovoltaic-storage integrated system under various charging strategy data.

[0066] A performance prediction model for the photovoltaic-storage integrated system is constructed based on a deep neural network. The historical discharge performance change characteristics of the photovoltaic-storage integrated system under various charging strategies are input into the performance prediction model of the photovoltaic-storage integrated system for training.

[0067] When the loss function of the performance prediction model of the integrated photovoltaic and energy storage system converges to the preset value, the model parameters of the performance prediction model of the integrated photovoltaic and energy storage system are saved, and the performance prediction model of the integrated photovoltaic and energy storage system is output.

[0068] It should be noted that the discharge performance data includes data such as the discharge amount per unit time and the discharge power per unit time. Because integrated photovoltaic and energy storage systems experience degradation of related electrode materials and battery cells after a certain number of years of use, their discharge performance will decline. This method can be used to construct a performance prediction model for integrated photovoltaic and energy storage systems, thereby predicting their discharge performance.

[0069] Furthermore, in this method, the discharge performance characteristics of the integrated photovoltaic-energy storage system are predicted within a preset time period using a performance prediction model of the integrated photovoltaic-energy storage system. Specifically:

[0070] Acquire the discharge performance change characteristic data of each photovoltaic-storage integrated system within a preset time period, and input the discharge performance change characteristic data of each photovoltaic-storage integrated system within the preset time period into the performance prediction model of the photovoltaic-storage integrated system for prediction.

[0071] By predicting, the discharge performance characteristics data of the photovoltaic-storage integrated system within a preset time period are obtained, and the discharge performance characteristics data of the photovoltaic-storage integrated system within the preset time period are output.

[0072] like Figure 2 As shown, furthermore, in this method, discharge optimization is performed using a genetic algorithm based on the discharge performance characteristic data of the integrated photovoltaic-storage system within a preset time period. Specifically, this includes:

[0073] S202: Based on the discharge performance characteristic data of the photovoltaic-storage integrated system within a preset time, set the discharge performance characteristic threshold of the photovoltaic-storage integrated system for each photovoltaic-storage integrated system, and initialize the real-time discharge amount data of each photovoltaic-storage integrated system.

[0074] S204: Introduce a genetic algorithm, set the number of generations based on the genetic algorithm, and determine whether the real-time discharge data of each photovoltaic-storage integrated system is less than the discharge performance characteristic threshold.

[0075] S206: When the real-time discharge data of each photovoltaic-storage integrated system is not uniformly less than the discharge performance characteristic threshold, the real-time discharge data of the photovoltaic-storage integrated system is readjusted based on the genetic generation until they are all less than the discharge performance characteristic threshold.

[0076] S208: When the real-time discharge data of each photovoltaic-storage integrated system is less than the discharge performance characteristic threshold, output the real-time discharge data of each photovoltaic-storage integrated system and perform discharge optimization according to the real-time discharge data of the photovoltaic-storage integrated system.

[0077] It's important to note that genetic algorithms are search algorithms used in computational mathematics to solve optimization problems; they are a type of evolutionary algorithm. Evolutionary algorithms were initially developed by drawing inspiration from phenomena in evolutionary biology, including heredity, mutation, natural selection, and hybridization. Genetic algorithms are typically implemented through computer simulation. For an optimization problem, a population of abstract representations (called chromosomes) of a certain number of candidate solutions (individuals) evolves towards better solutions. Traditionally, solutions are represented in binary (a string of 0s and 1s), but other representations can also be used. Evolution begins with a population of completely random individuals and proceeds generation by generation. In each generation, the fitness of the entire population is evaluated, and several individuals are randomly selected from the current population (based on their fitness) to generate a new population through natural selection and mutation. This new population becomes the current population in the next iteration of the algorithm. By using genetic algorithms to perform cluster control of integrated photovoltaic and energy storage systems in a target area, the real-time discharge data of each integrated photovoltaic and energy storage system is kept below the discharge performance characteristic threshold, thereby improving the lifespan of the integrated photovoltaic and energy storage systems.

[0078] In addition, this method may also include:

[0079] By conducting performance tests on the photovoltaic-storage integrated system under working environment and obtaining the discharge performance attenuation coefficient under various working environment data, a knowledge graph is constructed based on the discharge performance attenuation coefficient under various working environment data.

[0080] Acquire the operating environment data of each integrated photovoltaic and energy storage system, and input the current operating environment data of the integrated photovoltaic and energy storage system into the knowledge graph for data matching;

[0081] By matching data, the discharge performance attenuation coefficient of each photovoltaic-storage integrated system under the working environment data is obtained;

[0082] Based on the discharge performance attenuation coefficient of each photovoltaic-storage integrated system under the aforementioned working environment data, the discharge performance characteristic data of the photovoltaic-storage integrated system within a preset time is updated, and discharge optimization is performed based on the updated discharge performance characteristic data of the photovoltaic-storage integrated system within the preset time using a genetic algorithm.

[0083] It should be noted that the discharge performance attenuation coefficient is the ratio between the discharge performance characteristic data of the photovoltaic-storage integrated system under standard temperature (25 degrees Celsius) and the discharge performance characteristic data under real-time temperature. This method can further optimize the discharge strategy of the photovoltaic-storage integrated system.

[0084] In addition, the power allocation strategy based on the power capacity of the integrated photovoltaic and energy storage system may also include:

[0085] Historical service data of the integrated photovoltaic and energy storage system is obtained, and a Bayesian network is introduced into it. The historical service data of the integrated photovoltaic and energy storage system is input into the Bayesian network for training, and the trained Bayesian network is obtained.

[0086] The service data of the integrated photovoltaic and energy storage system within a preset time period is obtained, and the service data of the integrated photovoltaic and energy storage system within the preset time period is input into the trained Bayesian network for prediction.

[0087] The fault prediction time of each photovoltaic-storage integrated system is obtained, and the power supply period corresponding to the power supply demand in the target area is obtained. It is then determined whether the fault prediction time of the photovoltaic-storage integrated system is within the power supply period corresponding to the power supply demand in the target area.

[0088] When the fault prediction time is not within the power supply period corresponding to the power supply demand in the target area, the corresponding photovoltaic-storage integrated system is selected as the recommended photovoltaic-storage integrated system, and the power capacity of the photovoltaic-storage integrated system is configured according to the power capacity of the photovoltaic-storage integrated system to obtain the power configuration strategy.

[0089] It should be noted that this method can improve the rationality of power allocation.

[0090] like Figure 3 As shown, the second aspect of the present invention provides a system 3 for optimizing energy storage charging and discharging strategies in a photovoltaic-energy storage integrated system. The system 3 includes a memory 31 and a processor 32. The memory 31 includes a program for optimizing energy storage charging and discharging strategies in a photovoltaic-energy storage integrated system. When the program for optimizing energy storage charging and discharging strategies in a photovoltaic-energy storage integrated system is executed by the processor 32, it implements any of the steps of the optimization method for energy storage charging and discharging strategies in a photovoltaic-energy storage integrated system.

[0091] like Figure 4 As shown, a third aspect of the present invention provides a terminal device, comprising:

[0092] Power demand forecasting module 10 constructs a power demand forecasting model and uses the power demand forecasting model to predict the power demand information of the target area;

[0093] The charging strategy configuration module 20 configures the power capacity of the photovoltaic-storage integrated system according to the power demand information of the target area, performs power configuration according to the power capacity of the photovoltaic-storage integrated system, obtains the power configuration strategy, and configures the charging strategy of the photovoltaic-storage integrated system according to the power configuration strategy.

[0094] The performance prediction model construction module 30 acquires the historical discharge performance change characteristics data of the photovoltaic-storage integrated system under various charging strategy data, and constructs the performance prediction model of the photovoltaic-storage integrated system based on the historical discharge performance change characteristics data of the photovoltaic-storage integrated system under various charging strategy data.

[0095] The discharge optimization module 40 predicts the discharge performance characteristics of the integrated photovoltaic and energy storage system within a preset time using the performance prediction model of the integrated photovoltaic and energy storage system, and performs discharge optimization based on the discharge performance characteristics of the integrated photovoltaic and energy storage system within the preset time using a genetic algorithm.

[0096] Furthermore, in this device, a power demand prediction model is constructed to predict the power demand information of the target area, specifically including:

[0097] A power demand prediction model is built based on deep neural networks, and power demand information of the target area is obtained through big data under various factors. The data of each factor and the power demand information are used as nodes to build a directed descriptive relationship.

[0098] Nodes are connected based on directed descriptive relationships to form a topology graph. The relevant adjacency matrix is ​​obtained based on the topology graph. The relevant adjacency matrix is ​​input into the power demand prediction model for training, and the trained power demand prediction model is obtained.

[0099] Data on influencing factors in the target area within a preset time period is obtained, and this data is then input into the trained power demand prediction model to make predictions and obtain power demand information for the target area.

[0100] Furthermore, in this device, the power capacity of the photovoltaic-storage integrated system is configured according to the power demand information of the target area, the power is configured according to the power capacity of the photovoltaic-storage integrated system, the power configuration strategy is obtained, and the charging strategy of the photovoltaic-storage integrated system is configured according to the power configuration strategy, specifically:

[0101] Obtain the maximum power capacity information of each photovoltaic-storage integrated system in the target area, and calculate the required number of photovoltaic-storage integrated systems based on the power supply demand information of the target area and the maximum power capacity information of each photovoltaic-storage integrated system in the target area.

[0102] Based on the quantity information of the required integrated photovoltaic and energy storage systems, randomly select the working integrated photovoltaic and energy storage systems to determine the working combination of the integrated photovoltaic and energy storage systems;

[0103] Configure the power capacity of the integrated photovoltaic and energy storage system according to the working combination of the integrated photovoltaic and energy storage system and the power supply demand information of the target area.

[0104] Power allocation is performed according to the power capacity of the photovoltaic-storage integrated system, power allocation strategy is obtained, and charging strategy is configured for the photovoltaic-storage integrated system according to the power allocation strategy.

[0105] Furthermore, in this device, historical discharge performance variation characteristic data of the integrated photovoltaic and energy storage system under various charging strategy data are acquired, and a performance prediction model of the integrated photovoltaic and energy storage system is constructed based on the historical discharge performance variation characteristic data of the integrated photovoltaic and energy storage system under various charging strategy data, specifically as follows:

[0106] Construct timestamps and statistically analyze the discharge performance change characteristics of the photovoltaic-storage integrated system under various charging strategy data at each timestamp, thus forming historical discharge performance change characteristics data of the photovoltaic-storage integrated system under various charging strategy data.

[0107] A performance prediction model for the photovoltaic-storage integrated system is constructed based on a deep neural network. The historical discharge performance change characteristics of the photovoltaic-storage integrated system under various charging strategies are input into the performance prediction model of the photovoltaic-storage integrated system for training.

[0108] When the loss function of the performance prediction model of the integrated photovoltaic and energy storage system converges to the preset value, the model parameters of the performance prediction model of the integrated photovoltaic and energy storage system are saved, and the performance prediction model of the integrated photovoltaic and energy storage system is output.

[0109] Furthermore, in this device, the discharge performance characteristics of the integrated photovoltaic and energy storage system are predicted within a preset time period using a performance prediction model of the integrated photovoltaic and energy storage system. Specifically:

[0110] Acquire the discharge performance change characteristic data of each photovoltaic-storage integrated system within a preset time period, and input the discharge performance change characteristic data of each photovoltaic-storage integrated system within the preset time period into the performance prediction model of the photovoltaic-storage integrated system for prediction.

[0111] By predicting, the discharge performance characteristics data of the photovoltaic-storage integrated system within a preset time period are obtained, and the discharge performance characteristics data of the photovoltaic-storage integrated system within the preset time period are output.

[0112] Furthermore, in this device, a genetic algorithm is used to optimize the discharge performance based on the discharge performance characteristics data of the integrated photovoltaic and energy storage system within a preset time period. Specifically, this includes:

[0113] Based on the discharge performance characteristic data of the photovoltaic-storage integrated system within a preset time, a discharge performance characteristic threshold is set for each photovoltaic-storage integrated system, and the real-time discharge amount data of each photovoltaic-storage integrated system is initialized.

[0114] A genetic algorithm is introduced, the number of generations is set based on the genetic algorithm, and it is determined whether the real-time discharge data of each photovoltaic-storage integrated system is less than the discharge performance characteristic threshold.

[0115] When the real-time discharge data of each photovoltaic-storage integrated system is not uniformly less than the discharge performance characteristic threshold, the real-time discharge data of the photovoltaic-storage integrated system is readjusted based on the genetic generation until they are all less than the discharge performance characteristic threshold.

[0116] When the real-time discharge data of each photovoltaic-storage integrated system is less than the discharge performance characteristic threshold, the real-time discharge data of each photovoltaic-storage integrated system is output, and discharge optimization is performed according to the real-time discharge data of the photovoltaic-storage integrated system.

[0117] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a program for optimizing the energy storage charging and discharging strategy in an integrated photovoltaic and energy storage system. When the program for optimizing the energy storage charging and discharging strategy in an integrated photovoltaic and energy storage system is executed by a processor, it implements any of the steps of the optimization method for optimizing the energy storage charging and discharging strategy in an integrated photovoltaic and energy storage system.

[0118] In summary, this invention constructs a power demand prediction model to predict the power demand information of a target area. Based on this model, it configures the energy capacity of the integrated photovoltaic-storage system (PV-SES) according to the target area's power demand information. It then allocates power according to the PV-SES's energy capacity, obtains a power allocation strategy, and configures a charging strategy for the PV-SES based on this strategy. This yields historical discharge performance variation data of the PV-SES under various charging strategies. Based on this historical discharge performance variation data, a performance prediction model for the PV-SES is constructed. Finally, this model predicts the discharge performance characteristics of the PV-SES within a preset time period, and a genetic algorithm optimizes the discharge performance based on this data. This invention improves the lifespan of the integrated photovoltaic-storage system by configuring its energy capacity according to the target area's power demand information and dynamically adjusting its charging and discharging strategies based on its discharge performance.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0120] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0121] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0122] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0124] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for optimizing energy storage charging and discharging strategy in a photo-energy storage integrated system, characterized in that, Specifically comprising: The power supply demand prediction model is constructed, and the power supply demand information of the target area is predicted through the power supply demand prediction model; comprising: Based on the deep neural network, the power supply demand prediction model is constructed, and the power supply demand information of the target area under each factor data is obtained through big data, each factor data and the power supply demand information are taken as nodes, and a directed description relationship is constructed; Based on the directed description relationship, the nodes are connected to form a topological structure diagram, the related adjacency matrix is obtained based on the topological structure diagram, the related adjacency matrix is input into the power supply demand prediction model for training, and the trained power supply demand prediction model is obtained; The influence factor data of the target area within a preset time is obtained, the influence factor data of the target area within a preset time is input into the trained power supply demand prediction model for prediction, and the power supply demand information of the target area is obtained; According to the power supply demand information of the target area, the electric energy capacity of the light storage integrated system is configured, the electric energy capacity of the light storage integrated system is configured, the electric energy configuration strategy is obtained, and the charging strategy configuration of the light storage integrated system is carried out according to the electric energy configuration strategy; The historical discharge performance change characteristic data of the light storage integrated system under each charging strategy data is obtained, and the performance prediction model of the light storage integrated system is constructed according to the historical discharge performance change characteristic data of the light storage integrated system under each charging strategy data; The discharge performance characteristic data of the light storage integrated system within a preset time is predicted through the performance prediction model of the light storage integrated system, and the discharge optimization is carried out according to the discharge performance characteristic data of the light storage integrated system within a preset time through genetic algorithm. 2.The method of claim 1, wherein, According to the power supply demand information of the target area, the electric energy capacity of the light storage integrated system is configured, the electric energy capacity of the light storage integrated system is configured, the electric energy configuration strategy is obtained, and the charging strategy configuration of the light storage integrated system is carried out according to the electric energy configuration strategy, specifically: The maximum electric energy capacity information of each light storage integrated system of the target area is obtained, the number information of the required light storage integrated system is calculated according to the power supply demand information of the target area and the maximum electric energy capacity information of each light storage integrated system of the target area; According to the number information of the required light storage integrated system, the working light storage integrated system is randomly selected, and the working combination of the light storage integrated system is determined; According to the working combination of the light storage integrated system and the power supply demand information of the target area, the electric energy capacity of the light storage integrated system is configured; According to the electric energy capacity of the light storage integrated system, the electric energy configuration strategy is obtained, and the charging strategy configuration of the light storage integrated system is carried out according to the electric energy configuration strategy. 3.The method of claim 1, wherein, The historical discharge performance change characteristic data of the light storage integrated system under each charging strategy data is obtained, and the performance prediction model of the light storage integrated system is constructed according to the historical discharge performance change characteristic data of the light storage integrated system under each charging strategy data, specifically: The construction time stamp is constructed, and the discharge performance change characteristic data of the integrated system of photovoltaic and energy storage under each charging strategy data is counted to form the historical discharge performance change characteristic data of the integrated system of photovoltaic and energy storage under each charging strategy data; The performance prediction model of the integrated system of photovoltaic and energy storage is constructed based on a deep neural network, and the historical discharge performance change characteristic data of the integrated system of photovoltaic and energy storage under each charging strategy data is input into the performance prediction model of the integrated system of photovoltaic and energy storage for training. When the loss function of the performance prediction model of the integrated system of photovoltaic and energy storage converges to a preset value, the model parameters of the performance prediction model of the integrated system of photovoltaic and energy storage are saved, and the performance prediction model of the integrated system of photovoltaic and energy storage is output. 4.The method of claim 1, wherein, The discharge performance characteristic data of the integrated system of photovoltaic and energy storage within a preset time is predicted through the performance prediction model of the integrated system of photovoltaic and energy storage, specifically as follows: The discharge performance change characteristic data of each integrated system of photovoltaic and energy storage within a preset time is obtained, and the discharge performance change characteristic data of each integrated system of photovoltaic and energy storage within a preset time is input into the performance prediction model of the integrated system of photovoltaic and energy storage for prediction. Through prediction, the discharge performance characteristic data of the integrated system of photovoltaic and energy storage within a preset time is obtained, and the discharge performance characteristic data of the integrated system of photovoltaic and energy storage within a preset time is output.

5. The method of claim 1, wherein, Discharge optimization is performed on the discharge performance characteristic data of the integrated system of photovoltaic and energy storage within a preset time through a genetic algorithm, specifically as follows: The discharge performance characteristic threshold of the integrated system of photovoltaic and energy storage is set for each integrated system of photovoltaic and energy storage according to the discharge performance characteristic data of the integrated system of photovoltaic and energy storage within a preset time, and the real-time discharge amount data of each integrated system of photovoltaic and energy storage is initialized; The genetic algorithm is introduced, the number of generations of the genetic algorithm is set, and it is determined whether the real-time discharge amount data of each integrated system of photovoltaic and energy storage is less than the discharge performance characteristic threshold; When the real-time discharge amount data of each integrated system of photovoltaic and energy storage is not less than the discharge performance characteristic threshold, genetic operation is performed based on the number of generations of the genetic algorithm, and the real-time discharge amount data of the integrated system of photovoltaic and energy storage is readjusted until it is less than the discharge performance characteristic threshold; When the real-time discharge amount data of each integrated system of photovoltaic and energy storage is less than the discharge performance characteristic threshold, the real-time discharge amount data of each integrated system of photovoltaic and energy storage is output, and discharge optimization is performed according to the real-time discharge amount data of the integrated system of photovoltaic and energy storage.

6. An energy storage charging and discharging strategy optimization system in a light and energy storage integrated system, characterized in that, The system includes a memory and a processor, and the memory includes an energy storage charge and discharge strategy optimization method program in the integrated system of photovoltaic and energy storage. When the energy storage charge and discharge strategy optimization method program in the integrated system of photovoltaic and energy storage is executed by the processor, the steps of the energy storage charge and discharge strategy optimization method in the integrated system of photovoltaic and energy storage as claimed in any one of claims 1-5 are implemented.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium includes an energy storage charge and discharge strategy optimization method program in the integrated system of photovoltaic and energy storage. When the energy storage charge and discharge strategy optimization method program in the integrated system of photovoltaic and energy storage is executed by the processor, the steps of the energy storage charge and discharge strategy optimization method in the integrated system of photovoltaic and energy storage as claimed in any one of claims 1-5 are implemented.

Images