A microgrid energy storage control method, energy storage control device and energy storage control platform

Abstract

The present disclosure relates to the field of microgrid energy storage, and specifically to a microgrid energy storage control method, energy storage control equipment, and energy storage control platform, the method comprising: obtaining the historical state of charge and historical output power of multiple energy storage units, training and establishing a multi-objective optimization genetic model of the energy storage unit, obtaining the state of charge and output power of multiple energy storage units in a recent period of time, inputting the multi-objective optimization genetic model, and obtaining new energy storage control parameters of multiple energy storage units; converting the energy storage control parameters of multiple energy storage units into multiple data streams of a controller capable of configuring multiple energy storage units, and configuring the multiple data streams to the controller to realize the control strategy update of multiple energy storage units in the microgrid. The present disclosure can update the energy storage control parameters used to control the operation strategies of multiple energy storage units according to the multi-objective optimization genetic model obtained by historical data training, and realize the online configuration of the controller.

Description

Technical Field

[0001] The present disclosure relates to the field of microgrid energy storage, and in particular to a microgrid energy storage control method, energy storage control equipment and energy storage control platform. Background Art

[0002] Microgrid energy storage usually includes some small-capacity distributed power sources, such as wind turbine energy storage units, solar photovoltaic cells, fuel cells, steam turbine power generation units, electric vehicle energy storage units, hydropower energy storage units, etc. The above energy storage units are connected to the microgrid and cooperate with the large power grid to realize the power supply and energy storage of the entire power grid. If the energy storage of the microgrid is not well controlled, it will affect the power supply fluctuations of the entire power grid, and will also affect the charge state and life of the energy storage units in the microgrid.

[0003] Usually, energy storage units in microgrids are intelligently controlled to achieve a balance between energy storage and power supply of each energy storage unit. For example, the fluctuation of output power of photovoltaic arrays and wind turbines is fully compensated by fuel cell groups, or some adaptive methods are used to adaptively change the control strategy of the charge state of energy storage units to improve the operating environment of energy storage units. However, whether it is an adaptive method or the charge balance control of each energy storage unit, it changes with the change of the operating environment. When switching the control strategy, it is usually necessary to shut down the system or suspend the control strategy to update the control program of each energy storage unit or the microgrid master control, which will cause temporary deafness of microgrid control and increase the probability of sudden risk of microgrid control. Summary of the invention

[0004] The present disclosure provides a microgrid energy storage control method, energy storage control device and energy storage control platform, which can solve at least one of the problems mentioned in the background technology. To solve the above technical problems, the present disclosure provides the following technical solutions:

[0005] As one aspect of an embodiment of the present disclosure, a microgrid energy storage control method is provided, comprising the following steps:

[0006] Obtaining historical state of charge and historical output power of multiple energy storage units, wherein the historical state of charge includes the maximum value, minimum value and average value of the state of charge of the energy storage unit in different time periods, and the historical output power includes the maximum output power of the energy storage unit and the average output power in different time periods;

[0007] Based on the historical state of charge and historical output power of multiple energy storage units, training and establishing a multi-objective optimization genetic model of energy storage units, wherein the multi-objective optimization genetic model updates energy storage control parameters for controlling operation strategies of multiple energy storage units according to the state of charge and output power of multiple energy storage units;

[0008] Obtaining the state of charge and output power of multiple energy storage units in a recent period of time, inputting them into the multi-objective optimization genetic model, and obtaining new energy storage control parameters of the multiple energy storage units;

[0009] The energy storage control parameters of the multiple energy storage units are converted into multiple data streams of a controller capable of configuring the multiple energy storage units, and the multiple data streams are configured to the controller to implement control strategy updates for the multiple energy storage units in the microgrid.

[0010] Optionally, training and establishing a multi-objective optimization genetic model for an energy storage unit includes:

[0011] According to prior knowledge, data with poor adaptability in the historical state of charge and historical output power of multiple energy storage units are eliminated, and an initial population with uniform distribution is generated;

[0012] Performing real number encoding and population replication on the initial population to obtain a population P with a size at least twice that of the initial population;

[0013] According to the energy storage and power supply balance requirements of multiple energy storage units in the microgrid, a multi-objective evaluation function is established to evaluate individual fitness, and the multi-objective evaluation function is used to select individuals in the population P to obtain individuals with high fitness;

[0014] The selected individuals with high fitness are cross-interchanged with other individuals in the population P in terms of charge state and output power to generate new individuals, and the new individuals are used as individuals of the population P to form a new population Q;

[0015] The population P and the new population Q are combined to obtain an evolved population, and a new round of selection is performed on the evolved population based on the multi-objective evaluation function to obtain a stable population consistent with the initial population size to form a multi-objective optimization genetic model with a multi-objective evaluation function and a stable population.

[0016] Optionally, obtaining new energy storage control parameters of multiple energy storage units includes:

[0017] The state of charge and output power of multiple energy storage units in a recent period of time are encoded as real numbers as individual populations;

[0018] Selecting individuals with high fitness from the individual population according to a multi-objective evaluation function;

[0019] The individuals with high fitness are cross-exchanged with individuals in the multi-objective optimization genetic model to generate a new population Q', and the new population Q' is combined with the stable population in the multi-objective optimization genetic model, and a new round of selection is performed based on the multi-objective evaluation function to obtain the optimal individual, and the energy storage control parameters of multiple energy storage units are generated based on the optimal individual.

[0020] Optionally, the energy storage and power supply balance requirements of multiple energy storage units in the microgrid include:

[0021] It is required that the sum of the output powers of the multiple energy storage units at the minimum charge state is greater than the peak load, where the peak load is the peak load that occurs in a short period of time in the power system to which the microgrid is connected;

[0022] Furthermore, it is required that the sum of the energy storage of the multiple energy storage units at the average charge value state is greater than the basic load, and the basic load is a load that exists stably in the power system.

[0023] Optionally, the energy storage and power supply balance requirements of multiple energy storage units in the microgrid also include:

[0024] The capacity of the generator sets corresponding to the multiple energy storage units is sufficient to meet the requirements at peak loads and the overload protection requirements caused by peak loads;

[0025] and, the output dispatching capability of multiple energy storage units.

[0026] As another aspect of the embodiments of the present disclosure, there is provided an energy storage control device, including:

[0027] A historical data acquisition unit, which acquires the historical state of charge and historical output power of multiple energy storage units, wherein the historical state of charge includes the maximum value, minimum value and average value of the state of charge of the energy storage unit in different time periods, and the historical output power includes the maximum output power of the energy storage unit and the average output power in different time periods;

[0028] A model building unit, based on the historical state of charge and historical output power of the multiple energy storage units, trains and builds a multi-objective optimization genetic model of the energy storage units, wherein the multi-objective optimization genetic model updates energy storage control parameters for controlling the operation strategies of the multiple energy storage units according to the state of charge and output power of the multiple energy storage units;

[0029] An energy storage control parameter updating unit obtains the state of charge and output power of multiple energy storage units in a recent period of time, inputs them into the multi-objective optimization genetic model, and obtains new energy storage control parameters of multiple energy storage units;

[0030] The control strategy configuration module converts the energy storage control parameters of the multiple energy storage units into multiple data streams of the controller capable of configuring the multiple energy storage units, and configures the multiple data streams to the controller to implement the control strategy update of the multiple energy storage units in the microgrid.

[0031] Optionally, the model building unit further includes:

[0032] According to prior knowledge, data with poor adaptability in the historical state of charge and historical output power of multiple energy storage units are eliminated, and an initial population with uniform distribution is generated;

[0033] Performing real number encoding and population replication on the initial population to obtain a population P with a size at least twice that of the initial population;

[0034] According to the energy storage and power supply balance requirements of multiple energy storage units in the microgrid, a multi-objective evaluation function is established to evaluate individual fitness, and the multi-objective evaluation function is used to select individuals in the population P to obtain individuals with high fitness;

[0035] The selected individuals with high fitness are cross-interchanged with other individuals in the population P in terms of charge state and output power to generate new individuals, and the new individuals are used as individuals of the population P to form a new population Q;

[0036] The population P and the new population Q are combined to obtain an evolved population, and a new round of selection is performed on the evolved population based on the multi-objective evaluation function to obtain a stable population consistent with the initial population size to form a multi-objective optimization genetic model with a multi-objective evaluation function and a stable population.

[0037] Optionally, the model building unit further includes:

[0038] The state of charge and output power of multiple energy storage units in a recent period of time are encoded as real numbers as individual populations;

[0039] Selecting individuals with high fitness from the individual population according to a multi-objective evaluation function;

[0040] The individuals with high fitness are cross-exchanged with individuals in the multi-objective optimization genetic model to generate a new population Q', and the new population Q' is combined with the stable population in the multi-objective optimization genetic model, and a new round of selection is performed based on the multi-objective evaluation function to obtain the optimal individual, and the energy storage control parameters of multiple energy storage units are generated based on the optimal individual.

[0041] Optionally, the energy storage and power supply balance requirements of multiple energy storage units in the microgrid include:

[0042] It is required that the sum of the output powers of the multiple energy storage units at the minimum charge state is greater than the peak load, where the peak load is the peak load that occurs in a short period of time in the power system to which the microgrid is connected;

[0043] Furthermore, it is required that the sum of the energy storage of the multiple energy storage units at the average charge value state is greater than the basic load, and the basic load is a load that exists stably in the power system.

[0044] As another aspect of an embodiment of the present disclosure, an energy storage control platform is provided, comprising: the energy storage control device as described above and multiple controllers on multiple energy storage units, wherein a control strategy configuration module in the energy storage control device configures multiple data streams to the multiple controllers.

[0045] Compared with the prior art, the present invention can update the energy storage control parameters used to control the operation strategies of multiple energy storage units according to the multi-objective optimization genetic model obtained by training historical data, realize the online configuration of the controller, reduce the risks and costs brought by shutdown and maintenance, which is equivalent to the evolution of hardware and facilitates the adaptive update of the system. Preferably, multiple controllers can adopt programmable logic arrays that are easy to program hardware, such as FPGA, so that hardware updates can be realized to make the system operation more reliable and faster. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a flow chart of the microgrid energy storage control method in Embodiment 1 of the present disclosure;

[0047] Figure 2 A flowchart of training and establishing a multi-objective optimization genetic model for an energy storage unit in Example 1 of the present disclosure;

[0048] Figure 3 A flow chart for obtaining energy storage control parameters in Embodiment 1 of the present disclosure;

[0049] Figure 4 It is a schematic block diagram of the energy storage control platform;

[0050] Figure 5 It is a schematic block diagram of the energy storage control device. DETAILED DESCRIPTION

[0051] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0052] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0053] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0054] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0055] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle logic. Due to space limitations, the present disclosure will not go into details.

[0056] In addition, the present disclosure also provides energy storage control equipment and energy storage control platform, which can be used to implement any microgrid energy storage control method provided by the present disclosure. The corresponding technical solutions and descriptions are referred to the corresponding records in the method part and will not be repeated here.

[0057] The execution subject of the microgrid energy storage control method may be a computer or other device capable of realizing energy storage control. For example, the method may be executed by a terminal device or a server or other processing device, wherein the terminal device may be a user equipment (UE), a personal digital assistant (PDA), a computing device, an industrial control device, etc. In some possible implementations, the microgrid energy storage control method may be implemented by a processor calling a computer-readable instruction stored in a memory.

[0058] Example 1

[0059] This embodiment provides a microgrid energy storage control method, such as Figure 1 As shown, the following steps are included:

[0060] S10, obtaining historical state of charge and historical output power of multiple energy storage units, wherein the historical state of charge includes the maximum value, minimum value and average value of the state of charge of the energy storage unit in different time periods, and the historical output power includes the maximum output power of the energy storage unit and the average output power in different time periods;

[0061] Among them, the state of charge is the ratio of the remaining capacity of the battery after it has been used for a period of time or has been shelved for a long time to its capacity in a fully charged state, usually expressed as a percentage; multiple energy storage units may include one or more of the following: wind turbine energy storage units, solar photovoltaic cells, fuel cells, steam turbine power generation units, electric vehicle energy storage units, hydroelectric energy storage units, etc.; among them, the historical output power is the rate at which each energy storage unit can provide electrical energy, usually in kilowatts (kW), and is related to the capacity and performance of the energy storage unit. For example, a 5kW battery energy storage system can provide an output of 5kW of electrical energy within 1 hour. By obtaining the historical state of charge and historical output power, we can know the historical energy storage capacity of the energy storage unit and the output power provided to the microgrid, which is conducive to evaluating the state of charge and output power of the entire microgrid.

[0062] S20, based on the historical state of charge and historical output power of multiple energy storage units, training and establishing a multi-objective optimization genetic model of energy storage units, wherein the multi-objective optimization genetic model updates energy storage control parameters for controlling operation strategies of multiple energy storage units according to the state of charge and output power of multiple energy storage units;

[0063] Among them, Figure 2 As shown, a multi-objective optimization genetic model for energy storage units is trained and established, including:

[0064] S201, eliminating data with poor adaptability from historical charge states and historical output powers of multiple energy storage units according to prior knowledge, and generating an initial population with uniform distribution;

[0065] Among them, the selection of the initial population affects the final performance of the algorithm. The distribution of individuals with strong adaptability, that is, the distribution of the solution space, is actually unclear. It is necessary to select based on prior knowledge to obtain a uniformly distributed initial population. Prior knowledge comes from the experience of the industry, such as the prior knowledge summarized by staff who are more familiar with the design of microgrids or staff who are rich in maintaining microgrids.

[0066] S203, performing real number encoding and population replication on the initial population to obtain a population P at least twice the number of the initial population;

[0067] The initial population in S201 is replicated. For example, the original initial population of N is converted into a population P of (2-5)N after real number coding and population replication.

[0068] S205, establishing a multi-objective evaluation function to evaluate individual fitness according to the energy storage and power supply balance requirements of multiple energy storage units in the microgrid, and applying the multi-objective evaluation function to individuals in the population P to obtain individuals with high fitness;

[0069] Among them, the energy storage and power supply balance requirements of multiple energy storage units in the microgrid include:

[0070] It is required that the sum of the output powers of multiple energy storage units in the minimum charge state is greater than the peak load, which is the peak load that occurs in a short period of time in the power system to which the microgrid is connected. For the peak load, the power supply capacity is required to be strong and able to meet the requirements of the peak power consumption period, that is, if the sum of the output powers of multiple energy storage units in the case of low power can also be greater than the peak load, it is guaranteed that the requirements of the peak power consumption period can be met, which is the most extreme operation guarantee for the microgrid.

[0071] And, it is required that the sum of the energy storage of multiple energy storage units under the average charge state is greater than the basic load, and the basic load is the load that exists stably in the power system. Basic loads such as the power supply requirements for residential electricity consumption and infrastructure require stable power supply. At this time, the average value of the daily energy storage of the energy storage unit under the average charge state can meet the basic load requirements. Among them, both the basic load and the peak load can be obtained based on the historical power consumption of the power system in the power grid to which the microgrid is connected or the newly connected power equipment.

[0072] Among them, the multi-objective evaluation function obtained according to the above requirements can be as follows:

[0073] Among them, P i is the energy storage output power of the energy storage unit, n is the number of energy storage units, P a For peak loads, e.g. The value can be 1.1-1.15 times P a ;

[0074] Where n is the number of energy storage units, W i is the energy storage capacity of the energy storage unit at the average charge state, W a It is the power system's heaviest load multiplied by the base load required per unit time. The value can be 1.05-1.2 times W a The ability of multiple energy storage units to meet the requirements can be evaluated based on the conditions that satisfy the above formula.

[0075] As an optional implementation, the energy storage and power supply balance requirements of multiple energy storage units in the microgrid also include:

[0076] The capacity of the generator sets corresponding to multiple energy storage units is sufficient to meet the requirements during peak loads and the overload protection requirements caused by peak loads. For example, the generator sets provide sufficient capacity to provide sufficient power supply during peak hours. It is also necessary to provide corresponding overload protection facilities for overload problems that may be caused by peak loads to ensure the safety of power supply. If there are overload protection problems, the conditions for triggering the overload protection and the number of triggering times can be counted to evaluate the ability to meet the requirements.

[0077] And, the output scheduling capability of multiple energy storage units, wherein the output scheduling capability can be the scheduling capability that the controller of the energy storage unit itself can output according to load changes to ensure the stability of power supply.

[0078] S207, cross-exchange the state of charge and output power of the selected individuals with high fitness with other individuals in the population P to generate new individuals, and use the new individuals as individuals of the population P to form a new population Q;

[0079] Among them, the crossover transposition in the above steps is the crossover mutation in the genetic algorithm to generate new individuals to achieve the inheritance and gene mutation of individuals with strong adaptability.

[0080] S209, combining the population P and the new population Q to obtain an evolved population, and performing a new round of selection on the evolved population based on the multi-objective evaluation function to obtain a stable population consistent with the initial population size to form a multi-objective optimization genetic model with a multi-objective evaluation function and a stable population. Perform reciprocating iterations to find a set of optimal solutions.

[0081] S30, acquiring the state of charge and output power of multiple energy storage units in a recent period of time, inputting them into the multi-objective optimization genetic model, and obtaining new energy storage control parameters of the multiple energy storage units;

[0082] Among them, the new energy storage control parameters of multiple energy storage units are obtained, such as Figure 3 As shown, including:

[0083] S301, encoding the charge states and output powers of multiple energy storage units over a recent period of time into real numbers as individual populations;

[0084] S303, selecting an individual with high fitness from the individual population according to a multi-objective evaluation function;

[0085] S305. Cross-exchange the individuals with high fitness with the individuals in the multi-objective optimization genetic model to generate a new population Q'. After combining the new population Q' with the stable population in the multi-objective optimization genetic model, a new round of selection is performed based on the multi-objective evaluation function to obtain the optimal individual therein, and energy storage control parameters of multiple energy storage units are generated based on the optimal individual.

[0086] S40, converting the energy storage control parameters of the multiple energy storage units into multiple data streams of a controller capable of configuring the multiple energy storage units, and configuring the multiple data streams to the controller to implement control strategy updates for the multiple energy storage units in the microgrid.

[0087] The controllers of the multiple energy storage units may be a programmable logic array, such as an FPGA, wherein Figure 4 As shown, the entire microgrid energy storage control method is implemented by an energy storage control device, and the energy storage control device is used to implement the configuration of the controllers of multiple energy storage units. Among them, multiple energy storage units correspond to multiple controllers, wherein the controllers are controller 1, controller 2, ..., controller n, wherein n is the number of controllers. Preferably, the controller is an FPGA, wherein the energy storage control device 100 has the ability to generate and configure multiple FPGAs and the data stream required to generate multiple FPGAs, for example, the energy storage control device 100 has Xilinx's ISE to generate data streams, and at the same time, the energy storage control device 100 is configured in passive serial mode to implement the configuration process of the control FPGA.

[0088] Based on the above configuration, the embodiment of the present disclosure proposes that the energy storage control parameters used to control the operation strategies of multiple energy storage units can be updated according to the multi-objective optimization genetic model obtained by training historical data, so as to realize the online configuration of the controller, reduce the risks and costs brought by shutdown and maintenance, which is equivalent to the evolution of hardware and facilitates the adaptive update of the system. Preferably, multiple controllers can adopt programmable logic arrays that are easy to program hardware, such as FPGA, so that hardware updates can be realized to make the system operation more reliable and faster.

[0089] Example 2

[0090] This embodiment provides an energy storage control device 100, such as Figure 5 As shown, including:

[0091] A historical data acquisition unit 1 is used to acquire the historical state of charge and historical output power of multiple energy storage units, wherein the historical state of charge includes the maximum value, minimum value and average value of the state of charge of the energy storage unit in different time periods, and the historical output power includes the maximum output power of the energy storage unit and the average output power in different time periods;

[0092] Among them, the state of charge is the ratio of the remaining capacity of the battery after it has been used for a period of time or has been shelved for a long time to its capacity in a fully charged state, usually expressed as a percentage; multiple energy storage units may include one or more of the following: wind turbine energy storage units, solar photovoltaic cells, fuel cells, steam turbine power generation units, electric vehicle energy storage units, hydroelectric energy storage units, etc.; among them, the historical output power is the rate at which each energy storage unit can provide electrical energy, usually in kilowatts (kW), and is related to the capacity and performance of the energy storage unit. For example, a 5kW battery energy storage system can provide an output of 5kW of electrical energy within 1 hour. By obtaining the historical state of charge and historical output power, we can know the historical energy storage capacity of the energy storage unit and the output power provided to the microgrid, which is conducive to evaluating the state of charge and output power of the entire microgrid.

[0093] Model building unit 2, based on the historical state of charge and historical output power of multiple energy storage units, trains and builds a multi-objective optimization genetic model of energy storage units, wherein the multi-objective optimization genetic model updates energy storage control parameters for controlling the operation strategies of multiple energy storage units according to the state of charge and output power of multiple energy storage units;

[0094] Among them, training and establishing a multi-objective optimization genetic model for energy storage units includes:

[0095] According to prior knowledge, data with poor adaptability in the historical state of charge and historical output power of multiple energy storage units are eliminated, and an initial population with uniform distribution is generated;

[0096] Among them, the selection of the initial population affects the final performance of the algorithm. The distribution of individuals with strong adaptability, that is, the distribution of the solution space, is actually unclear. It is necessary to select based on prior knowledge to obtain a uniformly distributed initial population. Prior knowledge comes from the experience of the industry, such as the prior knowledge summarized by staff who are more familiar with the design of microgrids or staff who are rich in maintaining microgrids.

[0097] Performing real number encoding and population replication on the initial population to obtain a population P with a size at least twice that of the initial population;

[0098] The initial population is replicated. For example, the original initial population of N is converted into a population P of (2-5)N after real number coding and population replication.

[0099] According to the energy storage and power supply balance requirements of multiple energy storage units in the microgrid, a multi-objective evaluation function is established to evaluate individual fitness, and the multi-objective evaluation function is used to select individuals in the population P to obtain individuals with high fitness;

[0100] Among them, the energy storage and power supply balance requirements of multiple energy storage units in the microgrid include:

[0101] It is required that the sum of the output powers of multiple energy storage units in the minimum charge state is greater than the peak load, which is the peak load that occurs in a short period of time in the power system to which the microgrid is connected. For the peak load, the power supply capacity is required to be strong and able to meet the requirements of the peak power consumption period, that is, if the sum of the output powers of multiple energy storage units in the case of low power can also be greater than the peak load, it is guaranteed that the requirements of the peak power consumption period can be met, which is the most extreme operation guarantee for the microgrid.

[0102] And, it is required that the sum of the energy storage of multiple energy storage units under the average charge state is greater than the basic load, and the basic load is the load that exists stably in the power system. Basic loads such as the power supply requirements for residential electricity consumption and infrastructure require stable power supply. At this time, the average value of the daily energy storage of the energy storage unit under the average charge state can meet the basic load requirements. Among them, both the basic load and the peak load can be obtained based on the historical power consumption of the power system in the power grid to which the microgrid is connected or the newly connected power equipment.

[0103] Among them, the multi-objective evaluation function obtained according to the above requirements can be as follows:

[0104] Among them, P i is the energy storage output power of the energy storage unit, n is the number of energy storage units, P a For peak loads, e.g. The value can be 1.1-1.15 times P a ;

[0105] Where n is the number of energy storage units, W i is the energy storage capacity of the energy storage unit at the average charge state, W a It is the power system's heaviest load multiplied by the base load required per unit time. The value can be 1.05-1.2 times W a The ability of multiple energy storage units to meet the requirements can be evaluated based on the conditions that satisfy the above formula.

[0106] As an optional implementation, the energy storage and power supply balance requirements of multiple energy storage units in the microgrid also include:

[0107] The capacity of the generator sets corresponding to multiple energy storage units is sufficient to meet the requirements during peak loads and the overload protection requirements caused by peak loads. For example, the generator sets provide sufficient capacity to provide sufficient power supply during peak hours. It is also necessary to provide corresponding overload protection facilities for overload problems that may be caused by peak loads to ensure the safety of power supply. If there are overload protection problems, the conditions for triggering the overload protection and the number of triggering times can be counted to evaluate the ability to meet the requirements.

[0108] And, the output scheduling capability of multiple energy storage units, wherein the output scheduling capability can be the scheduling capability that the controller of the energy storage unit itself can output according to load changes to ensure the stability of power supply.

[0109] The selected individuals with high fitness are cross-interchanged with other individuals in the population P in terms of charge state and output power to generate new individuals, and the new individuals are used as individuals of the population P to form a new population Q;

[0110] Among them, the crossover transposition in the above steps is the crossover mutation in the genetic algorithm to generate new individuals to achieve the inheritance and gene mutation of individuals with strong adaptability.

[0111] The population P and the new population Q are combined to obtain an evolved population, and a new round of selection is performed on the evolved population based on the multi-objective evaluation function to obtain a stable population with the same number as the initial population to form a multi-objective optimization genetic model with a multi-objective evaluation function and a stable population. Repeated iterations are performed to find a set of optimal solutions.

[0112] The energy storage control parameter updating unit 3 obtains the state of charge and output power of multiple energy storage units in a recent period of time, inputs them into the multi-objective optimization genetic model, and obtains new energy storage control parameters of multiple energy storage units;

[0113] The energy storage control parameters of the new multiple energy storage units are obtained, including:

[0114] The state of charge and output power of multiple energy storage units in a recent period of time are encoded as real numbers as individual populations;

[0115] Selecting individuals with high fitness from the individual population according to a multi-objective evaluation function;

[0116] The individuals with high fitness are cross-exchanged with individuals in the multi-objective optimization genetic model to generate a new population Q', and the new population Q' is combined with the stable population in the multi-objective optimization genetic model, and a new round of selection is performed based on the multi-objective evaluation function to obtain the optimal individual, and the energy storage control parameters of multiple energy storage units are generated based on the optimal individual.

[0117] The control strategy configuration module 4 converts the energy storage control parameters of the multiple energy storage units into multiple data streams of the controller capable of configuring the multiple energy storage units, and configures the multiple data streams to the controller to realize the control strategy update of the multiple energy storage units in the microgrid.

[0118] The controllers of the multiple energy storage units may be a programmable logic array, such as an FPGA, wherein Figure 4 As shown, the entire microgrid energy storage control method is implemented by an energy storage control device, and the energy storage control device is used to configure the controllers of multiple energy storage units.

[0119] Example 3

[0120] This embodiment provides an energy storage control platform, such as Figure 4 As shown, it includes: the energy storage control device 100 as in Example 2 and multiple controllers on multiple energy storage units, and the control strategy configuration module in the energy storage control device configures multiple data streams to the multiple controllers. Among them, multiple energy storage units correspond to multiple controllers, wherein the controllers are controller 1, controller 2, ..., controller n, where n is the number of controllers. Preferably, the controller is an FPGA, wherein the energy storage control device 100 has the ability to generate and configure multiple FPGAs and the data streams required to generate multiple FPGAs, for example, the energy storage control device 100 has Xilinx's ISE to generate data streams, and at the same time, the energy storage control device 100 is configured to a passive serial mode to implement the configuration process of the control FPGA.

[0121] Although embodiments of the present disclosure have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present disclosure, and the scope of the present disclosure is defined by the appended claims and their equivalents.

Claims

1. A microgrid energy storage control method, characterized in that: The steps include: Obtaining historical state of charge and historical output power of multiple energy storage units, wherein the historical state of charge includes the maximum value, minimum value and average value of the state of charge of the energy storage unit in different time periods, and the historical output power includes the maximum output power of the energy storage unit and the average output power in different time periods; Based on the historical state of charge and historical output power of multiple energy storage units, training and establishing a multi-objective optimization genetic model of energy storage units, wherein the multi-objective optimization genetic model updates energy storage control parameters for controlling operation strategies of multiple energy storage units according to the state of charge and output power of multiple energy storage units; Obtaining the state of charge and output power of multiple energy storage units in a recent period of time, inputting them into the multi-objective optimization genetic model, and obtaining new energy storage control parameters of the multiple energy storage units; Converting energy storage control parameters of multiple energy storage units into multiple data streams of a controller capable of configuring multiple energy storage units, and configuring the multiple data streams to the controller to implement control strategy updates for multiple energy storage units in a microgrid; Training and building a multi-objective optimization genetic model for energy storage units, including: According to prior knowledge, data with poor adaptability in the historical state of charge and historical output power of multiple energy storage units are eliminated, and an initial population with uniform distribution is generated; Performing real number encoding and population replication on the initial population to obtain a population P with a size at least twice that of the initial population; According to the energy storage and power supply balance requirements of multiple energy storage units in the microgrid, a multi-objective evaluation function is established to evaluate individual fitness, and the multi-objective evaluation function is used to select individuals in the population P to obtain individuals with high fitness; The selected individuals with high fitness are cross-interchanged with other individuals in the population P in terms of charge state and output power to generate new individuals, and the new individuals are used as individuals of the population P to form a new population Q; The population P and the new population Q are combined to obtain an evolved population, and a new round of selection is performed on the evolved population based on a multi-objective evaluation function to obtain a stable population consistent with the initial population size to form a multi-objective optimization genetic model with a multi-objective evaluation function and a stable population; The new energy storage control parameters of multiple energy storage units are obtained, including: The state of charge and output power of multiple energy storage units in a recent period of time are encoded as real numbers as individual populations; Selecting individuals with high fitness from the individual population according to a multi-objective evaluation function; The individuals with high fitness are cross-exchanged with individuals in the multi-objective optimization genetic model to generate a new population Q', and the new population Q' is combined with the stable population in the multi-objective optimization genetic model, and a new round of selection is performed based on the multi-objective evaluation function to obtain the optimal individual, and the energy storage control parameters of multiple energy storage units are generated based on the optimal individual.

2. The microgrid energy storage control method according to claim 1, characterized in that: Energy storage and power supply balance requirements for multiple energy storage units in a microgrid, including: It is required that the sum of the output powers of the multiple energy storage units at the minimum charge state is greater than the peak load, where the peak load is the peak load that occurs in a short period of time in the power system to which the microgrid is connected; Furthermore, it is required that the sum of the energy storage of the multiple energy storage units at the average charge value state is greater than the basic load, and the basic load is a load that exists stably in the power system.

3. The microgrid energy storage control method according to claim 2, characterized in that: The energy storage and power supply balance requirements of multiple energy storage units in the microgrid also include: The capacity of the generator sets corresponding to the multiple energy storage units is sufficient to meet the requirements at peak loads and the overload protection requirements caused by peak loads; and, the output dispatching capability of multiple energy storage units.

4. An energy storage control device, characterized in that: include: A historical data acquisition unit, which acquires the historical state of charge and historical output power of multiple energy storage units, wherein the historical state of charge includes the maximum value, minimum value and average value of the state of charge of the energy storage unit in different time periods, and the historical output power includes the maximum output power of the energy storage unit and the average output power in different time periods; A model building unit, based on the historical state of charge and historical output power of the multiple energy storage units, trains and builds a multi-objective optimization genetic model of the energy storage units, wherein the multi-objective optimization genetic model updates energy storage control parameters for controlling the operation strategies of the multiple energy storage units according to the state of charge and output power of the multiple energy storage units; An energy storage control parameter updating unit obtains the state of charge and output power of multiple energy storage units in a recent period of time, inputs them into the multi-objective optimization genetic model, and obtains new energy storage control parameters of multiple energy storage units; A control strategy configuration module converts energy storage control parameters of multiple energy storage units into multiple data streams of a controller capable of configuring multiple energy storage units, and configures the multiple data streams to the controller to implement control strategy updates for multiple energy storage units in a microgrid; Training and building a multi-objective optimization genetic model for energy storage units, including: According to prior knowledge, data with poor adaptability in the historical state of charge and historical output power of multiple energy storage units are eliminated, and an initial population with uniform distribution is generated; Performing real number encoding and population replication on the initial population to obtain a population P with a size at least twice that of the initial population; According to the energy storage and power supply balance requirements of multiple energy storage units in the microgrid, a multi-objective evaluation function is established to evaluate individual fitness, and the multi-objective evaluation function is used to select individuals in the population P to obtain individuals with high fitness; The selected individuals with high fitness are cross-interchanged with other individuals in the population P in terms of charge state and output power to generate new individuals, and the new individuals are used as individuals of the population P to form a new population Q; The population P and the new population Q are combined to obtain an evolved population, and a new round of selection is performed on the evolved population based on a multi-objective evaluation function to obtain a stable population consistent with the initial population size to form a multi-objective optimization genetic model with a multi-objective evaluation function and a stable population; The new energy storage control parameters of multiple energy storage units are obtained, including: The state of charge and output power of multiple energy storage units in a recent period of time are encoded as real numbers as individual populations; Selecting individuals with high fitness from the individual population according to a multi-objective evaluation function; The individuals with high fitness are cross-exchanged with individuals in the multi-objective optimization genetic model to generate a new population Q', and the new population Q' is combined with the stable population in the multi-objective optimization genetic model, and a new round of selection is performed based on the multi-objective evaluation function to obtain the optimal individual, and the energy storage control parameters of multiple energy storage units are generated based on the optimal individual.

5. The energy storage control device according to claim 4, characterized in that: Energy storage and power supply balance requirements for multiple energy storage units in a microgrid, including: It is required that the sum of the output powers of the multiple energy storage units at the minimum charge state is greater than the peak load, where the peak load is the peak load that occurs in a short period of time in the power system to which the microgrid is connected; Furthermore, it is required that the sum of the energy storage of the multiple energy storage units at the average charge value state is greater than the basic load, and the basic load is a load that exists stably in the power system.

6. An energy storage control platform, characterized in that: include: According to the energy storage control device as described in any one of claims 4-5 and multiple controllers on multiple energy storage units, the control strategy configuration module in the energy storage control device configures multiple data streams to the multiple controllers.

Images