Method and device for acquiring energy storage configuration strategy of power distribution network

Abstract

The invention discloses a method and a device for acquiring an energy storage configuration strategy of a power distribution network. The method comprises the steps of obtaining load data of a power distribution network, target parameter data of a power distribution network system of the power distribution network and new energy power supply data of the power distribution network; based on the target parameter data, power flow data of the power distribution network system are determined, and the power flow data are used for representing the flow condition of power in the power distribution network; based on the power flow data, inputting the load data, the target parameter data and the new energy power supply data into an energy storage configuration model of the power distribution network for analysis, and obtaining a target energy storage configuration strategy of the power distribution network, the energy storage configuration model is constructed through historical load data of the power distribution network, historical target parameter data of a power distribution network system and historical new energy power data of the power distribution network, and the target energy storage configuration strategy is used for configuring energy storage resources of the power distribution network. The technical problem that the energy storage configuration strategy for improving the new energy bearing capacity of the power distribution network cannot be effectively obtained is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network, and in particular to a method and device for acquiring an energy storage configuration strategy of a distribution network. Background Art

[0002] As a bridge for distributing electricity to power users, the distribution network supports the normal operation of various production and life activities. Therefore, ensuring the normal and stable operation of the distribution network is of great practical significance. At present, the carrying capacity of the distribution network is mostly evaluated from a single perspective, which makes it difficult to reflect the true carrying capacity of the distribution network for new energy sources, resulting in the inability to effectively obtain the technical problem of energy storage configuration strategy to improve the new energy carrying capacity of the distribution network.

[0003] With respect to the above-mentioned technical problem of being unable to effectively obtain the energy storage configuration strategy of the distribution network, no effective solution has been proposed so far. Summary of the invention

[0004] The embodiments of the present invention provide a method and device for acquiring an energy storage configuration strategy for a distribution network, so as to at least solve the technical problem that an energy storage configuration strategy for improving the new energy carrying capacity of the distribution network cannot be effectively acquired.

[0005] According to one aspect of the embodiment of the invention, a method for obtaining an energy storage configuration strategy for a distribution network is provided. The method may include: obtaining load data of the distribution network, target parameter data of the distribution network system of the distribution network, and new energy power supply data of the distribution network, wherein the target parameter data is used to characterize the power transmission performance and / or power distribution performance of the distribution network system, and the target parameter data is obtained by updating the initial parameter data of the distribution network system; based on the target parameter data, determining the flow data of the distribution network system, wherein the flow data is used to characterize the flow of power in the distribution network; based on the flow data, inputting the load data, the target parameter data and the new energy power supply data into the energy storage configuration model of the distribution network for analysis, and obtaining the target energy storage configuration strategy of the distribution network, wherein the energy storage configuration model is constructed by using the historical load data of the distribution network, the historical target parameter data of the distribution network system and the historical new energy power supply data of the distribution network, and the target energy storage configuration strategy is used to configure the energy storage resources of the distribution network.

[0006] Optionally, based on the flow data, the load data, the target parameter data and the new energy power source data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network, including: based on multiple evaluation indicators of the distribution network, using the distribution network's carrying capacity evaluation model to perform a carrying capacity evaluation on the flow data to obtain multiple evaluation indicator function values ​​of the target node in the distribution network, wherein the carrying capacity evaluation model is used to evaluate the carrying capacity of the distribution network; using the target node's weight allocation strategy to perform a weighted operation on multiple evaluation indicator function values ​​to obtain a comprehensive indicator weight of the target node, wherein the weight allocation strategy is used to weight multiple evaluation indicator function values ​​according to the importance of different evaluation indicators; based on the comprehensive indicator weight, determine the fitness function value of the target node; based on the fitness function value, input the load data, the target parameter data and the new energy power source data into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network.

[0007] Optionally, multiple evaluation indicators include: the proportion of renewable energy power generation, voltage deviation rate, network loss rate, net load deviation rate, power flow imbalance, state fragility, new energy consumption rate and the total capacity of energy storage systems in the distribution network, wherein the proportion of renewable energy power generation is used to characterize the utilization degree of renewable energy in the distribution network, the voltage deviation rate is used to characterize the ratio of the difference between the actual voltage and the rated voltage of the distribution network to the rated voltage, the network loss rate is used to characterize the loss of electric energy in the transmission and distribution process of the distribution network, the net load deviation rate is used to characterize the difference between the net load power and the predicted net load power of the distribution network within the target time period, the power flow imbalance is used to characterize the uneven distribution degree of line transmission power on each branch or node in the distribution network, the state fragility is used to characterize the reliability of the distribution network when abnormal conditions occur, the new energy consumption rate is used to characterize the proportion of new energy used in the distribution network, and the total capacity of the energy storage system is used to characterize the electric energy storage capacity of the distribution network system.

[0008] Optionally, based on the fitness function value, the load data, the target parameter data and the new energy power source data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network, including: based on the fitness function value, determining the dominance information of the target node, wherein the dominance information is used to characterize the dominance relationship between the target node and other nodes in the distribution network except the target node; inputting the load data, the target parameter data and the new energy power source data into the energy storage configuration model for analysis to obtain the initial energy storage configuration strategy; based on the dominance information, using the energy storage configuration model to update the initial energy storage configuration strategy to obtain the target energy storage configuration strategy.

[0009] Optionally, based on the dominance information, the initial energy storage configuration strategy is updated using the energy storage configuration model to obtain a target energy storage configuration strategy, including: based on the dominance information, obtaining an initial inertia weight in the energy storage configuration model; mapping the initial inertia weight using a mapping function of the initial inertia weight to obtain a target inertia weight; updating the energy storage configuration model using the target inertia weight to obtain a target energy storage configuration model; and updating the initial energy storage configuration strategy using the target energy storage configuration model to obtain a target energy storage configuration strategy.

[0010] Optionally, the target energy storage configuration model is used to update the initial energy storage configuration strategy to obtain the target energy storage configuration strategy, including: obtaining the target fitness function value of the distribution network; determining the ratio between the fitness function value and the target fitness function value as the fitness ratio of the target node; comparing the fitness ratio with the fitness function threshold of the target node to obtain a comparison result of the target node; based on the comparison result, updating the initial energy storage configuration strategy to obtain the target energy storage configuration strategy.

[0011] Optionally, based on the comparison result, the initial energy storage configuration strategy is updated to obtain a target energy storage configuration strategy, including: in response to the comparison result being that the fitness ratio is less than or equal to the fitness function threshold, the initial energy storage configuration strategy is updated using the first constraint condition of the target node to obtain the target energy storage configuration strategy; in response to the comparison result being that the fitness ratio is greater than the fitness function threshold, the initial energy storage configuration strategy is updated using the second constraint condition of the target node to obtain the target energy storage configuration strategy.

[0012] According to one aspect of an embodiment of the present invention, there is provided a device for acquiring an energy storage configuration strategy of a distribution network, the device may include: a first acquisition unit, for acquiring load data of the distribution network, target parameter data of a distribution network system of the distribution network, and new energy power supply data of the distribution network, wherein the target parameter data is used to characterize the power transmission performance and / or power distribution performance of the distribution network system, and the target parameter data is obtained by updating the initial parameter data of the distribution network system; a determination unit, for determining the flow data of the distribution network system based on the target parameter data, wherein the flow data is used to characterize the flow of power in the distribution network; a second acquisition unit, for inputting the load data, the target parameter data and the new energy power supply data into an energy storage configuration model of the distribution network for analysis based on the flow data, to obtain a target energy storage configuration strategy of the distribution network, wherein the energy storage configuration model is constructed by using historical load data of the distribution network, historical target parameter data of the distribution network system and historical new energy power supply data of the distribution network, and the target energy storage configuration strategy is used to configure the energy storage resources of the distribution network.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method for obtaining the energy storage configuration strategy of the distribution network of an embodiment of the present invention.

[0014] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, which includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement a method for acquiring an energy storage configuration strategy for a distribution network according to an embodiment of the present invention.

[0015] According to another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in the embodiments of the present invention is implemented.

[0016] In an embodiment of the present invention, load data of a distribution network, target parameter data of a distribution network system of the distribution network, and new energy power source data of the distribution network are obtained, wherein the target parameter data is used to characterize the power transmission performance and / or power distribution performance of the distribution network system, and the target parameter data is obtained by updating the initial parameter data of the distribution network system; based on the target parameter data, flow data of the distribution network system is determined, wherein the flow data is used to characterize the flow of power in the distribution network; based on the flow data, the load data, the target parameter data and the new energy power source data are input into an energy storage configuration model of the distribution network for analysis, to obtain a target energy storage configuration strategy of the distribution network, wherein the energy storage configuration model is constructed by using historical load data of the distribution network, historical target parameter data of the distribution network system and historical new energy power source data of the distribution network, and the target energy storage configuration strategy is used to configure energy storage resources of the distribution network. That is to say, the embodiment of the present invention can first obtain the load data of the distribution network, the target parameter data of the distribution network system of the distribution network, and the new energy power supply data of the distribution network, and then determine the flow data of the distribution network system according to the target parameter data obtained above, and finally input the load data, the target parameter data and the new energy power supply data into the energy storage configuration model of the distribution network for analysis according to the obtained flow data, so as to achieve the purpose of obtaining the target energy storage configuration strategy for configuring the energy storage resources of the distribution network. Considering that after obtaining the load data of the distribution network, the target parameter data of the distribution network system and the new energy power supply data of the distribution network, the flow data of the distribution network system can be determined according to the target parameter data, and then the target energy storage configuration strategy of the distribution network can be obtained by using the energy storage configuration model of the distribution network, thereby solving the technical problem of not being able to effectively obtain the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network, so as to achieve the technical effect of effectively obtaining the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of a method for acquiring an energy storage configuration strategy for a distribution network according to an embodiment of the present invention;

[0019] Figure 2 is a flow chart of a method for improving the carrying capacity of a distribution network based on energy storage site selection and capacity determination according to an embodiment of the present invention;

[0020] Figure 3 is a flow chart of a particle crossover mutation method according to an embodiment of the present invention;

[0021] Figure 4 It is a schematic diagram of a device for acquiring an energy storage configuration strategy of a distribution network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, a method for obtaining an energy storage configuration strategy for a distribution network is provided. It should be noted that in the flowchart of the accompanying drawings, the steps shown therein can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a method for acquiring an energy storage configuration strategy for a distribution network according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0026] Step S101, acquiring load data of the distribution network, target parameter data of the distribution network system of the distribution network, and new energy power source data of the distribution network.

[0027] In the technical solution provided in the above step S101 of the present invention, the load data of the distribution network, the target parameter data of the distribution network system of the distribution network, and the new energy power supply data of the distribution network can be obtained, wherein the target parameter data is used to characterize the power transmission performance and / or power distribution performance of the distribution network system, and the target parameter data is obtained by updating the initial parameter data of the distribution network system.

[0028] Optionally, typical daily data of wind power and photovoltaic power generation in the distribution network is obtained. The load data may be time-sharing load data of each node in the distribution network, and the time-sharing load data may be obtained by obtaining target parameter data and typical daily data of the distribution network system. The target parameter data may be referred to as the network parameters of the distribution network.

[0029] For example, the network parameters of the distribution network system to be calculated and the typical daily data of load, wind power and photovoltaic power are obtained, and the time-sharing load data of each node is obtained according to the network parameters and daily load data.

[0030] For another example, if the data obtained includes power data, and all power data are calculated in megawatts (MW), the input data needs to be unified. The time-sharing load data of each node in the distribution network is obtained according to the system's network parameters and the typical daily total load curve, and the reactive power provided by the grid-connected power source of new energy is ignored. All reactive power is provided by the upper-level power grid and reactive compensation device.

[0031] Step S102: determining the power flow data of the distribution network system based on the target parameter data.

[0032] In the technical solution provided in the above step S102 of the present invention, after obtaining the target parameter data, the flow data of the distribution network system can be determined, wherein the flow data is used to characterize the flow of electricity in the distribution network.

[0033] Optionally, after obtaining the target parameter data, the power flow data of the distribution network system is solved by calling an open source software package (Matpower), and then the next step of processing is performed based on the obtained power flow data.

[0034] Optionally, the power flow data may include: current and voltage, power, load information, device status, network topology information, and fault information of each node in the distribution network. It should be noted that only the power flow data of the distribution network system obtained is illustrated here, and the data type included in the power flow data of the distribution network system is not specifically limited.

[0035] Step S103, based on the power flow data, the load data, the target parameter data and the new energy power source data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network.

[0036] In the technical solution provided in the above step S103 of the present invention, based on the obtained flow data, the load data, the target parameter data and the new energy power supply data can be input into the energy storage configuration model of the distribution network for analysis, so as to achieve the purpose of obtaining the target energy storage configuration strategy of the distribution network, wherein the target energy storage configuration strategy of the distribution network can be the optimal energy storage configuration solution.

[0037] Optionally, the energy storage configuration model is constructed through historical load data of the distribution network, historical target parameter data of the distribution network system and historical new energy power supply data of the distribution network, and the target energy storage configuration strategy is used to configure the energy storage resources of the distribution network.

[0038] Optionally, according to the demand information of the distribution network, the relevant parameters of the energy storage configuration model and the relevant parameters of the particle swarm algorithm in the energy storage configuration model are set. For example, according to specific needs, the appropriate population size and number of iterations are set, and according to the configuration quantity demand information of the energy storage system, the particle dimension is set. The particle dimension setting is shown in the following formula:

[0039] m=24n+2

[0040] In the above formula, m can be used to represent the particle dimension, including the charging and discharging power of the energy storage in the distribution network at each moment, the energy storage capacity, and the location of the energy storage installation node; n is used to represent the configuration quantity of the energy storage system.

[0041] Furthermore, when initializing the population, in order to improve the initial uniformity of particles to improve their ergodicity and randomness, the search capability of the particle swarm algorithm can be improved while accelerating the convergence speed of the algorithm, so the chaotic mapping nonlinear (Logistic) function is used to generate the initial population, where the Logistic function can be expressed by the following formula:

[0042] Z k+1=4Z k ×(1-Z k )

[0043] Among them, Z0 can be a random number between 0 and 1. Since the energy storage is placed at the node of the distribution network, the one-dimensional particles about the energy storage location in the generated particles need to be rounded each time they are updated. The initialized population is used as the initial optimal population and the optimal particle is selected from it.

[0044] Optionally, after obtaining the power flow data, the load data, target parameter data and new energy power source data are analyzed using a particle swarm algorithm in the energy storage configuration model according to the power flow data to obtain a target energy storage configuration strategy.

[0045] It should be noted that this is only a preferred implementation method for obtaining the target energy storage configuration strategy of the distribution network, and does not specifically limit the process and method for obtaining the target energy storage configuration strategy of the distribution network. As long as the load data, target parameter data and new energy power supply data are input into the energy storage configuration model of the distribution network for analysis based on the flow data, the process and method for obtaining the target energy storage configuration strategy of the distribution network are within the scope of protection of the present invention and are not listed here.

[0046] In the above steps S101 to S103 of the present invention, the load data of the distribution network, the target parameter data of the distribution network system of the distribution network, and the new energy power supply data of the distribution network can be first obtained, and then the flow data of the distribution network system can be determined according to the target parameter data obtained above, and finally the load data, the target parameter data and the new energy power supply data are input into the energy storage configuration model of the distribution network for analysis according to the obtained flow data, so as to achieve the purpose of obtaining the target energy storage configuration strategy for configuring the energy storage resources of the distribution network. Considering that after obtaining the load data of the distribution network, the target parameter data of the distribution network system and the new energy power supply data of the distribution network, the flow data of the distribution network system can be determined according to the target parameter data, and then the target energy storage configuration strategy of the distribution network can be obtained by using the energy storage configuration model of the distribution network, thereby solving the technical problem of not being able to effectively obtain the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network, so as to achieve the technical effect of effectively obtaining the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network.

[0047] The above method of this embodiment is further introduced below.

[0048] As an optional implementation method, step S103, based on the flow data, inputs the load data, target parameter data and new energy power data into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network, including: based on multiple evaluation indicators of the distribution network, using the distribution network's carrying capacity evaluation model to evaluate the flow data, and obtain multiple evaluation indicator function values ​​of the target node in the distribution network, wherein the carrying capacity evaluation model is used to evaluate the carrying capacity of the distribution network; using the target node's weight allocation strategy, weighting operations are performed on multiple evaluation indicator function values ​​to obtain the comprehensive indicator weight of the target node, wherein the weight allocation strategy is used to weight multiple evaluation indicator function values ​​according to the importance of different evaluation indicators; based on the comprehensive indicator weight, the fitness function value of the target node is determined; based on the fitness function value, the load data, target parameter data and new energy power data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network.

[0049] In this embodiment, the carrying capacity of the power flow data can be evaluated based on multiple evaluation indicators of the distribution network using the carrying capacity evaluation model of the distribution network, so as to obtain multiple evaluation indicator function values ​​of the target node in the distribution network, and then the evaluation indicator function value can be weighted using the weight allocation strategy of the target node to achieve the purpose of obtaining the comprehensive indicator weight of the target node, and then the fitness function value of the target node can be determined based on the comprehensive indicator weight obtained above, and finally the load data, target parameter data and new energy power data can be input into the energy storage configuration model of the distribution network for analysis based on the fitness function value obtained above, so as to obtain the target energy storage configuration strategy. Among them, the comprehensive indicator weight can be referred to as the comprehensive weight. In the particle swarm algorithm, the target node can be a specific particle.

[0050] Optionally, multiple evaluation indicators can be preset indicators, such as the proportion of renewable energy power generation, voltage deviation rate, network loss rate, net load deviation rate, power flow imbalance, state vulnerability, renewable energy consumption rate and the total capacity of the energy storage system in the distribution network. It should be noted that only examples are given here for multiple evaluation indicators.

[0051] Optionally, the evaluation index function value can be a specific numerical value corresponding to the evaluation index, for example, the function value of the proportion of renewable energy power generation can be 80.02%; the function value of the voltage deviation rate can be 0.29%; the function value of the network loss rate can be 6.29%; the function value of the net load deviation rate can be 20.62%, etc. Here, only examples are given for the evaluation index function values.

[0052] Optionally, a weight distribution strategy is used to perform a weighted operation on multiple evaluation index function values ​​to obtain the comprehensive index weight of the target node, thereby achieving the purpose of obtaining the fitness function value of the target node, wherein the weight distribution strategy can be a combination of subjective and objective weights. For example, after calculating the function values ​​of various indicators, the function values ​​of various indicators are weighted by combining subjective and objective weights. Among them, the subjective weight uses the hierarchical analysis method to establish a hierarchical structure model, and based on actual experience analysis, the various indicators in the system are compared pairwise to form a judgment matrix, so that the weight of the indicator can be calculated using the square root method, and in order to ensure the rationality of the calculated weight, the result needs to be checked for consistency. If the check fails, the judgment matrix needs to be rebuilt.

[0053] For another example, the objective weight is calculated using the entropy weight method. Before the calculation, the original data needs to be normalized, and the different indicators are dimensionless and unified into standard indicators that can be directly calculated to ensure that the weights are consistent with the objective data. After calculating the subjective and objective weights of the indicators, in order to maximize the unity of the objective and subjective in the weighting of the indicators, thereby improving the accuracy of the weight calculation results, the least squares model of the indicator weight is established using the Lagrangian function, as shown in the following formula:

[0054]

[0055] In the above formula, N s and M can be the number of rows and columns of the indicator value matrix; w aj 、w ej , w are the AHP weight, entropy weight weight and comprehensive weight of indicator j respectively; I can be the normalized indicator value matrix.

[0056] Furthermore, according to the above formula, the comprehensive weight of the indicator can be obtained, and then according to the above comprehensive weight, the fitness function value of the target node is obtained by calculation, and the calculation formula is as follows:

[0057]

[0058] Optionally, after obtaining the fitness function value, based on the fitness function value and the target constraints of the energy storage system of the distribution network, the load data, the target parameter data and the new energy power source data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy, wherein the target constraints can optimize the fitness function value so that the optimized fitness function value can meet the operating constraints of the energy storage system.

[0059] For example, since the particle swarm algorithm will generate many particles that do not meet the actual operation constraints during the search process, it is necessary to add a penalty term to the fitness function value of the particles that violate the constraints so that the final optimization result meets the operation constraints of the energy storage system. The target constraint conditions of the energy storage system can be expressed by the following formula:

[0060]

[0061] In the above formula, and They represent the lower and upper limits of the charge and discharge power of the jth energy storage system respectively; E j (t) is the electric energy stored in the energy storage system j at time t; σ is the current rate of self-discharge; SOC j (t) can be used to indicate the charge state of the energy storage system at time t. In order to prevent overcharging and over-discharging of the energy storage system from affecting the life of the system, it is set between 0.2 and 0.9, and is kept at 0.5 at the beginning and end of an operation cycle; c and d are used to indicate the charge and discharge state of the energy storage system. When the energy storage system is charged, c=1, d=0; when the energy storage system is discharged, c=0, d=1.

[0062] As an optional implementation method, multiple evaluation indicators include: the proportion of renewable energy power generation, voltage deviation rate, network loss rate, net load deviation rate, power flow imbalance, state fragility, new energy consumption rate and the total capacity of the energy storage system in the distribution network, wherein the proportion of renewable energy power generation is used to characterize the utilization degree of renewable energy in the distribution network, the voltage deviation rate is used to characterize the ratio of the difference between the actual voltage and the rated voltage of the distribution network to the rated voltage, the network loss rate is used to characterize the loss of electric energy in the distribution network during the transmission and distribution process, the net load deviation rate is used to characterize the difference between the net load power and the predicted net load power of the distribution network within the target time period, the power flow imbalance is used to characterize the uneven distribution degree of line transmission power on each branch or node in the distribution network, the state fragility is used to characterize the reliability of the distribution network when abnormal conditions occur, the new energy consumption rate is used to characterize the proportion of new energy used in the distribution network, and the total capacity of the energy storage system is used to characterize the electric energy storage capacity of the distribution network system.

[0063] In this embodiment, the carrying capacity of the distribution network is evaluated through six dimensions, and each dimension includes at least one evaluation index, wherein the six dimensions may be flexibility, reliability, stability, safety, quality and economy. Among them, the flexibility of the distribution network can be characterized by the proportion of new energy power generation; the reliability of the distribution network can be characterized by the voltage deviation rate and the network loss rate; the stability of the distribution network can be characterized by the net load deviation rate and the flow imbalance; the safety of the distribution network can be characterized by the state vulnerability; and the quality of the distribution network can be characterized by the new energy consumption rate.

[0064] Optionally, the economic efficiency of the distribution network can be characterized by the total capacity of the energy storage system. For example, when considering the benefits of the energy storage system, its cost should also be considered, and the total capacity of the energy storage system can be selected as an economic indicator.

[0065] Alternatively, the proportion of renewable energy power generation can be expressed by the following formula:

[0066]

[0067] In the above formula, c NG It can be expressed as the proportion of renewable energy power generation; P DG,t It can be expressed as the new energy output at the tth moment; P load,t It can be expressed as the load power at the tth moment.

[0068] Optionally, the voltage deviation rate can be expressed by the following formula:

[0069]

[0070] In the above formula, c RU Used to indicate voltage deviation rate; U N Used to indicate rated voltage; U i,t Used to represent the node voltage at time t.

[0071] Optionally, the network loss rate can be expressed by the following formula:

[0072]

[0073] In the above formula, c LS Used to indicate network loss rate; I i,t It is used to represent the current of the i-th branch at the t-th moment; R i Used to represent the resistance of the i-th branch.

[0074] Optionally, the net load deviation rate may be expressed by the following formula:

[0075]

[0076] In the above formula, c NL Used to indicate the net load deviation rate; P NL,t Used to represent the net load power at time t; P NL,f,t Used to represent the predicted net load power at time t.

[0077] Alternatively, the power flow imbalance can be expressed by the following formula:

[0078]

[0079] In the above formula, c PFUsed to indicate the degree of power flow imbalance; P line,i,t It is used to represent the line transmission power of the i-th branch at the t-th time; P line,ave,t It is used to represent the average line transmission power at time t; P line,max Used to indicate the maximum line transmission power.

[0080] Alternatively, the state vulnerability can be expressed by the following formula:

[0081]

[0082] In the above formula, c GV It is used to represent the state vulnerability index; BV is used to represent the average vulnerability of the power grid; J is used to represent the average balance of the power grid; α and β are weight coefficients, and their sum is 1. Among them, the average vulnerability of the power grid BV can be expressed by the following formula:

[0083]

[0084] In the above formula, N is used to represent the number of nodes in the distribution network system; v t,i Used to represent the vulnerability value of node i at time t; v t,max and v t,min They represent the maximum vulnerability value and the minimum vulnerability value at the tth moment respectively. The average balance degree J of the power grid can be expressed by the following formula:

[0085]

[0086] In the above formula, p t,i It is used to indicate the ratio of the vulnerability of node i at time t to the total vulnerability of the distribution network at the current time.

[0087] Alternatively, the new energy consumption rate can be expressed by the following formula:

[0088]

[0089] In the above formula, c CN Used to indicate the new energy consumption rate, P DG,f,t Used to represent the predicted power generation of renewable energy at time t.

[0090] As an optional implementation method, based on the fitness function value, the load data, the target parameter data and the new energy power data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network, including: based on the fitness function value, determining the dominance information of the target node, wherein the dominance information is used to characterize the dominance relationship between the target node and other nodes in the distribution network except the target node; inputting the load data, the target parameter data and the new energy power data into the energy storage configuration model for analysis to obtain the initial energy storage configuration strategy; based on the dominance information, using the energy storage configuration model to update the initial energy storage configuration strategy to obtain the target energy storage configuration strategy.

[0091] In this embodiment, after obtaining the fitness function value, the control information of the target node can be determined, and then the load data, target parameter data and new energy power supply data are input into the energy storage configuration model for analysis to obtain the initial energy storage configuration strategy. According to the control information obtained above, the energy storage configuration model can be used to update the initial configuration strategy to achieve the purpose of obtaining the target energy storage configuration strategy.

[0092] Optionally, the initial energy storage configuration strategy is the particle output by the energy storage configuration model after the load data, target parameter data and new energy power data are input into the energy storage configuration model for analysis. The target energy storage configuration strategy can be the historical optimal particle output by the energy storage configuration model after the initial energy storage configuration strategy is updated using the energy storage configuration model according to the control information.

[0093] For example, after calculating the fitness function value of the particle, the particle dominance relationship is determined based on the fitness function value, and the historical optimal particle and the global optimal particle are updated to determine whether the iteration termination requirements are met. If so, the historical optimal particle at this time can be output, which is the optimal energy storage configuration plan; if not, continue to iterate.

[0094] To put it more concretely, the iterative update of the particle swarm algorithm is based on the particle's own information and group information in the n-dimensional solution space to jointly determine its speed and direction of movement, and to continuously approach the optimal solution by changing its position. During the iterative solution, each particle updates its speed and position by tracking two "optimal solutions", and the basic iterative update formula is as follows:

[0095]

[0096] In the above formula, w is used to represent the inertia weight; c1 and c2 are used to represent the individual learning factor and the group learning factor respectively; r1 and r2 are random numbers between 0 and 1; It is used to represent the n-th dimension component in the optimal position vector of the m-th particle at the iter iteration; Used to represent the n-th dimension component in the population optimal position vector at the iter-th iteration.

[0097] As an optional implementation method, based on the dominance information, the initial energy storage configuration strategy is updated using the energy storage configuration model to obtain a target energy storage configuration strategy, including: based on the dominance information, obtaining the initial inertia weight in the energy storage configuration model; mapping the initial inertia weight using a mapping function of the initial inertia weight to obtain a target inertia weight; updating the energy storage configuration model using the target inertia weight to obtain a target energy storage configuration model; and updating the initial energy storage configuration strategy using the target energy storage configuration model to obtain a target energy storage configuration strategy.

[0098] In this embodiment, after obtaining the control information, the initial inertia weight in the energy storage configuration model can be obtained first, and then the initial inertia weight can be mapped using the mapping function of the initial inertia weight to obtain the target inertia weight. Then, according to the target inertia weight obtained above, the energy storage configuration model can be updated to obtain the target energy storage configuration model. The target energy storage configuration model can be used to update the initial energy storage configuration strategy to achieve the purpose of obtaining the target energy storage configuration strategy.

[0099] Optionally, the mapping function may be a Logistic function. For example, to solve the problem of lack of guidance on the value of the inertia weight, the inertia weight may be updated by a nonlinear change of the Logistic chaos mapping, that is, it may be expressed by the following formula:

[0100]

[0101] In the above formula, Z iter Used to represent the Logistic chaotic map value; w min and w max are the minimum and maximum inertia weights, which are generally 0.4 and 0.9 respectively. max It can be expressed as the maximum number of iterations.

[0102] It should be noted that the particle swarm algorithm has the following problems when solving high-dimensional nonlinear problems: there is a lack of guidance on the value of inertia weight, the population diversity is lost quickly, and it is easy to fall into a local solution; and the random initial solution may be very far away from the global optimal solution, which is not conducive to the convergence accuracy and speed of the algorithm; the movement direction of the particles is determined by their individual optimality and group optimality, and there is premature convergence and poor performance on complex problems; there is a lack of guidance in the selection of the global optimal solution of the population. In order to solve the problem that the random initial solution may be far away from the global optimal solution, a new population is generated on the basis of the original population to increase the coverage of the solution space, and individuals with high fitness are selected to enter the next iteration.

[0103] Furthermore, the current population is mirrored about the center of the search space to generate a mirror population. The population between the center of the search space and the mirror population is usually closer to the global optimal solution than the mirror population. Therefore, a population is randomly generated between the center of the search space and the mirror point, which is a new population. The new population can be expressed by the following formula:

[0104]

[0105] In the above formula, x i q Used to represent the i-th dimension variable of the new particle; lb i andub i They are used to represent the lower and upper limits of the value of the i-th dimension variable. In order to ensure that the mirror solution can be performed in a limited space without falling into the local optimum, the traditional fixed boundary is changed to a dynamic boundary, that is, lb i andub i Respectively by min(x i ) and max(x i ) to replace it.

[0106] As an optional implementation method, the target energy storage configuration model is used to update the initial energy storage configuration strategy to obtain the target energy storage configuration strategy, including: obtaining the target fitness function value of the distribution network; determining the ratio between the fitness function value and the target fitness function value as the fitness ratio of the target node; comparing the fitness ratio with the fitness function threshold of the target node to obtain a comparison result of the target node; based on the comparison result, updating the initial energy storage configuration strategy to obtain the target energy storage configuration strategy.

[0107] In this embodiment, the target fitness function value of the distribution network can be obtained first, and then the ratio between the fitness function value and the target fitness function value can be determined as the fitness ratio of the target node. The fitness ratio and the fitness function threshold of the target node are compared to obtain the comparison result of the target node. According to the comparison result, the initial energy storage configuration strategy can be updated to achieve the purpose of obtaining the target energy storage configuration strategy.

[0108] Optionally, the fitness function threshold may be referred to as the threshold. The target fitness function value may be the average fitness value of all nodes in the distribution network. The fitness function value may be referred to as the fitness value.

[0109] For example, by calculating the ratio of the fitness value of the current particle to the average fitness value of all particles in the population, we can determine the strength of the relationship between the current particle and the average level of the population, and thus choose different update methods.

[0110] It should be noted that this is only a preferred implementation method for updating the initial energy storage configuration strategy, and the updating method and process of the initial energy storage configuration strategy are not specifically limited. As long as the fitness function value is compared with the fitness function threshold of the target node, the process and method for updating the initial energy storage configuration strategy are within the protection scope of the present invention and will not be repeated here.

[0111] As an optional implementation method, based on the comparison result, the initial energy storage configuration strategy is updated to obtain a target energy storage configuration strategy, including: in response to the comparison result that the fitness ratio is less than or equal to the fitness function threshold, the initial energy storage configuration strategy is updated using the first constraint condition of the target node to obtain the target energy storage configuration strategy; in response to the comparison result that the fitness ratio is greater than the fitness function threshold, the initial energy storage configuration strategy is updated using the second constraint condition of the target node to obtain the target energy storage configuration strategy.

[0112] In this embodiment, after obtaining the comparison result, if the comparison result is that the fitness ratio is less than or equal to the fitness function threshold, the initial energy storage configuration strategy can be updated using the first constraint condition to obtain the target energy storage configuration strategy, wherein the fitness ratio can be called the particle fitness ratio. For example, when the particle fitness ratio is less than or equal to the threshold, it means that the current particle performance is higher than the average level. Then, the first constraint condition can be used to update the initial energy storage configuration strategy, thereby enhancing the local search capability of the algorithm and obtaining the optimal energy storage configuration solution. The first constraint condition can be expressed by the following formula:

[0113]

[0114] In the above formula, w is used to represent the inertia weight; c1 and c2 are used to represent the individual learning factor and the group learning factor respectively; r1 and r2 are random numbers between 0 and 1; It is used to represent the n-th dimension component in the optimal position vector of the m-th particle at the iter iteration; Used to represent the n-th dimension component in the population optimal position vector at the iter-th iteration.

[0115] Optionally, if the comparison result is that the fitness ratio is greater than the fitness function threshold, the second constraint condition can be used to update the initial energy storage configuration strategy to obtain the target energy storage configuration strategy. For example, when the particle fitness ratio is greater than the threshold, it means that the current particle performance is lower than the average level, and then the second constraint condition is used for updating to increase the probability of the algorithm searching for the global optimal solution and achieve the optimal energy storage configuration solution. The second constraint condition can be expressed by the following formula:

[0116]

[0117] In the above formula, w is used to represent the inertia weight; c1 and c2 are used to represent the individual learning factor and the group learning factor respectively; r1 and r2 are random numbers between 0 and 1; It is used to represent the n-th dimension component in the optimal position vector of the m-th particle at the iter iteration; Used to represent the n-th dimension component in the population optimal position vector at the iter-th iteration.

[0118] Furthermore, in order to solve the problem of lack of guidance in selecting the global optimal solution of the population, the crossover and mutation operation in the genetic algorithm can be introduced into the particle swarm algorithm to perform crossover and mutation on the position vector of the particle to improve the diversity of the population. By continuously updating the particle position and speed until the iteration termination condition is met, the optimal particle output at this time is the optimal energy storage configuration solution for improving the carrying capacity of the distribution network when new energy power sources are connected to the grid.

[0119] In the application embodiment of the present invention, a comprehensive distribution network carrying capacity evaluation index system is established from multiple dimensions, such as safety, flexibility, stability, reliability, etc., and an energy storage configuration model is established. Secondly, a particle swarm algorithm is used to solve the energy storage configuration model to avoid the problems existing in the mathematical programming method when solving the model, and in order to avoid the premature convergence of the particle swarm algorithm, which causes the optimization process to fall into the local optimal solution and the problem of slow solution speed, the particle swarm algorithm can be improved so that the distribution network can effectively improve the new energy carrying capacity of the distribution network after executing the target energy storage configuration strategy.

[0120] In this embodiment, the load data of the distribution network, the target parameter data of the distribution network system of the distribution network, and the new energy power supply data of the distribution network can be obtained first, and then the flow data of the distribution network system can be determined according to the target parameter data obtained above, and finally the load data, the target parameter data and the new energy power supply data are input into the energy storage configuration model of the distribution network for analysis according to the obtained flow data, so as to achieve the purpose of obtaining the target energy storage configuration strategy for configuring the energy storage resources of the distribution network. Considering that after obtaining the load data of the distribution network, the target parameter data of the distribution network system and the new energy power supply data of the distribution network, the flow data of the distribution network system can be determined according to the target parameter data, and then the target energy storage configuration strategy of the distribution network can be obtained by using the energy storage configuration model of the distribution network, thereby solving the technical problem of not being able to effectively obtain the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network, so as to achieve the technical effect of effectively obtaining the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network.

[0121] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0122] At present, the research on the technology of improving the carrying capacity of distribution network for new energy power sources aims to analyze the characteristics of new energy power sources, and then take effective measures to reduce or even eliminate the adverse effects of new energy power sources on the distribution network when they are connected, thereby improving the carrying capacity of the distribution network and promoting the large-scale access of new energy power sources. However, at present, the carrying capacity of the distribution network is mostly evaluated from a single perspective, which makes it difficult to reflect the real carrying capacity of the distribution network for new energy power sources, resulting in the technical problem of being unable to effectively obtain the energy storage configuration strategy to improve the new energy carrying capacity of the distribution network.

[0123] Therefore, in order to solve the above problems, the present invention provides a method for obtaining an energy storage configuration strategy for a distribution network. The method can first obtain the load data of the distribution network, the target parameter data of the distribution network system of the distribution network, and the new energy power supply data of the distribution network, and then determine the flow data of the distribution network system according to the target parameter data obtained above, and finally input the load data, the target parameter data and the new energy power supply data into the energy storage configuration model of the distribution network according to the obtained flow data for analysis, so as to achieve the purpose of obtaining the target energy storage configuration strategy for configuring the energy storage resources of the distribution network. Considering that after obtaining the load data of the distribution network, the target parameter data of the distribution network system and the new energy power supply data of the distribution network, the flow data of the distribution network system can be determined according to the target parameter data, and then the target energy storage configuration strategy of the distribution network can be obtained by using the energy storage configuration model of the distribution network, thereby solving the technical problem of not being able to effectively obtain the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network, so as to achieve the technical effect of effectively obtaining the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network.

[0124] Figure 2 is a flow chart of a method for improving the carrying capacity of a distribution network based on energy storage site selection and capacity determination according to an embodiment of the present invention. Figure 2 As shown, the flow chart mainly includes the following steps:

[0125] Step S201, obtaining typical daily data of distribution network parameters, wind power, photovoltaic power, and load.

[0126] In this embodiment, the network parameters of the distribution network system to be calculated and the typical daily data of load, wind power and photovoltaic power are obtained, and the time-sharing load data of each node is obtained according to the network parameters and daily load data.

[0127] For example, if the data obtained includes power data, and all power data are calculated in MW, the input data needs to be unified. The time-sharing load data of each node in the distribution network is obtained according to the system's network parameters and the typical daily total load curve, and the reactive power provided by the grid-connected new energy power source is ignored. All reactive power is provided by the upper-level power grid and reactive compensation device.

[0128] Step S202, setting algorithm-related parameters (including population size, number of iterations, particle swarm dimension, etc.), processing the energy storage location and capacity of the distribution network, and generating an initial population.

[0129] In this embodiment, firstly, the appropriate population size and number of iterations are set according to specific requirements, and the dimension of the particles is set according to the configuration quantity requirement information of the energy storage system. The particle dimension setting is shown in the following formula:

[0130] m=24n+2

[0131] In the above formula, m is used to represent the particle dimension, including the charging and discharging power, energy storage capacity and energy storage installation node location of the energy storage in the distribution network at each moment; n is used to represent the configuration quantity of the energy storage system.

[0132] Furthermore, when initializing the population, in order to improve the initial uniformity of particles to improve their ergodicity and randomness, the search capability of the particle swarm algorithm can be improved while accelerating the convergence speed of the algorithm, so the chaotic mapping nonlinear (Logistic) function is used to generate the initial population, where the Logistic function can be expressed by the following formula:

[0133] Z k+1 =4Z k ×(1-Z k )

[0134] Among them, Z0 is a random number between 0 and 1. Since the energy storage is placed at the node of the distribution network, the one-dimensional particles about the energy storage location in the generated particles need to be rounded each time they are updated. The initialized population is used as the initial optimal population and the optimal particle is selected from it.

[0135] Step S203, calculate the power flow data of the distribution network system, calculate multiple objective function values ​​of each particle according to the carrying capacity assessment model, weight each objective function value in a subjective and objective way, and calculate the fitness function value of the particle.

[0136] In this embodiment, the network parameters of the distribution network can be modified in real time, and Matpower is called to solve the power flow data of the distribution network system. The carrying capacity is evaluated based on the obtained power flow data, and the fitness function value of the particle can be determined based on the evaluation result. For example, the carrying capacity of the distribution network is evaluated through six dimensions, and each dimension includes at least one evaluation indicator.

[0137] Optionally, the flexibility of the distribution network can be characterized by evaluating the proportion of renewable energy generation; the reliability of the distribution network can be characterized by the voltage deviation rate and network loss rate; the stability of the distribution network can be characterized by the net load deviation rate and flow imbalance; the safety of the distribution network can be characterized by the state vulnerability; and the quality of the distribution network can be characterized by the renewable energy consumption rate. The economic efficiency of the distribution network can be characterized by the total capacity of the energy storage system. For example, when considering the benefits of the energy storage system, its cost should also be considered, and the total capacity of the energy storage system can be selected as an economic indicator.

[0138] Alternatively, the proportion of renewable energy power generation can be expressed by the following formula:

[0139]

[0140] In the above formula, c NG It can be expressed as the proportion of renewable energy power generation; P DG,t It can be expressed as the new energy output at the tth moment; P load,t It can be expressed as the load power at the tth moment.

[0141] Optionally, the voltage deviation rate can be expressed by the following formula:

[0142]

[0143] In the above formula, c RU Used to indicate voltage deviation rate; U N Used to indicate rated voltage; U i,t Used to represent the node voltage at time t.

[0144] Optionally, the network loss rate can be expressed by the following formula:

[0145]

[0146] In the above formula, c LS Used to indicate network loss rate; I i,t It is used to represent the current of the i-th branch at the t-th time; R i Used to represent the resistance of the i-th branch.

[0147] Optionally, the net load deviation rate may be expressed by the following formula:

[0148]

[0149] In the above formula, c NL Used to indicate the net load deviation rate; P NL,t Used to represent the net load power at time t; P NL,f,t Used to represent the predicted net load power at time t.

[0150] Alternatively, the power flow imbalance can be expressed by the following formula:

[0151]

[0152] In the above formula, c PF Used to indicate the degree of power flow imbalance; P line,i,t It is used to represent the line transmission power of the i-th branch at the t-th time; P line,ave,t It is used to represent the average line transmission power at time t; P line,max Used to indicate the maximum line transmission power.

[0153] Alternatively, the state vulnerability can be expressed by the following formula:

[0154]

[0155] In the above formula, c GV It is used to represent the state vulnerability index; BV is used to represent the average vulnerability of the power grid; J is used to represent the average balance of the power grid; α and β are weight coefficients, and their sum is 1. Among them, the average vulnerability of the power grid BV can be expressed by the following formula:

[0156]

[0157] In the above formula, N is used to represent the number of nodes in the distribution network system; v t,i Used to represent the vulnerability value of node i at time t; v t,max and v t,min They represent the maximum vulnerability value and the minimum vulnerability value at the tth moment respectively. The average balance degree J of the power grid can be expressed by the following formula:

[0158]

[0159] In the above formula, p t,i It is used to indicate the ratio of the vulnerability of node i at time t to the total vulnerability of the distribution network at the current time.

[0160] Alternatively, the new energy consumption rate can be expressed by the following formula:

[0161]

[0162] In the above formula, c CN Used to indicate the new energy consumption rate, P DG,f,t Used to represent the predicted power generation of renewable energy at time t.

[0163] In this embodiment, after calculating the function value of each indicator, the function value of each indicator is weighted by combining subjective and objective weights. Among them, the subjective weight adopts the hierarchical analysis method to establish a hierarchical structure model, and based on actual experience analysis, the indicators in the system are compared two by two to form a judgment matrix, so that the weight of the indicator can be calculated by the square root method, and in order to ensure the rationality of the calculated weight, the result needs to be checked for consistency. If the check fails, the judgment matrix needs to be rebuilt.

[0164] Optionally, the objective weight is calculated using the entropy weight method. Before the calculation, the original data needs to be normalized, and different indicators are dimensionless and unified into standard indicators that can be directly calculated to ensure that the weights are consistent with the objective data. After calculating the subjective and objective weights of the indicators, in order to maximize the unity of the objective and subjective in the weighting of the indicators, thereby improving the accuracy of the weight calculation results, the least squares model of the indicator weight is established using the Lagrangian function, as shown in the following formula:

[0165]

[0166] In the above formula, N s and M can be the number of rows and columns of the indicator value matrix; w aj 、w ej , w are the AHP weight, entropy weight weight and comprehensive weight of indicator j respectively; I can be the normalized indicator value matrix.

[0167] Furthermore, according to the above formula, the comprehensive weight of the indicator can be obtained, and then according to the above comprehensive weight, the fitness function value of the target node is obtained by calculation, and the calculation formula is as follows:

[0168]

[0169] Optionally, after obtaining the fitness function value, based on the fitness function value and the target constraints of the energy storage system of the distribution network, the load data, the target parameter data and the new energy power source data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy, wherein the target constraints can optimize the fitness function value so that the optimized fitness function value can meet the operating constraints of the energy storage system.

[0170] For example, since the particle swarm algorithm will generate many particles that do not meet the actual operation constraints during the search process, it is necessary to add a penalty term to the fitness function value of the particles that violate the constraints so that the final optimization result meets the operation constraints of the energy storage system. The target constraint conditions of the energy storage system can be expressed by the following formula:

[0171]

[0172] In the above formula, and They represent the lower and upper limits of the charge and discharge power of the jth energy storage system respectively; E j (t) is the electric energy stored in the energy storage system j at time t; σ is the current rate of self-discharge; SOC j (t) can be used to indicate the charge state of the energy storage system at time t. In order to prevent overcharging and over-discharging of the energy storage system from affecting the life of the system, it is set between 0.2 and 0.9, and is kept at 0.5 at the beginning and end of an operation cycle; c and d are used to indicate the charge and discharge state of the energy storage system. When the energy storage system is charged, c=1, d=0; when the energy storage system is discharged, c=0, d=1.

[0173] Step S204, determining the particle historical optimum and the global optimum according to the particle dominance relationship.

[0174] In this embodiment, after the fitness function value of the particle is calculated, the particle dominance relationship is determined according to the fitness function value, and the historical optimal particle and the global optimal particle are updated.

[0175] Step S205: whether the historical optimal particle and the global optimal particle meet the termination condition.

[0176] In this embodiment, it is determined whether the historical optimal particle and the global optimal particle meet the termination condition. If so, step S206 is executed; if not, step S207 is executed.

[0177] Optionally, the iterative update of the particle swarm algorithm is based on the particle's own information and group information in the n-dimensional solution space to jointly determine the speed and direction of its movement, and continuously approach the optimal solution by changing its position. During the iterative solution, each particle updates its speed and position by tracking two "optimal solutions", and the basic iterative update formula is as follows:

[0178]

[0179] In the above formula, w is used to represent the inertia weight; c1 and c2 are used to represent the individual learning factor and the group learning factor respectively; r1 and r2 are random numbers between 0 and 1; It is used to represent the n-th dimension component in the optimal position vector of the m-th particle at the iter iteration; Used to represent the n-th dimension component in the population optimal position vector at the iter-th iteration.

[0180] Step S206, outputting the optimal energy storage configuration plan.

[0181] In this embodiment, if the historical optimal particle and the global optimal particle meet the termination condition, the historical optimal particle at this time can be output, which is the optimal energy storage configuration solution.

[0182] Step S207, iter=iter+1.

[0183] In this embodiment, if the historical optimal particle and the global optimal particle do not satisfy the termination condition, iter=iter+1 may be executed.

[0184] Step S208, updating particle speed and position.

[0185] Step S209, using the adversarial learning strategy to generate an adversarial population, combining it with the original population to form a mixed population, and selecting the top 50% of individuals to replace the original population.

[0186] In this embodiment, an adversarial learning strategy can be used to generate an adversarial population, which is combined with the original population to form a mixed population, and then the top 50% of individuals can be selected to replace the original population.

[0187] It should be noted that the particle swarm algorithm has the following problems when solving high-dimensional nonlinear problems: there is a lack of guidance on the value of inertia weight, the population diversity is lost quickly, and it is easy to fall into a local solution; and the random initial solution may be very far away from the global optimal solution, which is not conducive to the convergence accuracy and speed of the algorithm; the movement direction of the particles is determined by their individual optimality and group optimality, and there is premature convergence and poor performance on complex problems; there is a lack of guidance in the selection of the global optimal solution of the population. In order to solve the problem that the random initial solution may be far away from the global optimal solution, a new population is generated on the basis of the original population to increase the coverage of the solution space, and individuals with high fitness are selected to enter the next iteration.

[0188] Furthermore, the current population is mirrored about the center of the search space to generate a mirror population. The population between the center of the search space and the mirror population is usually closer to the global optimal solution than the mirror population. Therefore, a population is randomly generated between the center of the search space and the mirror point, which is a new population. The new population can be expressed by the following formula:

[0189]

[0190] In the above formula, The i-th dimension variable used to represent the new particle; lb i andub i They are used to represent the lower and upper limits of the value of the i-th dimension variable. In order to ensure that the mirror solution can be performed in a limited space without falling into the local optimum, the traditional fixed boundary is changed to a dynamic boundary, that is, lb i andub i Respectively by min(x i) and max(x i ) to replace it.

[0191] Optionally, in order to solve the problem of lack of guidance on the value of inertia weight, the inertia weight can be updated by nonlinear change of Logistic chaotic mapping, that is, it can be expressed by the following formula:

[0192]

[0193] In the above formula, Z iter Used to represent the Logistic chaotic map value; w min and w max are the minimum and maximum inertia weights, which are generally 0.4 and 0.9 respectively. max It can be expressed as the maximum number of iterations.

[0194] In this embodiment, the problem of updating particle speed and position can be solved by using an adaptive position and speed update strategy. Specifically, by calculating the ratio of the fitness value of the current particle to the average fitness value of all particles in the population, the strength of the relationship between the current particle and the average level of the population can be determined, so as to select different update methods.

[0195] Optionally, when the particle fitness ratio is less than or equal to the threshold, it means that the current particle performance is higher than the average level, and the first constraint condition can be used to update the initial energy storage configuration strategy, thereby enhancing the local search capability of the algorithm and obtaining the optimal energy storage configuration solution, wherein the first constraint condition can be expressed by the following formula:

[0196]

[0197] In the above formula, w is used to represent the inertia weight; c1 and c2 are used to represent the individual learning factor and the group learning factor respectively; r1 and r2 are random numbers between 0 and 1; It is used to represent the n-th dimension component in the optimal position vector of the m-th particle at the iter iteration; Used to represent the n-th dimension component in the population optimal position vector at the iter-th iteration.

[0198] Optionally, when the particle fitness ratio is greater than a threshold, it indicates that the current particle performance is lower than the average level, and then the second constraint condition is used for updating, so as to improve the probability of the algorithm searching for the global optimal solution and achieve the optimal energy storage configuration scheme, wherein the second constraint condition can be expressed by the following formula:

[0199]

[0200] In the above formula, w is used to represent the inertia weight; c1 and c2 are used to represent the individual learning factor and the group learning factor respectively; r1 and r2 are random numbers between 0 and 1; It is used to represent the n-th dimension component in the optimal position vector of the m-th particle at the iter iteration; Used to represent the n-th dimension component in the population optimal position vector at the iter-th iteration.

[0201] Step S210: whether the particle meets the crossover mutation condition.

[0202] In this embodiment, it is determined whether the particle meets the crossover mutation condition. If so, step S211 is executed, and then step S203 is executed; if not, step S203 is directly executed.

[0203] Step S211, crossover mutation is performed on the particle position vector to improve the diversity of the population.

[0204] In this embodiment, if the particle meets the crossover mutation condition, the particle position vector may be crossover mutated to improve the diversity of the population.

[0205] In this embodiment, in order to solve the problem of lack of guidance in selecting the global optimal solution of the population, the crossover mutation operation in the genetic algorithm can be introduced into the particle swarm algorithm, and the position vector of the particle can be crossover mutated to improve the diversity of the population. By continuously updating the particle position and speed until the iteration termination condition is met, the optimal particle output at this time is the optimal energy storage configuration solution for improving the carrying capacity of the distribution network when the new energy power source is connected to the grid.

[0206] Optionally, Figure 3 is a flow chart of a particle crossover mutation method according to an embodiment of the present invention. Figure 3 As shown, the particle crossover mutation method mainly includes the following steps:

[0207] Step S301, determining the difference threshold σ, crossover rate pc and mutation rate pm of the global optimal solution.

[0208] Step S302, calculate the difference X between particle i and the global optimal solution of the population, and use it as the basis for crossover mutation.

[0209] Step S303: whether the difference X is less than the difference threshold σ.

[0210] In this embodiment, it is determined whether the difference value X is less than the difference value threshold value σ. If yes, step S304 is executed; if no, the process ends directly.

[0211] Step S304, generate a random number r.

[0212] Step S305: whether the random number r is less than the mutation rate pm.

[0213] In this embodiment, it is determined whether the random number r is less than the mutation rate pm. If yes, step S306 is executed; if not, the process ends directly.

[0214] Step S306, performing a mutation operation.

[0215] In this embodiment, the mutation operation is performed according to the following formula:

[0216] x i =lb i +(ub i -lb i )*rand().

[0217] Step S307: Whether the random number r is less than the crossover rate pc.

[0218] In this embodiment, it is determined whether the random number r is less than the crossover rate pc. If yes, step S308 is executed; if no, the process ends directly.

[0219] Step S308, cross-processing the global optimal solution of the population with the mutated particles.

[0220] In an embodiment of the present invention, the results before and after the distribution network carrying capacity is improved can be compared and verified. Table 1 is a comparison table before and after the carrying capacity is improved. It can be seen from Table 1 that before and after the configuration of energy storage, all indicators except the state vulnerability have been improved to a certain extent. For example, the proportion of new energy power generation was 74.61% before the improvement and 80.02% after the improvement; the comprehensive carrying capacity index has an obvious improvement effect, indicating that the energy storage site selection and capacity determination does have an improvement effect on the distribution network carrying capacity. For example, the comprehensive carrying capacity was 2.5365 before the improvement and 1.9795 after the improvement.

[0221] Table 1 Comparison of load capacity before and after improvement

[0222]

[0223] Furthermore, in order to prove the superiority of the bearing capacity assessment model established in the present invention, a comparison is made with the existing bearing capacity assessment model, and the comparison results are shown in Table 2.

[0224] Table 2 Comparison of bearing capacity assessment models

[0225]

[0226] As can be seen from Table 2, although the carrying capacity improvement strategy obtained based on the existing evaluation model is better in terms of the proportion of new energy power generation and the new energy consumption rate, the improvement is very small, which reduces the power quality of the distribution network, increases the line loss of the distribution network, and aggravates the internal power flow imbalance, making the distribution network more fragile, and the comprehensive carrying capacity is not as good as the model of the present invention. In comparison, the distribution network carrying capacity improvement strategy obtained based on the evaluation model proposed by the present invention can better improve the acceptance capacity of new energy.

[0227] In this embodiment, the load data of the distribution network, the target parameter data of the distribution network system of the distribution network, and the new energy power supply data of the distribution network can be obtained first, and then the flow data of the distribution network system can be determined according to the target parameter data obtained above, and finally the load data, the target parameter data and the new energy power supply data are input into the energy storage configuration model of the distribution network for analysis according to the obtained flow data, so as to achieve the purpose of obtaining the target energy storage configuration strategy for configuring the energy storage resources of the distribution network. Considering that after obtaining the load data of the distribution network, the target parameter data of the distribution network system and the new energy power supply data of the distribution network, the flow data of the distribution network system can be determined according to the target parameter data, and then the target energy storage configuration strategy of the distribution network can be obtained by using the energy storage configuration model of the distribution network, thereby solving the technical problem of not being able to effectively obtain the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network, so as to achieve the technical effect of effectively obtaining the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network.

[0228] According to an embodiment of the present invention, a device for acquiring an energy storage configuration strategy of a distribution network is provided. It should be noted that the device for acquiring an energy storage configuration strategy of a distribution network can be used to execute a method for acquiring an energy storage configuration strategy of a distribution network in an embodiment of the present invention.

[0229] Figure 4 Schematic diagram of a device for acquiring energy storage configuration strategy of a distribution network according to an embodiment of the present invention. Figure 4 As shown, a device 400 for acquiring an energy storage configuration strategy of a distribution network may include: a first acquiring unit 401 , a determining unit 402 , and a second acquiring unit 403 .

[0230] The first acquisition unit 401 is used to acquire the load data of the distribution network, the target parameter data of the distribution network system of the distribution network, and the new energy power supply data of the distribution network, wherein the target parameter data is used to characterize the power transmission performance and / or power distribution performance of the distribution network system, and the target parameter data is obtained by updating the initial parameter data of the distribution network system.

[0231] The determination unit 402 is used to determine the power flow data of the distribution network system based on the target parameter data, wherein the power flow data is used to characterize the flow of power in the distribution network.

[0232] The second acquisition unit 403 is used to input the load data, target parameter data and new energy power data into the energy storage configuration model of the distribution network for analysis based on the flow data, so as to obtain the target energy storage configuration strategy of the distribution network, wherein the energy storage configuration model is constructed by using the historical load data of the distribution network, the historical target parameter data of the distribution network system and the historical new energy power data of the distribution network, and the target energy storage configuration strategy is used to configure the energy storage resources of the distribution network.

[0233] Optionally, the second acquisition unit 403 may include: an evaluation module, which is used to perform a carrying capacity evaluation on the flow data based on multiple evaluation indicators of the distribution network and using the carrying capacity evaluation model of the distribution network to obtain multiple evaluation indicator function values ​​of the target node in the distribution network, wherein the carrying capacity evaluation model is used to evaluate the carrying capacity of the distribution network; an acquisition module, which is used to perform a weighted operation on multiple evaluation indicator function values ​​using a weight allocation strategy of the target node to obtain a comprehensive indicator weight of the target node, wherein the weight allocation strategy is used to weight multiple evaluation indicator function values ​​according to the importance of different evaluation indicators; a determination module, which is used to determine the fitness function value of the target node based on the comprehensive indicator weight; an input module, which is used to input the load data, target parameter data and new energy power supply data into the energy storage configuration model of the distribution network for analysis based on the fitness function value, and obtain the target energy storage configuration strategy of the distribution network.

[0234] Optionally, multiple evaluation indicators include: the proportion of renewable energy power generation, voltage deviation rate, network loss rate, net load deviation rate, power flow imbalance, state fragility, new energy consumption rate and the total capacity of energy storage systems in the distribution network, wherein the proportion of renewable energy power generation is used to characterize the utilization degree of renewable energy in the distribution network, the voltage deviation rate is used to characterize the ratio of the difference between the actual voltage and the rated voltage of the distribution network to the rated voltage, the network loss rate is used to characterize the loss of electric energy in the transmission and distribution process of the distribution network, the net load deviation rate is used to characterize the difference between the net load power and the predicted net load power of the distribution network within the target time period, the power flow imbalance is used to characterize the uneven distribution degree of line transmission power on each branch or node in the distribution network, the state fragility is used to characterize the reliability of the distribution network when abnormal conditions occur, the new energy consumption rate is used to characterize the proportion of new energy used in the distribution network, and the total capacity of the energy storage system is used to characterize the electric energy storage capacity of the distribution network system.

[0235] Optionally, the input module may include: a determination submodule, used to determine the dominance information of the target node based on the fitness function value, wherein the dominance information is used to characterize the dominance relationship between the target node and other nodes in the distribution network except the target node; an input submodule, used to input load data, target parameter data and new energy power supply data into the energy storage configuration model for analysis to obtain an initial energy storage configuration strategy; an update submodule, used to update the initial energy storage configuration strategy using the energy storage configuration model based on the dominance information to obtain a target energy storage configuration strategy.

[0236] Optionally, the update submodule is used to obtain the initial inertia weight in the energy storage configuration model based on the control information; to map the initial inertia weight using the mapping function of the initial inertia weight to obtain the target inertia weight; to update the energy storage configuration model using the target inertia weight to obtain the target energy storage configuration model; to update the initial energy storage configuration strategy using the target energy storage configuration model to obtain the target energy storage configuration strategy.

[0237] Optionally, the update submodule is also used to obtain a target fitness function value of the distribution network; it is also used to determine the ratio between the fitness function value and the target fitness function value as the fitness ratio of the target node; it is also used to compare the fitness ratio with the fitness function threshold of the target node to obtain a comparison result of the target node; it is also used to update the initial energy storage configuration strategy based on the comparison result to obtain a target energy storage configuration strategy.

[0238] Optionally, the update submodule is also used to update the initial energy storage configuration strategy using the first constraint condition of the target node in response to the comparison result that the fitness ratio is less than or equal to the fitness function threshold, so as to obtain the target energy storage configuration strategy; and is also used to update the initial energy storage configuration strategy using the second constraint condition of the target node in response to the comparison result that the fitness ratio is greater than the fitness function threshold, so as to obtain the target energy storage configuration strategy.

[0239] In this embodiment, the load data of the distribution network, the target parameter data of the distribution network system of the distribution network, and the new energy power supply data of the distribution network are obtained by a first acquisition unit, wherein the target parameter data is used to characterize the power transmission performance and / or power distribution performance of the distribution network system, and the target parameter data is obtained by updating the initial parameter data of the distribution network system; the flow data of the distribution network system is determined by a determination unit based on the target parameter data, wherein the flow data is used to characterize the flow of power in the distribution network; the load data, the target parameter data and the new energy power supply data are input into the energy storage configuration model of the distribution network based on the flow data by a second acquisition unit for analysis, so as to obtain the target energy storage configuration strategy of the distribution network, wherein the energy storage configuration model is constructed by the historical load data of the distribution network, the historical target parameter data of the distribution network system and the historical new energy power supply data of the distribution network, and the target energy storage configuration strategy is used to configure the energy storage resources of the distribution network, thereby solving the technical problem of being unable to effectively obtain the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network, so as to achieve the technical effect of being able to effectively obtain the energy storage configuration strategy for improving the new energy carrying capacity of the distribution network.

[0240] According to an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method for obtaining the energy storage configuration strategy of the distribution network in the embodiment of the present invention.

[0241] According to an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement a method for acquiring an energy storage configuration strategy for a distribution network in an embodiment of the present invention.

[0242] According to an embodiment of the present invention, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the method for acquiring the energy storage configuration strategy of the distribution network in the embodiment of the present invention is implemented.

[0243] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0244] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0245] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units can be a logical function division, and there can be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0246] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0247] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0248] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0249] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for acquiring an energy storage configuration strategy for a distribution network, characterized in that: include: Obtaining load data of the distribution network, target parameter data of the distribution network system of the distribution network, and new energy power supply data of the distribution network, wherein the target parameter data is used to characterize the power transmission performance and / or power distribution performance of the distribution network system, and the target parameter data is obtained by updating the initial parameter data of the distribution network system; Based on the target parameter data, determining the power flow data of the distribution network system, wherein the power flow data is used to characterize the flow of electric power in the distribution network; Based on the flow data, the load data, the target parameter data and the new energy power supply data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network, wherein the energy storage configuration model is constructed through the historical load data of the distribution network, the historical target parameter data of the distribution network system and the historical new energy power supply data of the distribution network, and the target energy storage configuration strategy is used to configure the energy storage resources of the distribution network.

2. The method according to claim 1, characterized in that Based on the flow data, the load data, the target parameter data and the new energy power source data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network, including: Based on multiple evaluation indicators of the distribution network, a carrying capacity evaluation model of the distribution network is used to evaluate the carrying capacity of the power flow data, so as to obtain multiple evaluation indicator function values ​​of the target nodes in the distribution network, wherein the carrying capacity evaluation model is used to evaluate the carrying capacity of the distribution network; Using the weight allocation strategy of the target node, a weighted operation is performed on the multiple evaluation index function values ​​to obtain the comprehensive index weight of the target node, wherein the weight allocation strategy is used to allocate weights to the multiple evaluation index function values ​​according to the importance of different evaluation indicators; Determining the fitness function value of the target node based on the comprehensive indicator weight; Based on the fitness function value, the load data, the target parameter data and the new energy power supply data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network.

3. The method according to claim 2, characterized in that The multiple evaluation indicators include: the proportion of renewable energy power generation, voltage deviation rate, network loss rate, net load deviation rate, power flow imbalance, state fragility, new energy consumption rate and the total capacity of the energy storage system in the distribution network, wherein the proportion of renewable energy power generation is used to characterize the utilization degree of renewable energy in the distribution network, the voltage deviation rate is used to characterize the ratio of the difference between the actual voltage and the rated voltage of the distribution network to the rated voltage, the network loss rate is used to characterize the loss of electric energy in the transmission and distribution process of the distribution network, the net load deviation rate is used to characterize the difference between the net load power and the predicted net load power of the distribution network within the target time period, the power flow imbalance is used to characterize the uneven distribution degree of line transmission power on each branch or node in the distribution network, the state fragility is used to characterize the reliability of the distribution network when abnormal conditions occur, the new energy consumption rate is used to characterize the proportion of new energy used in the distribution network, and the total capacity of the energy storage system is used to characterize the electric energy storage capacity of the distribution network system.

4. The method according to claim 2, characterized in that: Based on the fitness function value, the load data, the target parameter data and the new energy power source data are input into the energy storage configuration model of the distribution network for analysis to obtain the target energy storage configuration strategy of the distribution network, including: Based on the fitness function value, determining dominance information of the target node, wherein the dominance information is used to characterize a dominance relationship between the target node and other nodes in the distribution network except the target node; Inputting the load data, the target parameter data and the new energy power source data into the energy storage configuration model for analysis to obtain an initial energy storage configuration strategy; Based on the control information, the initial energy storage configuration strategy is updated using the energy storage configuration model to obtain the target energy storage configuration strategy.

5. The method according to claim 4, characterized in that Based on the control information, the initial energy storage configuration strategy is updated using the energy storage configuration model to obtain the target energy storage configuration strategy, including: Based on the control information, obtaining an initial inertia weight in the energy storage configuration model; Mapping the initial inertia weight using the mapping function of the initial inertia weight to obtain a target inertia weight; The energy storage configuration model is updated using the target inertia weight to obtain a target energy storage configuration model; The initial energy storage configuration strategy is updated using the target energy storage configuration model to obtain the target energy storage configuration strategy.

6. The method according to claim 5, characterized in that The initial energy storage configuration strategy is updated using the target energy storage configuration model to obtain the target energy storage configuration strategy, including: Obtaining a target fitness function value of the distribution network; Determine the ratio between the fitness function value and the target fitness function value as the fitness ratio of the target node; Comparing the fitness ratio with the fitness function threshold of the target node to obtain a comparison result of the target node; Based on the comparison result, the initial energy storage configuration strategy is updated to obtain the target energy storage configuration strategy.

7. The method according to claim 6, characterized in that Based on the comparison result, the initial energy storage configuration strategy is updated to obtain the target energy storage configuration strategy, including: In response to the comparison result being that the fitness ratio is less than or equal to the fitness function threshold, the initial energy storage configuration strategy is updated using the first constraint condition of the target node to obtain the target energy storage configuration strategy; In response to the comparison result being that the fitness ratio is greater than the fitness function threshold, the initial energy storage configuration strategy is updated using the second constraint condition of the target node to obtain the target energy storage configuration strategy.

8. A device for acquiring energy storage configuration strategy of a distribution network, characterized in that: include: A first acquisition unit is used to acquire load data of the distribution network, target parameter data of the distribution network system of the distribution network, and new energy power supply data of the distribution network, wherein the target parameter data is used to characterize the power transmission performance and / or power distribution performance of the distribution network system, and the target parameter data is obtained by updating the initial parameter data of the distribution network system; A determination unit, configured to determine flow data of the distribution network system based on the target parameter data, wherein the flow data is used to characterize the flow of electric power in the distribution network; A second acquisition unit is used to input the load data, the target parameter data and the new energy power supply data into the energy storage configuration model of the distribution network for analysis based on the flow data, so as to obtain a target energy storage configuration strategy of the distribution network, wherein the energy storage configuration model is constructed through historical load data of the distribution network, historical target parameter data of the distribution network system and historical new energy power supply data of the distribution network, and the target energy storage configuration strategy is used to configure energy storage resources of the distribution network.

Images