Energy storage configuration method, equipment, device, medium and program of power distribution area

Abstract

The embodiment of the invention provides an energy storage configuration method, equipment and device for a power distribution area, a medium and a program. The invention relates to the field of energy storage configuration of a power distribution area. The method comprises the following steps: determining at least one typical scene according to source load historical data of a light storage system in the power distribution area; determining power flow distribution parameters of the power distribution area based on the typical scene and the topological data and the operation data of the power distribution area; and determining energy storage configuration parameters of the power distribution area based on the power flow distribution parameters and the configuration cost parameters, and configuring operation of energy storage equipment and an optical storage system in the power distribution area based on the energy storage configuration parameters. The method is used for achieving the technical effect of improving the energy storage configuration accuracy of the power distribution area.

Description

Technical Field

[0001] This application relates to the field of energy storage configuration in distribution substations, and more particularly to a method, equipment, device, medium, and procedure for energy storage configuration in distribution substations. Background Technology

[0002] The gradual integration of flexible loads such as distributed photovoltaic power and electric vehicles into the distribution network has led to an increase in the load factor of distribution transformers. Due to the randomness of users' electricity consumption habits and the fluctuation of renewable energy output, distribution substations are experiencing significant seasonal overload problems, especially during the high temperatures of summer and the low temperatures of winter.

[0003] Existing solutions to heavy overload in distribution transformer areas often involve installing photovoltaic energy storage systems on the low-voltage user side of the transformer, optimizing the configuration with the goal of maximizing economic benefits. This method typically uses the life-cycle cost and revenue of the energy storage equipment as the core indicator; or it involves monitoring the real-time load rate of the distribution area and adjusting the equipment's operating status in conjunction with controllable resources to suppress short-term overloads.

[0004] During localized peak shaving, uneven power redistribution within the feeder may occur due to energy storage charging and discharging strategies, potentially leading to overload risks on other lines. Furthermore, current energy storage allocation models are mostly based on typical daily or annual average load data, which is insufficient for short-term peak loads during extreme seasons (such as high temperatures in summer or low temperatures in winter), causing configuration schemes to fail in actual operation. Therefore, existing technologies suffer from poor energy storage configuration effectiveness across distribution substations. Summary of the Invention

[0005] This application provides a method, equipment, device, medium, and program for configuring energy storage in distribution substations, in order to improve the accuracy of energy storage configuration in distribution substations.

[0006] In a first aspect, embodiments of this application provide an energy storage configuration method for a distribution radio station, including:

[0007] At least one typical scenario is determined based on the source-load historical data of the photovoltaic-storage system in the distribution radio station area. The typical scenario is used to characterize the operating period of the distribution radio station area when the load rate meets the overload condition.

[0008] Based on typical scenarios, topology data and operational data of distribution substations, the power flow distribution parameters of distribution substations are determined; among them, the power flow distribution parameters are used to characterize the uniformity of load distribution of each operating line in the photovoltaic-storage system.

[0009] Based on power flow distribution parameters and configuration cost parameters, the energy storage configuration parameters of the distribution transformer area are determined, and the operation of energy storage devices and photovoltaic-storage systems in the distribution transformer area is configured based on the energy storage configuration parameters.

[0010] In one possible implementation, at least one typical scenario is determined based on the source-load historical data of the photovoltaic-storage system in the distribution area, including:

[0011] The historical source-load data is vectorized according to the time dimension to obtain power samples at each historical moment;

[0012] The power samples are clustered according to the operating segments of the distribution station area to obtain the clustering results for each operating segment;

[0013] Based on the clustering results, the runtime segments whose load rates meet the overload regulation requirements are selected, and the runtime segments are determined as typical scenarios.

[0014] In one possible implementation, the historical source-load data is vectorized according to the time dimension to obtain power samples at each historical moment, including:

[0015] Determine the first feature vector of the source load historical data based on the time dimension;

[0016] Acquire at least one data point from weather data, electricity price information, and user behavior patterns of the distribution area at various historical moments, and determine the data point as an auxiliary input feature vector;

[0017] The first feature vector and the auxiliary input feature vector are fused to obtain power samples for each historical moment.

[0018] In one possible implementation, based on typical scenarios, distribution area topology data, and operational data, the power flow distribution parameters of the distribution area are determined, including:

[0019] Based on the topology and operation data of each operating line in the distribution substation, the load fluctuation parameters of each operating line under typical scenarios are determined.

[0020] Based on the line weight and load fluctuation parameters of each operating line, the load fluctuation parameters are weighted and fused to obtain the distribution parameter components of the distribution substation in a typical scenario.

[0021] Determine the probability of typical scenarios occurring in the distribution area, and determine the power flow distribution parameters based on the distribution parameter components and scenario probabilities.

[0022] In one possible implementation, the energy storage configuration parameters of the distribution substation are determined based on power flow distribution parameters and configuration cost parameters, including:

[0023] Multiple candidate configuration parameters are generated based on runtime constraints;

[0024] Based on the objective function, calculate the first fitness corresponding to each candidate configuration parameter. The objective function consists of power flow distribution parameters and configuration cost parameters.

[0025] The candidate configuration parameters are updated based on each first fitness to obtain intermediate configuration parameters, and the second fitness corresponding to each intermediate configuration parameter is calculated.

[0026] The above update and calculation steps are executed iteratively until the fitness change obtained from two adjacent rounds of calculation is less than a preset threshold.

[0027] The final iterative result that meets the conditions is determined as the energy storage configuration parameters of the distribution substation.

[0028] In one possible implementation, the operational constraints include:

[0029] Based on the load data, operating data, and safe operating conditions of the energy storage equipment in the distribution substation, the first constraint condition of the energy storage equipment is determined.

[0030] Based on the load data and safe operating conditions of the photovoltaic and energy storage systems in the distribution area, the second constraint condition of the photovoltaic and energy storage systems is determined.

[0031] Based on the load data, operating data, and safe operating conditions of each operating line and its nodes in the distribution area, the third constraint conditions for each operating line and its nodes are determined.

[0032] Secondly, embodiments of this application provide an energy storage configuration device for a distribution radio station, comprising:

[0033] The first processing module is used to determine at least one typical scenario based on the source-load historical data of the optical storage system in the distribution radio station area. The typical scenario is used to characterize the operating period of the distribution radio station area when the load rate meets the overload condition.

[0034] The second processing module is used to determine the power flow distribution parameters of the distribution area based on typical scenarios, topology data and operation data of the distribution area; wherein, the power flow distribution parameters are used to characterize the uniformity of load distribution of each operating line in the photovoltaic storage system.

[0035] The third processing module is used to determine the energy storage configuration parameters of the distribution substation based on power flow distribution parameters and configuration cost parameters, and to configure the operation of energy storage devices and photovoltaic-storage systems in the distribution substation based on the energy storage configuration parameters.

[0036] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0037] The memory stores computer-executed instructions;

[0038] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0039] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0040] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0041] The energy storage configuration method, equipment, device, medium, and program for distribution transformer substations provided in this application, by selecting and determining at least one typical scenario based on the historical source-load data collected by the photovoltaic-storage system within the distribution transformer substation, accurately reflects the actual operating period of the substation when the load rate reaches or exceeds the overload threshold, thus providing a representative operating condition basis for subsequent analysis. Next, combining the determined typical scenario with the existing topology data and real-time operating data of the distribution transformer substation, the power flow distribution parameters of the substation are further calculated and obtained. These parameters effectively characterize whether the load distribution on each operating line in the photovoltaic-storage system is balanced, reflecting the load distribution between lines. The uniformity of power distribution provides a key indicator for assessing the system's operating status and potential risks. Finally, by comprehensively considering the obtained power flow distribution parameters and the configuration cost parameters related to energy storage equipment, and through reasonable optimization analysis and calculation, the optimal energy storage configuration parameters suitable for the distribution area are finally determined. Based on these configuration parameters, the operation strategy of the energy storage equipment in the area and the entire photovoltaic-energy storage system is scientifically configured. This not only effectively addresses overload periods but also improves the economy and reliability of system operation by optimizing line load distribution. The technical effect of obtaining the optimal energy storage configuration scheme with reasonable cost investment under the premise of ensuring the safe and stable operation of the distribution area is derived. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] Figure 1 A flowchart illustrating the energy storage configuration method for the distribution substation provided in this application. Figure 1 ;

[0044] Figure 2 A flowchart illustrating the energy storage configuration method for the distribution substation provided in this application. Figure 2 ;

[0045] Figure 3 An improved topology diagram of the IEEE 33-node distribution network in the energy storage configuration method for a distribution substation;

[0046] Figure 4 A fitness curve of an energy storage configuration method for a distribution substation;

[0047] Figure 5 A diagram showing the uniformity index of power flow distribution in the energy storage configuration method for a distribution substation.

[0048] Figure 6 A parameter diagram showing the configuration results of energy storage devices in an energy storage configuration method for a distribution substation.

[0049] Figure 7 A schematic diagram of the energy storage configuration device for the power distribution area provided in this application;

[0050] Figure 8 A hardware schematic diagram of the energy storage configuration device for the distribution radio station provided in this application.

[0051] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0052] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of methods and approaches consistent with some aspects of this application as detailed in the appended claims.

[0053] Among related technologies, battery energy storage has become a new approach to address voltage exceedances and heavy overloads in distribution networks due to its advantages such as fast response speed, flexible power configuration, and deployment. One approach involves installing photovoltaic-energy storage systems on the low-voltage user side of transformer substations, aiming to maximize economic benefits over the entire lifecycle to alleviate heavy overload problems in distribution areas. However, this method, focusing on maximizing the benefits of energy storage configuration, ignores the impact of energy storage on power flow distribution, potentially leading to reverse peak shaving issues. Another approach involves adjusting equipment operating status in real time using adjustable resources based on the current substation load rate to prevent equipment failure due to heavy overload. However, this method does not consider the possibility of insufficient energy storage capacity during seasonal heavy overloads, which could cause control strategies to fail.

[0054] To address the aforementioned technical issues, this application provides a method, equipment, apparatus, medium, and program for configuring energy storage in distribution substations. Starting with historical source-load data from the photovoltaic-storage system within the distribution substation, it analyzes and selects at least one typical scenario. These typical scenarios precisely correspond to critical operating periods in actual operation where the substation's load rate exceeds set overload conditions, providing a practically representative and targeted basis for subsequent energy storage configuration. Furthermore, this method integrates the aforementioned typical scenario information with the distribution substation's topology data and real-time operating data. Through systematic power flow calculation, it extracts power flow distribution parameters reflecting the uniformity of load distribution among the operating lines in the photovoltaic-storage system. These parameters can intuitively reveal the load distribution between lines. Balanced operation lays the technical foundation for identifying potential overload risks and optimizing power flow paths. Finally, based on the obtained power flow distribution parameters and configuration cost parameters related to the selection and deployment of energy storage equipment, the optimal energy storage configuration parameters are determined by comprehensively balancing technical requirements and economic objectives. Based on this, the energy storage equipment layout in the distribution substation and its collaborative operation strategy with the photovoltaic-storage system are rationally configured, thereby effectively suppressing the overload problem in the substation. At the same time, by optimizing the load distribution between lines, the overall system operating efficiency and power supply reliability are improved. A scientific energy storage configuration scheme that meets both safe operation requirements and economic costs is derived, providing key technical support for the intelligent and economical operation of the distribution substation.

[0055] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0056] Figure 1 A flowchart illustrating the energy storage configuration method for the distribution substation provided in this application. Figure 1 ,like Figure 1 As shown, the method includes:

[0057] S101. Determine at least one typical scenario based on the source-load historical data of the photovoltaic-storage system in the distribution area.

[0058] In this embodiment, the distribution substation is the area in the power system that directly distributes and supplies electricity to power users. The distribution substation may contain a photovoltaic-storage system and energy storage devices. The photovoltaic-storage system contains distributed photovoltaics, which can be installed in the distribution substation to convert solar energy into electrical energy and supply electricity to users in the distribution substation nearby. Optionally, the electrical energy generated by the distributed photovoltaics can charge the energy storage devices to achieve energy storage.

[0059] Historical source-load data refers to the power generation data of the photovoltaic (PV) and energy storage (ESS) systems in a distribution substation at various times over a past period (e.g., one day, one week, one month). It reflects the power generation capacity of the PV and ESS systems under different times and environmental conditions (e.g., irradiance, temperature). Historical source-load data may include, but is not limited to, historical load data and historical PV output data of distributed photovoltaic systems within the PV and ESS system. A typical scenario refers to a set of operating periods determined based on the historical source-load data of the PV and ESS system, representing specific characteristics of the distribution substation under a particular operating state (e.g., when the load rate meets overload conditions). For example, during the high-temperature period in summer, due to increased use of high-power appliances such as air conditioners, the load rate of the distribution substation is high, which may lead to overload. In this case, the matching relationship between the power generation of the PV and ESS system and the load can be analyzed as a typical scenario. Typical scenarios characterize the operating periods of the distribution substation when the load rate meets overload conditions; for example, a typical scenario could be a typical day during the operation of the PV and ESS system, or a typical time period within a day during the operation of the PV and ESS system.

[0060] Optionally, when the server acquires historical source load data, it can acquire it in chronological order. For example, it can acquire historical source load data for each day of the year on a daily basis, in which case the historical source load data for each day can be determined using the average value of that day. Alternatively, it can divide each day into two data acquisition units, daytime and nighttime, on an hourly basis, acquiring two historical source load data sets per day. The historical source load data for the daytime can be determined using the average value within the corresponding hourly period, and the historical source load data for the nighttime can also be determined using the average value within the corresponding hourly period. Furthermore, it can acquire data in smaller time intervals, such as every hour, two hours, four hours, etc., to obtain a series of historical source load data arranged by time.

[0061] S102. Based on typical scenarios, the topology data and operational data of the distribution substation, determine the power flow distribution parameters of the distribution substation.

[0062] In this embodiment, topology data refers to data describing the connection relationships and layout structure between various electrical devices (such as transformers, lines, switches, distributed photovoltaic devices, energy storage devices, etc.) in a distribution substation, used to reflect the transmission path of electricity within the distribution substation. In practice, topology data can be obtained through design drawings of the distribution substation, geographic information system data, or on-site surveys. For example, a simple distribution substation topology may include a transformer with multiple operating lines branching off from it, each line connecting different user loads and photovoltaic / energy storage system devices. The topology data will record in detail the connection methods and location relationships between these devices.

[0063] Operational data refers to various data generated by the distribution substation during real-time operation. Operational data may include, but is not limited to, electrical parameters such as voltage and current, and the operating status of equipment (such as the open / closed status of switches, equipment fault alarm information, etc.). In practice, operational data can be collected in real time by sensors and monitoring devices installed on various devices within the distribution substation.

[0064] Power flow distribution parameters characterize the uniformity of load distribution across operating lines in a photovoltaic-storage system. They reflect the flow of electricity and load allocation within these lines. Operating lines refer to the power transmission lines connecting various devices in the photovoltaic-storage system within the distribution substation topology; typically, they refer to the power transmission lines between two adjacent devices. By determining the power flow distribution parameters of the distribution substation, the operating efficiency and stability of the photovoltaic-storage system can be determined. For example, if some lines are overloaded while others are lightly loaded, it indicates uneven load distribution, which may affect the safe operation and power quality of the system.

[0065] For example, sensors or monitoring devices for data acquisition can be installed on various devices within the distribution transformer area. The server can acquire the data collected by the sensors or monitoring devices to obtain the operating data of the distribution transformer area, as well as the topology data of the distribution transformer area through its design drawings. Then, the server can determine the operating lines between various devices in the photovoltaic energy storage system based on the topology data, and determine the load distribution uniformity of each operating line in the photovoltaic energy storage system based on the operating data of the distribution transformer area, thereby obtaining the power flow distribution parameters of the distribution transformer area.

[0066] S103. Based on power flow distribution parameters and configuration cost parameters, determine the energy storage configuration parameters of the distribution transformer area, and configure the operation of energy storage devices and photovoltaic-storage systems in the distribution transformer area based on the energy storage configuration parameters.

[0067] In this embodiment, the energy storage configuration parameters refer to the parameters determined based on the power flow distribution parameters and configuration cost parameters, which are used to configure the operation of energy storage devices and photovoltaic-storage systems in the distribution area. The energy storage configuration parameters may include, but are not limited to, the capacity, quantity, and installation location of the energy storage devices, as well as the operating parameters of the photovoltaic-storage system (such as current, voltage, charging and discharging time period, etc.).

[0068] For example, the server can determine the energy storage configuration parameters of a distribution transformer area based on power flow distribution parameters and configuration cost parameters. The server can use optimization algorithms (such as genetic algorithms, particle swarm optimization, or sparrow algorithms) to comprehensively analyze and optimize the power flow distribution parameters and configuration cost parameters to obtain the optimal energy storage configuration parameters. Then, the server can configure the operation of energy storage devices and the photovoltaic-storage system in the distribution transformer area based on the energy storage configuration parameters. For instance, the server can control the corresponding number of energy storage converters and energy storage devices to connect to the corresponding locations within the distribution transformer area based on the number and corresponding installation locations of the energy storage devices in the energy storage configuration parameters, and control the photovoltaic-storage system to operate according to the corresponding operating parameters in the energy storage configuration parameters.

[0069] The energy storage configuration method for distribution transformer substations provided in this application first focuses on the source-load historical data of the photovoltaic-storage system in the substation. Through in-depth mining and statistical analysis of this data, at least one typical scenario is identified and extracted. These typical scenarios accurately depict the critical operating periods when the load rate of the substation reaches or exceeds the overload condition during actual operation, providing a clear and representative operating condition background for the subsequent formulation of energy storage configuration schemes. On this basis, the identified typical scenarios are further combined with the existing topology data and operating status data of the distribution transformer substation. Through the system's power flow analysis method, a power flow distribution parameter that can comprehensively reflect the uniformity of load distribution on each operating line in the photovoltaic-storage system is calculated. This parameter directly reflects the differences in load bearing between different lines, providing a basis for judging potential bottlenecks in system operation. This provides a quantitative basis for assessing overload risk. Ultimately, considering the aforementioned power flow distribution parameters and the configuration cost parameters involved in the actual deployment of the energy storage system, through multi-objective optimization or trade-off analysis, energy storage configuration parameters that can effectively alleviate overload problems and have good economic efficiency are determined. Based on this, the capacity, layout, and coordinated operation strategy of energy storage equipment in the distribution substation are scientifically configured, thereby improving the load regulation capability of the distribution substation during peak or abnormal operating periods. By optimizing the load distribution between lines, the risk of local overload is reduced, while the investment cost of the energy storage system is reasonably controlled. An optimized energy storage configuration scheme that takes into account safety, economy, and operational efficiency is derived, providing an important technical path and implementation plan for improving the overall power supply quality and intelligent management level of the distribution substation.

[0070] Figure 2 A flowchart illustrating the energy storage configuration method for the distribution substation provided in this application. Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1Based on the embodiments, the energy storage configuration method for distribution substations is described in detail, wherein typical scenarios are determined through steps S201 to S202; power flow distribution parameters are determined through step S203; and energy storage configuration parameters are determined through step S204; the method includes:

[0071] S201. Determine the first feature vector of the source-load historical data based on the time dimension; obtain at least one data information from the weather data, electricity price information and user behavior patterns of the distribution substation at each historical moment, and determine the data information as the auxiliary input feature vector; fuse the first feature vector and the auxiliary input feature vector to obtain the power sample at each historical moment.

[0072] In this embodiment, when processing historical source-load data, the time dimension can clearly define the specific time corresponding to each power data point. Taking a 24-hour day as an example, the time dimension can be accurate to the minute or even the second. Vectorization refers to the process of converting discrete power data into vector form. When processing historical source-load data, since historical source-load data includes historical load data and historical photovoltaic output data, vectorization can represent the load data and photovoltaic output data at each historical moment as a vector for subsequent mathematical operations and analysis. A power sample refers to a data unit obtained after vectorization, used to represent the power generation at a specific historical moment. In the case of a one-dimensional vector, the power sample is a single numerical value; in the case of a multi-dimensional vector, the power sample is an array containing multiple numerical values. For example, for the power generation data at a certain moment in a day, the power sample obtained after vectorization can include the historical load data and historical photovoltaic output data for the corresponding moment.

[0073] The data information used to generate the auxiliary input feature vector includes, but is not limited to, weather data (such as key meteorological factors affecting photovoltaic output and air conditioning load, such as light intensity, temperature, and humidity); electricity price information, such as time-of-use pricing and peak-valley pricing, which are economic leverage data guiding user electricity consumption behavior; and user behavior patterns, such as weekday / holiday electricity consumption habits and typical daily load curves, which reflect user electricity consumption patterns. After these auxiliary data are processed into auxiliary input feature vectors, they are fused with the first feature vector to generate power at various historical moments that incorporate the combined effects of source-load characteristics, external environment, market mechanisms, and user behavior. This technical approach, through multi-dimensional data linkage, not only accurately captures the inherent fluctuation patterns of source and load over time, but also deeply explores the nonlinear impact of weather changes on renewable energy output and load demand, the dynamic guiding role of electricity price signals on user electricity consumption behavior, and the shaping effect of users' inherent electricity consumption habits on the system load curve. This significantly improves the completeness and representativeness of the power sample information, providing more comprehensive and high-quality training data that is closer to actual operating scenarios for subsequent data-driven load forecasting, energy storage optimization configuration, or grid operation analysis. It effectively enhances the model's adaptability to complex operating conditions and its prediction accuracy.

[0074] S202. Cluster the power samples according to the operating segments of the distribution station area to obtain the clustering results of each operating segment; based on the clustering results, select the operating segments whose load rate meets the overload regulation and determine the typical scenarios of the operating segments.

[0075] In this embodiment, clustering refers to the process of grouping various power samples. Specifically, clustering methods can include, but are not limited to, K-means clustering and hierarchical clustering. The clustering result refers to the grouping of power samples obtained after processing by the clustering algorithm. Each clustering result can contain a group of power samples that are similar in operating time (scenario). By vectorizing historical source-load data along the time dimension and combining it with auxiliary input feature vectors, power samples for each historical moment are generated (each sample is an array composed of a load vector and a photovoltaic vector). The samples are then clustered according to the operating time of the distribution substation to obtain the clustering results corresponding to each time period (each cluster represents an operating scenario). Based on the load rate and overload conditions of the clustering results, at least one typical scenario is selected.

[0076] Optionally, after determining the typical scenarios, the server can determine the scenario probability of each typical scenario based on the number of power samples in the target sample cluster associated with each typical scenario and the number of all runtime segments. For example, the scenario probability can be determined based on the ratio of the number of power samples in the target sample cluster associated with the typical scenario to the number of all runtime segments.

[0077] S203. Based on the topology data and operation data of each operating line in the distribution substation, determine the load fluctuation parameters of each operating line under typical scenarios; according to the line weight and load fluctuation parameters of each operating line, perform weighted fusion of the load fluctuation parameters to obtain the distribution parameter components of the distribution substation under typical scenarios; determine the scenario probability of the typical scenario occurring in the distribution substation, and determine the power flow distribution parameters according to the distribution parameter components and scenario probability.

[0078] In this embodiment, the load fluctuation parameter is used to characterize the degree of load fluctuation of each operating line in the distribution substation over time under specific typical scenarios. The load fluctuation parameter can reflect the stability and variation of the load in the operating line. If the load fluctuation parameter of a certain operating line is large, it indicates that the load of the operating line changes drastically, which may have a significant impact on the stable operation of the distribution substation; conversely, a small load fluctuation parameter indicates that the line load is relatively stable.

[0079] Based on topology and operational data, the server can perform statistical analysis on the operational data of each operating line using statistical methods such as standard deviation, variance, and coefficient of variation. This analysis yields the load fluctuation parameters for each operating line under specific typical scenarios. Repeating this process, the server can obtain the load fluctuation parameters for each operating line in the distribution substation under various typical scenarios. Optionally, for a specific operating line, the server can determine the current value of that line at a certain moment under a corresponding typical scenario and the maximum current that the line can withstand from the operational data. Based on this current value and the maximum current, the server can then determine the load fluctuation parameters, obtained using the following formula:

[0080]

[0081] in, For the l-th operating line in a typical scenario The load fluctuation parameters are as follows, where T represents a typical scenario. The total number of time periods (moments) below. Typical scenario The current value of the l-th operating line at time t. This represents the maximum carrying current of the l-th operating line. To take the average value.

[0082] Optionally, line weights are numerical values ​​reflecting the relative importance of each operating line in a distribution substation. Taking into account line importance (such as whether it connects to critical users / equipment), load capacity, and impact on system stability, methods for setting line weights include, but are not limited to, giving higher weights to critical lines (those with significant fault or anomaly impact) and lower weights to secondary lines (those with low load and weak impact). Weighted fusion is a process of calculating the load fluctuation parameters of each line using line weights to obtain the distribution parameter components of the distribution substation in a typical scenario. This comprehensively reflects the overall load fluctuation situation. Higher-weighted critical lines have a greater impact on the components, making the results more accurately reflect the actual load distribution. In actual calculations, line weights can be determined using expert scoring or the analytic hierarchy process (AHP), and then the weights of each line are multiplied by their load fluctuation parameters and summed to obtain the distribution parameter components for that typical scenario.

[0083] For each typical scenario, the power flow distribution parameters of the distribution area are determined based on the distributed parameter components and standard distributed parameters under the corresponding typical scenario, and can be obtained by the following formula:

[0084]

[0085] in, Power flow distribution parameters for the distribution area; This is a typical scenario for a distribution radio station area without energy storage devices. Standard distribution parameters under standard distribution parameters This can be calculated based on the overall value of 1 in the above formula. Let L be the line weight of the l-th operating line, and L be the total number of operating lines in the distribution area. Typical scenario The distributed parameter components are shown below, where T represents a typical scenario. The total number of time periods (moments) below. Typical scenario The current value of the l-th operating line at time t. This represents the maximum carrying current of the l-th operating line. To take the average value.

[0086] Probability statistics are performed on each operating segment of the distribution transformer area to determine the probability of at least one typical scenario. Based on the probability of at least one typical scenario, the distribution parameter components corresponding to at least one typical scenario are fused to obtain the power flow distribution parameters of the distribution transformer area.

[0087] The term "operational period" refers to the time interval during which a distribution transformer substation operates. Different operational periods correspond to different operating scenarios for the substation, such as scenarios where the load meets overload requirements or scenarios where the load does not meet overload requirements. In practice, operational periods can be divided according to different time scales, such as hours, days, months, and seasons. Taking a day as an example, it can be divided into daytime periods and nighttime periods. Within different operational periods, the load conditions of the distribution transformer substation and the power generation of the photovoltaic and energy storage system will differ.

[0088] Probabilistic statistics refers to the process of statistically analyzing the frequency of different load conditions in each runtime segment to determine the probability of occurrence in that runtime segment. For example, counting the number of times each runtime segment experienced a load rate exceeding 80% (i.e., overload condition) over the past year, and then dividing by the total number of runtime segments, yields the probability of an overload condition occurring in that runtime segment. The probability of a typical scenario refers to the probability of a typical scenario occurring across all runtime segments. For instance, if probabilistic statistics reveal that a certain typical scenario occurred in 20% of the total number of runtime segments over a past statistical period, then the probability of that typical scenario is 0.2, reflecting the frequency of different typical scenarios.

[0089] Fusion of the distributed parameter components corresponding to at least one typical scenario refers to the process of fusing the distributed parameter components corresponding to multiple typical scenarios to obtain the power flow distribution parameters. Fusion methods may include, but are not limited to, weighted summation, weighted averaging, and simple summation.

[0090] For example, the server can perform probability statistics on each runtime segment of the distribution area to determine the probability of at least one typical scenario. The server can determine the statistical period, which may be the period used to determine the typical scenario, and determine the number of runtime segments within that period. Then, the server counts the number of times a typical scenario occurs in each runtime segment and calculates the proportion of the typical scenario's occurrences to the total number of runtime segments, thus obtaining the scenario probability of that typical scenario. Based on the scenario probabilities corresponding to at least one typical scenario, the server can fuse the distribution parameter components corresponding to each typical scenario to obtain the power flow distribution parameters of the distribution area. For example, the server can multiply the distribution parameter components of each typical scenario by their corresponding scenario probabilities and then sum them to obtain the power flow distribution parameters of the distribution area. For instance, assuming there are two typical scenarios with scenario probabilities p1 and p2, and corresponding distribution parameter components x1 and x2, the fused power flow distribution parameter X = p1 × x1 + p2 × x2.

[0091] In an optional embodiment, when determining the scenario probability of each typical scenario, in some cases, the typical scenario is only the typical case among all runtime segments, such that the sum of the scenario probabilities of each typical scenario is not 1. In this case, the scenario probabilities of each typical scenario can be linearly scaled so that the sum of the scenario probabilities of each typical scenario is 1. For example, assuming there are two typical scenarios with scenario probabilities p1 and p2 respectively, then the linearly scaled p1 is p1×(1 / (p1+p2)) and the linearly scaled p2 is p2×(1 / (p1+p2)), to meet the probability normalization requirement and make the subsequent calculation of power flow distribution parameter fusion based on the cangjing probability more reasonable.

[0092] In this embodiment, by performing probability statistics on each operating segment of the distribution substation and fusing the distribution parameter components under different typical scenarios based on the obtained scenario probabilities, the influence of each typical scenario on the power flow distribution can be comprehensively considered, avoiding the limitations of single scenario analysis. This makes the obtained power flow distribution parameters more consistent with the actual operating conditions and helps to configure the operation of the distribution substation more scientifically.

[0093] S204. Generate multiple candidate configuration parameters based on operational constraints; calculate the first fitness corresponding to each candidate configuration parameter according to the objective function, which consists of power flow distribution parameters and configuration cost parameters; update the candidate configuration parameters based on each first fitness to obtain intermediate configuration parameters, and calculate the second fitness corresponding to each intermediate configuration parameter; iteratively execute the above update and calculation steps until the fitness change obtained from two adjacent rounds of calculation is less than a preset threshold; determine the final iteration result that meets the conditions as the energy storage configuration parameters of the distribution substation.

[0094] In this embodiment, the first fitness is an index that quantitatively evaluates the merits of candidate configuration parameters in energy storage configuration within a distribution area. A higher value indicates a better configuration. It is determined based on power flow distribution parameters and configuration cost parameters (e.g., by weighted comprehensive evaluation, where the two are weighted and summed) and is used to guide the optimization direction. The update is the process of adjusting and optimizing candidate parameters based on the evaluation results of the first fitness (e.g., through genetic algorithm mutation, particle swarm optimization position update, etc.) to gradually bring the parameters closer to the global optimum, and then generating intermediate configuration parameters. The second fitness similarly evaluates the merits of the intermediate parameters (calculated in a similar way to the first fitness) and is used to judge the optimization effect. The energy storage configuration conditions are determined by comparing whether the difference between the second fitness and the first fitness in the current optimization round is less than a preset threshold to determine whether the scheme meets the criteria. If it meets the criteria, the iteration is terminated and the final configuration is determined using the intermediate parameters; otherwise, the first fitness is recalculated and the iteration continues until the conditions are met.

[0095] Taking the hybrid algorithm combining the sparrow search algorithm with the Gurobi solver as an example, firstly, multiple candidate configuration parameters are determined for the distribution area under operational constraints. This is similar to initializing a sparrow population, determining its size and dimensions. The server can determine the number of candidate configuration parameters and the parameter dimensions within each candidate parameter. For example, each set of candidate configuration parameters can include the number and location of energy storage devices, the operating power, current, and voltage of the photovoltaic-storage system, etc., as parameter dimensions. The parameter scale is 30 sets, meaning there are 30 sets of candidate configuration parameters. Each set of candidate configuration parameters includes the number and location of energy storage devices, the operating power, current, and voltage of the photovoltaic-storage system as set under operational constraints.

[0096] Based on the topology of the distribution radio area, each candidate configuration parameter can be expressed as:

[0097]

[0098] Where X is a matrix composed of the candidate configuration parameters. For each candidate configuration parameter, N is the parameter size of the candidate configuration parameter, such as 30, X i For the i-th candidate configuration parameter, Let d represent the specific parameters included in the i-th candidate configuration parameter, where d is the parameter dimension.

[0099] Based on the candidate configuration parameters, power flow distribution parameters, and configuration cost parameters, determine the first fitness for each candidate configuration parameter. If an objective function is constructed based on the power flow distribution parameters and configuration cost parameters, aiming to minimize the weighted sum of the power flow distribution parameters and configuration cost parameters, this objective function can be expressed as:

[0100]

[0101] in, For distribution radio areas in typical scenarios The power flow distribution parameters are as follows: Typical scenario The scenario probability, w1 is the weighting coefficient of the power flow distribution parameters of the photovoltaic-storage system in the energy storage configuration, C ESS w2 represents the configuration cost parameter of energy storage equipment in the distribution substation, and w2 represents the weighting coefficient of the configuration cost parameter of the energy storage device in the energy storage configuration.

[0102] The objective function is solved for each candidate configuration parameter to obtain its corresponding first fitness. Then, each candidate configuration parameter is updated based on its first fitness to obtain intermediate configuration parameters. The update method refers to the specific way to adjust and optimize each candidate configuration parameter, determined by the level of the first fitness. Different first fitness values ​​can correspond to different update methods, allowing the candidate configuration parameters to change towards a globally better direction.

[0103] For example, taking the hybrid algorithm combining the sparrow search algorithm with the Gurobi solver, the better configuration parameter among the candidate configuration parameters can be determined as the discoverer, while the remaining worse configuration parameters are designated as the joiners. The discoverer and joiners can update according to their respective update methods. When the position of the discoverer changes, the joiner can update its own position based on the change in the position of the discoverer. That is, when the candidate configuration parameter of the discoverer is updated, the candidate configuration parameter of the joiner can be updated based on the update of the candidate configuration parameter of the discoverer.

[0104] In an optional embodiment, when updating the candidate configuration parameters for the discoverer, the update method is as follows:

[0105]

[0106] in, For the i-th candidate configuration parameter to be the discoverer; Here, represents the intermediate configuration parameter corresponding to the i-th candidate configuration parameter for the discoverer; i is the index of the discoverer; t is the iteration number; R2 is the warning value; ST is the safety value of the current environment; r2 is a random number between [0,1]; T max is the maximum number of iterations; Q is a random number following a normal distribution; and L is the unit value matrix.

[0107] When updating the configuration parameters of a candidate joining entity, the update method is as follows:

[0108]

[0109] in, The intermediate configuration parameters are the configuration parameters corresponding to the j-th candidate configuration parameter for joining; Here are the configuration parameters for the j-th candidate to join; j is the index of the joiner; t is the iteration number; The current optimal position is the candidate configuration parameter with the highest fitness. This represents the worst possible position, i.e., the candidate configuration parameter with the lowest first fitness. A matrix is ​​generated by randomly assigning +1 and -1 to elements; Q is a random number that follows a normal distribution; L is a unit value matrix; N is the number of all candidate configuration parameters.

[0110] When updating the candidate configuration parameters for the scout, the update method is as follows:

[0111]

[0112] in, For the k-th candidate configuration parameter to act as a scout; Here are the configuration parameters for the (k+1)th candidate scout; k is the index of the joiner; t is the iteration number; The current optimal position is the candidate configuration parameter with the highest fitness. β represents the worst position, i.e., the candidate configuration parameter with the smallest first fitness; β is a random number following a normal distribution; K is a random number between [-1, 1]. To avoid the smallest constant with a denominator of zero; f g The global optimal fitness value is the largest first fitness value; f w f represents the worst global fitness value, i.e., the smallest first fitness. i The first fitness of the i-th candidate configuration parameter.

[0113] The operational constraints include: determining the first constraint for the energy storage equipment based on the load data, operating data, and safe operating conditions of the energy storage equipment in the distribution transformer area; determining the second constraint for the photovoltaic-energy storage system based on the load data and safe operating conditions of the photovoltaic-energy storage system in the distribution transformer area; and determining the third constraint for each operating line and each line node based on the load data, operating data, and safe operating conditions of each operating line and each operating line node in the distribution transformer area.

[0114] The first constraint includes: the active and reactive power of the energy storage device are constrained by the current state of the energy storage converter and the energy storage device, that is:

[0115]

[0116] Among them, P ESS,t Let Q be the active power of the energy storage device at time t. ESS,t Let be the reactive power of the energy storage device at time t. The rated power capacity of the energy storage converter. This indicates that there exists a time t for the formula to hold true.

[0117] When providing voltage support, the energy storage device is constrained by the upper and lower limits of its reactive power, which are limited by the capacity of the energy storage converter.

[0118]

[0119] Among them, Q ESS,t Let be the reactive power of the energy storage device at time t. This represents the upper limit of the reactive power of the energy storage device. This represents the lower limit of the upper limit of the reactive power of the energy storage device. This indicates that there exists a time t for the formula to hold true.

[0120] The current state constraints of the energy storage device are as follows:

[0121]

[0122] Among them, SOE t Let SOE be the state of charge of the energy storage device at time t. t+1 Let P be the state of charge of the energy storage device at time t+1. ESS,t E represents the active power of the energy storage device at time t. ESS,n The rated capacity of the configured energy storage device is λ, which is an adjustable parameter, typically ranging from 0 to 0.5. For time intervals, This indicates that there exists a time t for the formula to hold true.

[0123] Given the constraints on charging and discharging losses in energy storage devices, the losses generated during the charging and discharging process of the energy storage batteries can be replaced by equivalent resistance, resulting in:

[0124]

[0125] Among them, R ESS R is the equivalent resistance. ESS,n For the rated capacity of the configured energy storage device, The rated power capacity of the energy storage converter. Let T be the time interval, and T be the total time. Let be the charging and discharging efficiency of the energy storage device; be a constant.

[0126] The overall constraints of energy storage devices, namely:

[0127]

[0128]

[0129]

[0130]

[0131] Among them, X ESS,i Let be a 0-1 decision variable for whether an energy storage device is installed at node i. This indicates that there exists a node i such that the above formula holds true. P represents the maximum number of energy storage devices allowed to be installed in a distribution area. k For the capacity of the configured energy storage device, This represents the maximum configurable capacity of the energy storage device. E represents the charge / discharge rate of the energy storage device. ESS This refers to the rated capacity of the energy storage device.

[0132] The server can determine a second constraint condition for the operation of the optical storage system based on the load data and safe operating conditions of the optical storage system in the distribution area. Specifically, the second constraint condition may include:

[0133] Photovoltaic output constraints in photovoltaic-storage systems, namely:

[0134]

[0135]

[0136] in, Let be the active power of the photovoltaic system at node i at time t. Let be the reactive power of the photovoltaic system at node i at time t. Let be the maximum active power of the photovoltaic system at time t; The rated power capacity of the photovoltaic inverter. This indicates that there exist nodes i and time t such that the corresponding formula holds true.

[0137] Based on the load data, operational data, and safe operating conditions of each operating line and its nodes within the distribution substation area, a third constraint condition is determined for the operation of each operating line and its nodes. In specific implementation, the third constraint condition may include:

[0138] Current flow balance constraint, namely:

[0139]

[0140] in, Let be the load active power of node i at time t. Let be the load reactive power of node i at time t. Let be the active power of the photovoltaic system at node i at time t. Let be the reactive power of the photovoltaic system at node i at time t. Let be the active power of the energy storage device at node i at time t. Let be the reactive power of the energy storage device at node i at time t. Let be the active power loss of node i at time t. Let be the reactive power loss of node i at time t. Let be the active power of the power flow on the line between node i and node j at time t. Let be the power flow reactive power of the line running between node i and node j at time t. Let i be the set of neighboring nodes of node i. This indicates that there exist nodes i and time t such that the corresponding formula holds true.

[0141] Node security constraints, namely:

[0142]

[0143] Among them, U i,t Let U be the voltage at node i at time t. min U is the minimum allowable value for the node voltage. max This represents the minimum permissible value for the node voltage. This indicates that there exist nodes i and time t such that the corresponding formula holds true.

[0144] Line overload constraint, namely:

[0145]

[0146] Among them, S ij,t Let the apparent power of the power flow between node i and node j at time t be denoted as . The maximum allowable power capacity of the running line between node i and node j. Let be the current in branch l at time t. The maximum current carrying capacity of branch l is This indicates that there exist nodes i, j, and time t such that the corresponding formula holds true.

[0147] S205. Configure the operation of energy storage devices and photovoltaic-storage systems in the distribution area based on energy storage configuration parameters.

[0148] In this embodiment, to verify the feasibility of the energy storage configuration methods for distribution transformer substations in the above embodiments, an improved IEEE-33 node distribution network is analyzed. The data used are actual data from distribution transformer substations experiencing seasonal heavy overload. The nodes of this network connected to distributed photovoltaic power sources are nodes 15, 20, 24, and 32, and its topology is as follows: Figure 3As shown. The rated capacities of distributed photovoltaic power sources PV1, PV2, PV3, and PV4 are 0.5MW, 1MW, 0.5MW, and 1MW, respectively. The candidate installation locations for energy storage devices are nodes 14, 20, 22, and 31. The unit power investment cost of the energy storage devices is $200,000 / MW, the unit capacity investment cost is $300,000 / MWh, the charge / discharge efficiency is 0.95, and the state of charge range is 0.2~0.8. The model is solved using a hybrid algorithm combining the sparrow search algorithm and the Gurobi solver, with the following parameter settings: population size of 20, discoverer ratio of 20%, safety factor of 0.6, and number of iterations of 100. The iteration process during the algorithm solution is as follows: Figure 4 As shown, the energy storage device configuration results are as follows: Figure 5 The table shows the power flow distribution uniformity index for four typical days (i.e., typical scenarios) in the distribution transformer area. Figure 6 As shown. Combined with Figure 5 and Figure 6 It can be seen that, compared with before treatment (i.e. before configuration), the power flow distribution uniformity index of typical days of heavy overload in the above embodiments has decreased significantly after treatment (configuration), that is, the heavy overload situation of the distribution area has been significantly improved, indicating that the methods of the above embodiments can ensure the economy of energy storage configuration while treating the heavy overload problem of the distribution area.

[0149] Figure 7 A schematic diagram of the energy storage configuration device for the distribution substation provided in this application is shown below. Figure 7 As shown, the energy storage configuration device 70 for the distribution substation provided in this embodiment includes:

[0150] The first processing module 701 is used to determine at least one typical scenario based on the source-load historical data of the optical storage system in the distribution area, wherein the typical scenario is used to characterize the operating period of the distribution area when the load rate meets the overload condition.

[0151] The second processing module 702 is used to determine the power flow distribution parameters of the distribution area based on typical scenarios, topology data and operation data of the distribution area; wherein, the power flow distribution parameters are used to characterize the uniformity of load distribution of each operating line in the photovoltaic storage system.

[0152] The third processing module 703 is used to determine the energy storage configuration parameters of the distribution substation based on the power flow distribution parameters and configuration cost parameters, and to configure the operation of the energy storage equipment and photovoltaic-storage system in the distribution substation based on the energy storage configuration parameters.

[0153] In one possible implementation, the first processing module 701 is further configured to:

[0154] The historical source-load data is vectorized according to the time dimension to obtain power samples at each historical moment;

[0155] The power samples are clustered according to the operating segments of the distribution station area to obtain the clustering results for each operating segment;

[0156] Based on the clustering results, the runtime segments whose load rates meet the overload regulation requirements are selected, and the runtime segments are determined as typical scenarios.

[0157] In one possible implementation, the first processing module 701 is further configured to:

[0158] Determine the first feature vector of the source load historical data based on the time dimension;

[0159] Acquire at least one data point from weather data, electricity price information, and user behavior patterns of the distribution area at various historical moments, and determine the data point as an auxiliary input feature vector;

[0160] The first feature vector and the auxiliary input feature vector are fused to obtain power samples for each historical moment.

[0161] In one possible implementation, the second processing module 702 is further configured to:

[0162] Based on the topology and operation data of each operating line in the distribution substation, the load fluctuation parameters of each operating line under typical scenarios are determined.

[0163] Based on the line weight and load fluctuation parameters of each operating line, the load fluctuation parameters are weighted and fused to obtain the distribution parameter components of the distribution substation in a typical scenario.

[0164] Determine the probability of typical scenarios occurring in the distribution area, and determine the power flow distribution parameters based on the distribution parameter components and scenario probabilities.

[0165] In one possible implementation, the third processing module 703 is further configured to:

[0166] Multiple candidate configuration parameters are generated based on runtime constraints;

[0167] Based on the objective function, calculate the first fitness corresponding to each candidate configuration parameter. The objective function consists of power flow distribution parameters and configuration cost parameters.

[0168] The candidate configuration parameters are updated based on each first fitness to obtain intermediate configuration parameters, and the second fitness corresponding to each intermediate configuration parameter is calculated.

[0169] The above update and calculation steps are executed iteratively until the fitness change obtained from two adjacent rounds of calculation is less than a preset threshold.

[0170] The final iterative result that meets the conditions is determined as the energy storage configuration parameters of the distribution substation.

[0171] In one possible implementation, the operational constraints include:

[0172] Based on the load data, operating data, and safe operating conditions of the energy storage equipment in the distribution substation, the first constraint condition of the energy storage equipment is determined.

[0173] Based on the load data and safe operating conditions of the photovoltaic and energy storage systems in the distribution area, the second constraint condition of the photovoltaic and energy storage systems is determined.

[0174] Based on the load data, operating data, and safe operating conditions of each operating line and its nodes in the distribution area, the third constraint conditions for each operating line and its nodes are determined.

[0175] The energy storage configuration device for the distribution substation provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0176] Figure 8 A hardware schematic diagram of the energy storage configuration device for the distribution substation provided in this application. (See attached diagram.) Figure 8 As shown, the electronic device 80 provided in this embodiment includes at least one processor 801 and a memory 802. Optionally, the device 80 further includes a communication component 803. The processor 801, memory 802, and communication component 803 are connected via a bus 804.

[0177] In a specific implementation, at least one processor 801 executes computer execution instructions stored in memory 802, causing at least one processor 801 to perform the above-described method.

[0178] The specific implementation process of processor 801 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0179] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0180] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0181] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0182] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0183] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0184] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0185] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0186] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, methods, or units, and may be electrical, mechanical, or other forms.

[0187] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0188] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0189] If a function is implemented as 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 this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0190] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0191] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for configuring energy storage in a distribution radio area, characterized in that, include: At least one typical scenario is determined based on the source-load historical data of the photovoltaic-storage system in the distribution radio station area; wherein, the typical scenario is used to characterize the operating period of the distribution radio station area when the load rate meets the overload condition. Based on the typical scenario, the topology data and operation data of the distribution station, the power flow distribution parameters of the distribution station are determined; wherein, the power flow distribution parameters are used to characterize the uniformity of load distribution of each operating line in the optical storage system; Based on the power flow distribution parameters and configuration cost parameters, the energy storage configuration parameters of the distribution substation are determined, and the operation of the energy storage devices and photovoltaic-storage systems in the distribution substation is configured based on the energy storage configuration parameters.

2. The method according to claim 1, characterized in that, The determination of at least one typical scenario based on the source-load historical data of the photovoltaic-storage system in the distribution area includes: The historical source-load data is vectorized according to the time dimension to obtain power samples at each historical moment; The power samples are clustered according to the operating segments of the distribution station area to obtain the clustering results for each operating segment; Based on the clustering results, the runtime segments whose load rates meet the overload regulation requirements are selected, and the runtime segments are identified as typical scenarios.

3. The method according to claim 2, characterized in that, The process of vectorizing the historical source-load data according to the time dimension to obtain power samples at each historical moment includes: Determine the first feature vector of the source load historical data based on the time dimension; Acquire at least one data information from the weather data, electricity price information, and user behavior patterns of the distribution station at each historical moment, and determine the data information as an auxiliary input feature vector; The first feature vector and the auxiliary input feature vector are fused to obtain the power samples for each historical moment.

4. The method according to claim 1, characterized in that, The determination of power flow distribution parameters for the distribution substation based on the typical scenario, the topology data, and operational data of the distribution substation includes: Based on the topology data and the operation data of each operating line in the distribution substation, the load fluctuation parameters of each operating line under the typical scenario are determined; Based on the line weight of each operating line and the load fluctuation parameter, the load fluctuation parameter is weighted and fused to obtain the distribution parameter components of the distribution substation under the typical scenario; Determine the probability of the typical scenario occurring in the distribution area, and determine the power flow distribution parameters based on the distribution parameter components and the scenario probability.

5. The method according to any one of claims 1-4, characterized in that, The step of determining the energy storage configuration parameters of the distribution substation based on the power flow distribution parameters and configuration cost parameters includes: Multiple candidate configuration parameters are generated based on runtime constraints; Based on the objective function, the first fitness corresponding to each of the candidate configuration parameters is calculated, wherein the objective function is composed of the power flow distribution parameters and the configuration cost parameters; The candidate configuration parameters are updated based on each first fitness to obtain intermediate configuration parameters, and the second fitness corresponding to each intermediate configuration parameter is calculated. The above update and calculation steps are executed iteratively until the fitness change obtained from two adjacent rounds of calculation is less than a preset threshold. The final iteration result that meets the conditions is determined as the energy storage configuration parameters of the distribution radio zone.

6. The method according to claim 5, characterized in that, The operational constraints include: Based on the load data, operating data, and safe operating conditions of the energy storage device in the distribution area, the first constraint condition of the energy storage device is determined; Based on the load data and safe operating conditions of the photovoltaic storage system in the distribution area, the second constraint condition of the photovoltaic storage system is determined; Based on the load data, operating data, and safe operating conditions of each operating line and line node in the distribution area, the third constraint conditions for each operating line and each line node are determined.

7. An energy storage configuration device for a distribution radio station area, characterized in that, include: The first processing module is used to determine at least one typical scenario based on the source-load historical data of the optical storage system in the distribution area. The typical scenario is used to characterize the operating period of the distribution area when the load rate meets the overload condition. The second processing module is used to determine the power flow distribution parameters of the distribution area based on the typical scenario, the topology data and operation data of the distribution area. The power flow distribution parameters are used to characterize the uniformity of load distribution of each operating line in the optical storage system. The third processing module is used to determine the energy storage configuration parameters of the distribution area based on the power flow distribution parameters and configuration cost parameters, and to configure the operation of the energy storage devices and photovoltaic-storage systems in the distribution area based on the energy storage configuration parameters.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.

Images