Control method, device, equipment, storage medium and program product of energy storage system

Abstract

The application relates to a control method and device of an energy storage system, computer equipment, a computer readable storage medium and a computer program product. Historical operation data of a target object of the energy storage system is acquired; a plurality of typical energy use scenes of the target object are determined according to the historical operation data; the plurality of typical energy use scenes are taken as constraints, and an optimal performance index of the energy storage system is taken as a first optimization target to determine a configuration optimization result; predicted operation data of the target object in a future preset operation period is determined according to the historical operation data; the configuration optimization result is taken as a constraint, and an optimal operation energy efficiency of the energy storage system in the preset operation period is determined according to the predicted operation data to generate an operation scheduling strategy of the energy storage system; and the energy storage system is controlled to execute the operation scheduling strategy. Through the technical scheme, the configuration optimization and the operation scheduling of the energy storage system are effectively coordinated.

Description

Technical Field

[0001] This application relates to the field of energy storage system technology, and in particular to a control method, apparatus, equipment, storage medium and program product for an energy storage system. Background Technology

[0002] With the continuous increase in renewable energy penetration and the diversification of electricity load, the challenges faced by the power system, such as increased volatility and widening peak-valley differences, are becoming increasingly prominent. Energy storage systems, with their flexible power regulation, have become a key technological means to support peak shaving and valley filling, renewable energy consumption, and grid ancillary services. In current engineering applications, the management of energy storage systems typically adopts scheduling schemes based on fixed rules, such as setting load thresholds to trigger charging and discharging, or controlling peak and valley periods based on time-of-use pricing.

[0003] However, the aforementioned technologies generally suffer from a core flaw: the capacity and power configuration optimization of energy storage systems is disconnected from and lacks connection with their daily operation and scheduling. Specifically, existing configuration methods are often independent of actual operating conditions, failing to incorporate dynamic constraints such as charge / discharge depth, cycle count, and power response requirements imposed by daily operation and scheduling strategies into configuration decisions. This leads to a disconnect between the configuration scheme and actual on-site needs. This separation makes it prone to spatiotemporal mismatches in actual operation and scheduling, such as energy storage capacity failing to match predicted peak loads, insufficient power response to support rapid adjustments, or charge / discharge strategies exceeding configuration boundaries. This not only results in low equipment utilization and wasted investment but also significantly reduces the overall operating efficiency and lifecycle economics of the energy storage system.

[0004] Therefore, how to effectively coordinate the configuration optimization and operation scheduling of energy storage systems has become a pressing technical challenge. Summary of the Invention

[0005] Therefore, it is necessary to provide a control method, device, computer equipment, computer-readable storage medium, and computer program product for an energy storage system to address the aforementioned technical problems, so as to enable effective coordination between the configuration optimization and operation scheduling of the energy storage system.

[0006] In a first aspect, this application provides a control method for an energy storage system, including:

[0007] Obtain historical operating data of the target object of the energy storage system;

[0008] Based on the historical operating data, multiple typical energy consumption scenarios for the target object are determined;

[0009] Using multiple typical energy consumption scenarios as constraints, and taking the optimal performance index of the energy storage system as the first optimization objective, the configuration optimization result is determined.

[0010] Based on the historical operating data, predict the operating data of the target object within a future preset operating period is determined;

[0011] Using the configuration optimization results as constraints, and based on the predicted operating data, with the second optimization objective being to achieve optimal operating energy efficiency of the energy storage system within the preset operating period, an operating scheduling strategy for the energy storage system is generated.

[0012] Control the energy storage system to execute the operation scheduling strategy.

[0013] In one embodiment, determining multiple typical energy consumption scenarios of the target object based on the historical operating data includes:

[0014] The historical operational data is clustered to obtain multiple cluster centers;

[0015] The typical energy consumption scenario is determined based on the cluster centers; wherein, one cluster center corresponds to one typical energy consumption scenario.

[0016] In one embodiment, determining the configuration optimization result by taking the typical energy consumption scenario as a constraint and achieving optimal performance indicators of the energy storage system as the first optimization objective includes:

[0017] Determine the boundary conditions that the energy storage system should satisfy when operating in each of the typical energy consumption scenarios;

[0018] Establish an objective function with the goal of achieving the optimal performance indicators of the energy storage system throughout its preset life cycle;

[0019] The objective function is solved under the given boundary conditions to obtain the configuration optimization result of the energy storage system.

[0020] In one embodiment, solving the objective function under the boundary conditions to obtain the configuration optimization result of the energy storage system includes:

[0021] Retrieve multiple candidate configuration parameter groups;

[0022] Substitute each of the candidate configuration parameter groups into each of the typical energy consumption scenarios;

[0023] The candidate configuration parameter group that satisfies the boundary conditions corresponding to each typical energy consumption scenario and makes the objective function optimal is determined as the target configuration parameter group;

[0024] The configuration optimization result is determined based on the target configuration parameter set.

[0025] In one embodiment, the configuration optimization result includes optimized energy storage capacity and optimized energy storage power; the step of using the configuration optimization result as a boundary condition, and based on the predicted operating data, generating an operation scheduling strategy for the energy storage system with the second optimization objective of achieving optimal operating energy efficiency of the energy storage system within a preset operating period, includes:

[0026] Based on the optimized energy storage capacity and the optimized energy storage power, the constraint boundaries for the operation and scheduling of the energy storage system are determined; wherein, the constraint boundaries include at least one of the upper limit of energy storage capacity, the upper limit of energy storage power, and the state of charge limit.

[0027] Based on the predicted operating data, with the maximization of the operating energy efficiency of the energy storage system within the preset operating period as the second optimization objective, the charging and discharging power of the energy storage system at each time node is determined within the constraint boundary, and the operating scheduling strategy is generated.

[0028] In one embodiment, the predicted operating data includes load change trends and electricity price change trends; the step of determining the charging and discharging power of the energy storage system at each time node within the constraint boundary and generating the operation scheduling strategy includes:

[0029] The peak load period and / or valley load period of the energy storage system within the preset operating period are determined based on the load change trend.

[0030] Based on the electricity price change trend, determine the peak electricity price period and / or the trough electricity price period within the preset operating time;

[0031] Based on the peak load period and / or the peak electricity price period, determine the discharge power and discharge period of the energy storage system within the constraint boundary;

[0032] Based on the off-peak load period and / or the off-peak electricity price period, determine the charging power and charging period of the energy storage system within the constraint boundary;

[0033] The operation scheduling strategy is generated based on the discharge power, discharge period, charging power, and charging period at each time point.

[0034] Secondly, this application also provides a control device for an energy storage system, comprising:

[0035] The acquisition module is used to acquire historical operating data of the target object of the energy storage system;

[0036] The first determining module is used to determine multiple typical energy consumption scenarios of the target object based on the historical operating data;

[0037] The first optimization module is used to take multiple typical energy consumption scenarios as constraints and take the optimal performance index of the energy storage system as the first optimization objective to determine the configuration optimization result.

[0038] The second determining module is used to determine the predicted operating data of the target object in a future preset operating period based on the historical operating data;

[0039] The second optimization module is used to take the configuration optimization result as a constraint and, based on the predicted operating data, to generate an operating scheduling strategy for the energy storage system with the second optimization objective of achieving optimal operating energy efficiency of the energy storage system within the preset operating period.

[0040] The control module is used to control the energy storage system to execute the operation scheduling strategy.

[0041] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in any of the embodiments of the first aspect above.

[0042] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the embodiments of the first aspect above.

[0043] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the embodiments of the first aspect above.

[0044] The aforementioned control method, device, computer equipment, computer-readable storage medium, and computer program product for energy storage systems determine multiple typical energy consumption scenarios that characterize the electricity consumption patterns of the target object of the energy storage system based on historical operating data. These typical energy consumption scenarios are then used as constraints to optimize the configuration parameters of the energy storage system. This ensures that configuration optimization is a constrained optimization based on the actual energy consumption patterns of the energy storage system, thereby guaranteeing that the configuration scheme matches actual demand. Furthermore, by using the configuration optimization results as constraints to generate operation scheduling strategies, operation scheduling is executed within the physical boundaries defined by the configuration scheme, avoiding problems such as scheduling instructions exceeding equipment capacity or mismatch with the configuration scheme. Simultaneously, operation scheduling makes decisions based on predicted operating data with the goal of optimal energy efficiency, overcoming the lag defects of traditional fixed threshold triggering methods. Therefore, the configuration scheme provides a reasonable physical boundary for operation scheduling, and operation scheduling maximizes benefits within the configuration boundary. This effectively solves technical problems such as spatiotemporal mismatch, insufficient or over-configured capacity, and charging / discharging strategy exceeding limits caused by the separation of configuration and operation, significantly improving the operating efficiency and life-cycle economics of the energy storage system. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the control method of an energy storage system in one embodiment;

[0047] Figure 2 This is a flowchart illustrating the control method of the energy storage system in another embodiment;

[0048] Figure 3 This is a flowchart illustrating the control method of the energy storage system in yet another embodiment;

[0049] Figure 4 This is a flowchart illustrating the control method of the energy storage system in yet another embodiment;

[0050] Figure 5 This is a structural block diagram of the control device of an energy storage system in one embodiment;

[0051] Figure 6 This is a structural block diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0054] The control method for energy storage systems provided in this application can be applied to various power consumption scenarios equipped with energy storage systems. Specifically, this control method is suitable for power consumption scenarios with predictable electricity consumption patterns and peak-valley electricity price differences, such as commercial buildings, office buildings, industrial parks, factories, data centers, hotels, hospitals, and transportation hubs.

[0055] In some embodiments, the control method for the energy storage system provided in this application can be applied to the control system of the energy storage system. This control system comprises three components: a data acquisition layer, an edge computing device, and a cloud management platform.

[0056] The data acquisition layer is deployed on-site, connecting various field devices via multiple communication protocols to collect historical operating data and send control commands to the energy storage system. Edge computing devices are deployed on-site to perform real-time scheduling calculations, protocol conversion, data preprocessing, and local control decisions. The cloud management platform is deployed on a cloud server to perform historical data storage, protocol library management, configuration parameter optimization calculations, and configuration scheme distribution.

[0057] Both edge computing devices and cloud management platforms have data processing capabilities. The control method of the energy storage system provided in this application embodiment can be executed in the edge computing device, or in the cloud management platform, or partially in the edge computing device and partially in the cloud management platform. No limitation is made here.

[0058] In one exemplary embodiment, refer to Figure 1 A control method for an energy storage system is provided, the method comprising the following steps S100 to S600.

[0059] S100: Obtain historical operating data of the target object in the energy storage system.

[0060] The target entities refer to the electricity-consuming entities served by the energy storage system, such as commercial complexes, industrial parks, office buildings, or independent microgrids.

[0061] Historical operating data refers to power-related monitoring data generated by the target object during its past operation. In some implementations, historical operating data can be acquired through various data acquisition devices in the data acquisition layer. For example, load data at the grid connection point or main incoming line of the energy storage system can be acquired through smart meters, photovoltaic output data of the photovoltaic system can be acquired through photovoltaic inverters, and data such as charging and discharging power and state of charge of the energy storage system can be acquired through the energy storage system management unit.

[0062] Alternatively, historical operating data can also be read directly from the target object's existing energy management system or building automation system.

[0063] As an example, after collecting historical operational data, it can be stored in a time sequence. For instance, collecting and storing historical operational data with a 15-minute time granularity creates daily load curves across 96 time segments, thus balancing data accuracy and storage efficiency. Alternatively, historical operational data can be collected and stored using other time granularities, such as 5 minutes, 10 minutes, or 30 minutes, depending on the load fluctuation characteristics of the target object and the performance of the data acquisition equipment.

[0064] In some implementations, historical operating data includes load data, renewable energy output data, electricity price data, and demand data. Load data reflects the power consumption of the target entity at different time points and its changing patterns; renewable energy output data reflects the power generation capacity and temporal characteristics of distributed power sources such as photovoltaic and wind power configured for the target entity; electricity price data reflects the differences in grid purchase prices over different time periods; and demand data reflects the maximum average power consumption of the target entity within a specific time window.

[0065] In some implementations, the duration of historical operational data collection can be configured. For example, historical operational data of the target object over the past year can be collected to cover the target object's electricity consumption characteristics in different seasons; historical operational data over the past month or quarter can also be collected to meet the data requirements of rapid deployment scenarios.

[0066] S200: Determine multiple typical energy consumption scenarios for the target object based on historical operating data.

[0067] Typical energy consumption scenarios are used to characterize the electricity consumption patterns of a target object. A typical energy consumption scenario is a temporal feature template extracted from historical operating data through pattern recognition, representing the typical electricity consumption behavior of the target object under different operating conditions. The electricity consumption behavior of the target object typically exhibits different patterns at different time scales; for example, there may be significant differences between weekdays and holidays, between different seasons, and between different weather conditions. The purpose of identifying multiple typical energy consumption scenarios is to identify these differentiated electricity consumption patterns.

[0068] As an example, with commercial buildings as the target, several typical energy consumption scenarios can be extracted, such as "high load scenario on hot summer workdays", "heating day scenario in winter", "ordinary workday scenario in spring and autumn" and "low load scenario on weekends / holidays".

[0069] Understandably, each typical energy consumption scenario is essentially a set of parameters that characterizes the electricity consumption characteristics under specific operating conditions. For example, it may include the typical load curve shape, typical photovoltaic output curve shape, typical electricity price distribution characteristics, and typical demand level for that scenario. By identifying multiple typical energy consumption scenarios, dispersed historical operating data can be condensed into several representative typical operating conditions, thereby enabling a description of the target object's electricity consumption behavior.

[0070] In some implementations, historical operating data reflects the electricity consumption behavior patterns of the target object at different time scales. By performing cluster analysis and other processing on the historical operating data, several representative electricity consumption patterns can be identified from the historical operating data.

[0071] As an example, each typical energy consumption scenario can be a working condition vector containing complete time-series information, covering multi-dimensional feature data such as load time-series, photovoltaic output time-series, and electricity price time-series under that typical energy consumption scenario.

[0072] S300: Taking multiple typical energy consumption scenarios as constraints and taking the optimal performance indicators of the energy storage system as the primary optimization objective, the configuration optimization result is determined.

[0073] Typical energy consumption scenarios represent the historical electricity consumption behavior of the target object. In the process of determining the configuration optimization results, the candidate configuration schemes need to be tested against the typical energy consumption scenarios as their operating conditions. That is, each candidate configuration scheme needs to be verified under the operating conditions represented by each typical energy consumption scenario. Only when the candidate configuration scheme can meet the basic physical constraints that the energy storage system should follow in each typical energy consumption scenario is the candidate configuration scheme considered feasible.

[0074] Basic physical limitations are objective constraints related to the operating characteristics of the energy storage system itself. For example, the charging and discharging power of the energy storage system is limited by its rated power, and the state of charge of the energy storage system is limited by the upper and lower limits determined by its rated capacity.

[0075] Under the constraints of the above typical energy consumption scenarios, the first optimization objective is to achieve the optimal performance index of the energy storage system. The target configuration scheme is selected from a large number of feasible candidate configuration schemes, thereby obtaining the configuration optimization result.

[0076] Performance metrics are evaluation indicators used to assess the overall operational performance of an energy storage system over its predetermined lifecycle. They measure the comprehensive advantages and disadvantages of different candidate configurations throughout their lifecycle. The specific composition of performance metrics can be flexibly adjusted in different application scenarios. As an example, performance metrics can include the comprehensive benefits generated by the energy storage system during operation, such as arbitrage benefits obtained through electricity price differences, demand cost reductions achieved by reducing peak loads, and reduced electricity purchase costs by incorporating distributed power sources. As another example, performance metrics can also include the comprehensive costs required by the energy storage system throughout its lifecycle, such as initial equipment investment costs, installation and commissioning costs, operation and maintenance costs, and equipment replacement costs. As another example, the net value after subtracting comprehensive costs from comprehensive benefits can be used as a performance metric to reflect the overall return level of the energy storage system throughout its lifecycle.

[0077] S400: Determines the predicted operating data of the energy storage system within the future preset operating period based on historical operating data.

[0078] Historical operational data contains temporal patterns in the electricity consumption behavior of the target entity, such as daily periodic variations in load, differences between weekdays and holidays, and differences in electricity consumption characteristics across different seasons. Based on these historical patterns, and combined with relevant influencing factors within the future preset operating period, reasonable inferences can be made about the future operating status of the target entity.

[0079] In some implementations, the load sequence and related variable sequence of the target object during historical operating periods are extracted from historical operating data, a prediction model reflecting the electricity consumption behavior of the target object is constructed, and the prediction model is applied to the future preset operating periods to obtain predicted operating data.

[0080] Alternatively, other methods can be used to determine the predicted operating data. For example, historical data with the same time attributes as the future preset operating period can be extracted from historical operating data as a reference, or a regression analysis method can be used to establish the correlation between electricity consumption behavior and influencing factors for prediction. The specific choice of the above different prediction methods can be flexibly determined according to the availability of data for the target object, the strength of the regularity of electricity consumption behavior, and the required prediction accuracy.

[0081] Predictive operational data should include at least time-series information related to the operation and scheduling of the energy storage system, such as the electricity load level and corresponding electricity price level of the target object at each time point within the preset operating period in the future.

[0082] The preset operating period can be the next 24 hours, or it can be set to the next 12 hours, the next 48 hours, or other suitable durations according to the energy storage capacity and scheduling needs of the energy storage system, depending on the actual needs of the energy storage system's regulation capability and scheduling cycle.

[0083] S500: Using the configuration optimization results as constraints, and based on the predicted operating data, with the second optimization objective being to achieve the optimal operating energy efficiency of the energy storage system within the preset operating period, an operation scheduling strategy for the energy storage system is generated.

[0084] Operational energy efficiency is an indicator used to evaluate the comprehensive operational benefits of an energy storage system through charge and discharge scheduling within a preset operating period. It reflects the comprehensive benefit level that an energy storage system can obtain by rationally arranging the timing and power of charge and discharge under a given configuration scheme.

[0085] As an example, operational energy efficiency can include arbitrage benefits gained through electricity price differences, demand costs reduced by cutting peak loads, and electricity purchase costs reduced by absorbing distributed power sources. The specific composition and weight of the benefit dimensions can be flexibly set according to the actual application scenario. For example, in scenarios where peak-valley arbitrage is the main objective, the focus can be on electricity price difference benefits, while in scenarios where demand management is the main objective, the focus can be on demand reduction benefits.

[0086] The configuration optimization results include various configuration parameters, which collectively define the operational capability range of the energy storage system when determining the operation and scheduling strategy. As an example, the configuration optimization results include optimized energy storage capacity and optimized energy storage power. Optimized energy storage capacity limits the maximum amount of electricity the energy storage system can store, corresponding to the upper and lower limits of the state of charge (SOC). Optimized energy storage power limits the maximum power the energy storage system can charge or release at any given time, corresponding to the upper and lower limits of the charge and discharge power. Therefore, when determining the operation and scheduling strategy for the energy storage system, it is essential to ensure that the system operates within the aforementioned SOC and charge / discharge power limits.

[0087] Using the configuration optimization results as constraints, and based on the predicted operating data, the second optimization objective is to achieve the optimal operating energy efficiency of the energy storage system within the preset operating period. The operation scheduling strategy of the energy storage system within the preset operating period is then determined.

[0088] As an example, the operation scheduling strategy may specifically include information such as whether the energy storage system is charging or discharging at each time node within a preset operating period, the power of charging or discharging, and the start and end times of charging and discharging. Its form may be a sequence of charging and discharging power values ​​at each time node within the preset operating period.

[0089] S600: Controls the energy storage system to execute operation scheduling strategies.

[0090] After determining the operation scheduling strategy, the operation scheduling strategy is converted into executable control commands, and these control commands are sent to the energy storage system to realize the control of the energy storage system.

[0091] The specific form of the control command depends on the equipment type and communication interface standard of the energy storage system. For example, it can be a power setpoint output in the form of an analog signal, a switch control signal output in the form of a digital signal, or a digital command frame based on a standard communication protocol (such as Modbus, CAN, etc.).

[0092] In some implementations, during the issuance of control commands, the actual operating status of the energy storage system is monitored, and the actual operating parameters (such as actual charging and discharging power, actual state of charge, etc.) are compared with the expected values ​​in the operation scheduling strategy. The subsequent control commands are adjusted based on the comparison results to ensure that the actual operation of the energy storage system is consistent with the description of the operation scheduling strategy.

[0093] In this embodiment, multiple typical energy consumption scenarios that characterize the electricity consumption patterns of the target energy storage system are determined based on historical operational data. These typical energy consumption scenarios are then used as constraints to optimize the configuration parameters of the energy storage system. This ensures that configuration optimization is a constrained optimization based on the actual energy consumption patterns of the energy storage system, thereby guaranteeing that the configuration scheme matches actual needs. Furthermore, by using the configuration optimization results as constraints to generate an operation scheduling strategy, operation scheduling is executed within the physical boundaries defined by the configuration scheme, avoiding problems such as scheduling instructions exceeding equipment capabilities or being mismatched with the configuration scheme. Simultaneously, operation scheduling makes decisions based on predicted operational data with the goal of optimal operational energy efficiency, overcoming the lag defects of traditional fixed threshold triggering methods. Thus, the configuration scheme provides a reasonable physical boundary for operation scheduling, and operation scheduling maximizes benefits within the configuration boundary. This effectively solves technical problems such as spatiotemporal mismatch, insufficient or over-configured capacity, and charging / discharging strategy exceeding limits caused by the separation of configuration and operation, significantly improving the operational efficiency and life-cycle economics of the energy storage system.

[0094] In some implementations, refer to Figure 2 S200 includes the following S210 to S220.

[0095] S210: Cluster the historical operation data to obtain multiple cluster centers.

[0096] S220: Determine typical energy consumption scenarios based on cluster centers.

[0097] Each cluster center corresponds to a typical energy consumption scenario.

[0098] Clustering is a method in unsupervised learning that aims to group data samples with similar features in a dataset into the same category, so that the similarity between samples of the same category is as high as possible and the difference between samples of different categories is as large as possible.

[0099] Historical operating data is used as samples to be clustered. A clustering algorithm calculates the similarity or distance between samples, grouping samples with high similarity into the same cluster, thereby identifying several major electricity consumption patterns naturally present in the historical operating data. After clustering, multiple cluster centers are obtained, each representing a typical characteristic of all samples in its cluster. Each cluster center is then designated as a typical energy consumption scenario, with one cluster center corresponding to one typical energy consumption scenario. In this embodiment, the specific type of clustering algorithm is not limited, as long as multiple cluster centers are obtained.

[0100] In some implementations, historical operational data includes load time-series data, which can be used as samples to be clustered. Each sample is represented by a vector consisting of load values ​​at different time points in the load time-series data.

[0101] In some implementations, historical data can be preprocessed before clustering, such as filling in missing values ​​in the original data, removing or correcting outliers, and normalizing the data, to improve the accuracy and reliability of the clustering results.

[0102] In some implementations, after identifying multiple typical energy consumption scenarios, the scenario weight value for each typical energy consumption scenario can be determined based on the proportion of the sample size corresponding to each typical energy consumption scenario to all historical operating data. The scenario weight value reflects the frequency or probability of each typical energy consumption scenario occurring in actual operation. By determining the scenario weight value, the optimization objective can be weighted according to the scenario weight value of each typical energy consumption scenario during subsequent configuration optimization, making the optimization results more focused on the frequently occurring typical energy consumption scenarios, thereby further improving the performance of the configuration scheme under common operating conditions.

[0103] In this embodiment, clustering is used to automatically identify the electricity consumption patterns of target objects, eliminating the need for manual experience in setting scenario types. This improves the objectivity and accuracy of identifying typical energy consumption scenarios and reduces labor costs. Furthermore, by identifying cluster centers as typical energy consumption scenarios, each scenario accurately characterizes the features of the applied electricity consumption patterns, providing a reliable data foundation for subsequent configuration optimization.

[0104] In some implementations, refer to Figure 3 S300 includes the following S310 to S330.

[0105] S310: Determine the boundary conditions that the energy storage system should meet when operating in each typical energy consumption scenario.

[0106] S320: Establish an objective function with the goal of achieving optimal performance indicators for the energy storage system throughout its preset life cycle.

[0107] S330: Solve the objective function under boundary conditions to obtain the configuration optimization results of the energy storage system.

[0108] Boundary conditions define the physically feasible domain of an energy storage system under various typical energy consumption scenarios. As an example, boundary conditions can include power balance boundary conditions and state-of-charge (POC) boundary conditions. Power balance boundary conditions require that, at any time point in any typical energy consumption scenario, the load demand of the target object must satisfy a power conservation relationship with the output of distributed power sources, the charging and discharging power of the energy storage system, and the power exchanged with the grid, and that the charging and discharging power of the energy storage system must not exceed its rated power limit. POC boundary conditions require that, at any time point in any typical energy consumption scenario, the POC of the energy storage system must be maintained within a safe operating range, neither exceeding the upper limit determined by its rated capacity nor falling below the lower limit.

[0109] The objective function is a mathematical expression used in optimization problems to evaluate the merits of candidate configuration schemes. It takes the candidate configuration schemes as input variables and the performance indicators of the energy storage system over a preset life cycle as output evaluation, and is used to measure the overall merits of different candidate configuration schemes.

[0110] As an example, the form of the objective function can be determined based on the composition of the performance metrics. For instance, when the performance metrics are defined as the net difference between overall benefits and overall costs, the objective function is to maximize that net difference.

[0111] In some implementations, multiple candidate configuration parameter sets are obtained, and each candidate configuration parameter set is substituted into each typical energy consumption scenario. The candidate configuration parameter set that satisfies the boundary conditions corresponding to each typical energy consumption scenario and makes the objective function optimal is determined as the target configuration parameter set. The configuration optimization result is determined based on the target configuration parameter set.

[0112] In this implementation, within the feasible region defined by the boundary conditions, the optimal set of configuration parameters for the objective function is searched. Specifically, a pre-defined optimization algorithm can be used to search the solution space of the candidate configuration parameter sets. The optimization algorithm iteratively adjusts the values ​​of the candidate configuration parameter sets, substituting each set into various typical energy consumption scenarios to verify the feasibility of the boundary conditions. If a candidate configuration parameter set does not satisfy the corresponding boundary conditions in any typical energy consumption scenario, it is excluded. For candidate configuration parameter sets that satisfy the boundary conditions in all typical energy consumption scenarios, the output value of their objective function is determined. After multiple iterations, the optimal solution is gradually approximated, and finally, the candidate configuration parameter set that satisfies the boundary conditions in all typical energy consumption scenarios and optimizes the objective function is output. This set is then identified as the target configuration parameter set and used as the configuration optimization result.

[0113] In this embodiment, each typical energy consumption scenario generates an independent set of boundary conditions, which together constitute constraints on candidate configuration schemes. Any candidate configuration scheme must satisfy the corresponding boundary conditions under all typical energy consumption scenarios to pass the feasibility verification, ensuring that the final output configuration optimization result has practical operational feasibility under all typical energy consumption scenarios of the target object, and avoiding the problem that the configuration scheme is designed only for a specific working condition and cannot operate normally under other working conditions.

[0114] In some implementations, the configuration optimization results include optimized energy storage capacity and optimized energy storage power. (Refer to...) Figure 4 S500 includes the following S510 to S520.

[0115] S510: Determine the constraint boundaries for the operation and scheduling of the energy storage system based on the optimized energy storage capacity and optimized energy storage power.

[0116] Among them, the constraint boundary includes at least one of the following: upper limit of energy storage capacity, upper limit of energy storage power, and state of charge limit.

[0117] S520: Based on the predicted operating data, with the second optimization objective of maximizing the operating energy efficiency of the energy storage system within the preset operating period, the charging and discharging power of the energy storage system at each time node is determined within the constraint boundary, and an operation scheduling strategy is generated.

[0118] Optimized energy storage capacity represents the maximum amount of electricity that an energy storage system can store, directly determining the upper limit of energy storage during scheduled operation. Optimized energy storage power represents the maximum power that an energy storage system can charge or release per unit time, directly determining the upper limit of the charging and discharging rate at various times during scheduled operation. Optimized energy storage capacity and optimized energy storage power together limit the physical capabilities of the energy storage system when determining the operation and scheduling strategy, forming the constraint boundary for the operation and scheduling of the energy storage system.

[0119] Constraint boundaries may include at least one of the following: upper limit of energy storage capacity, upper limit of energy storage power, and state of charge (SCC) limit. The upper limit of energy storage capacity corresponds to the optimized energy storage capacity, limiting that the cumulative stored energy of the energy storage system at any given time must not exceed this upper limit. The upper limit of energy storage power corresponds to the optimized energy storage power, limiting that the absolute value of the charging and discharging power of the energy storage system at any given time must not exceed this upper limit. The SCC limit is used to constrain the range of SCC changes during the operation of the energy storage system. The upper limit of the SCC limit is related to the upper limit of energy storage capacity, while the lower limit of the SCC limit can be set independently according to the safe operation requirements of the energy storage system, for example, it can be set to 10% to 20% of the rated capacity.

[0120] Predictive operating data provides predicted values ​​for the operating conditions of the target object within a preset operating period in the future. Based on this, a charging and discharging power scheme that maximizes the energy efficiency of the energy storage system under the premise of satisfying the above-mentioned constraint boundaries is determined.

[0121] Operational energy efficiency is an indicator used to evaluate the comprehensive operational benefits achieved by an energy storage system through charge and discharge scheduling within a preset operating period. Maximizing operational energy efficiency as the optimization goal means that the determination of the operation scheduling strategy is guided by maximizing comprehensive operational benefits.

[0122] When determining the charging and discharging power at each time point, a preset optimization algorithm is used to search for the power sequence that maximizes the operating energy efficiency within the feasible region defined by the constraint boundary, thereby generating an operation scheduling strategy.

[0123] In some implementations, the optimization algorithm can be a particle swarm optimization (PSO) algorithm. The PSO algorithm initializes multiple particles in the solution space. Each particle represents a candidate scheduling strategy, and its position vector corresponds to the sequence of charging and discharging power values ​​at each time point within a preset runtime period. That is, a single particle contains power decision information for all time points within the preset runtime period, with the number of dimensions being the same as the number of time points. Each particle has two attributes: position and velocity. Position represents the coordinates of the candidate solution in the solution space, and velocity represents the particle's direction and speed of movement in the solution space. In each iteration, for each particle, a simulation is first performed based on the power sequence corresponding to the particle to calculate the trajectory of the state of charge change at each time point. The candidate scheduling strategy is then checked to see if it satisfies the constraint boundaries (e.g., whether the charging and discharging power exceeds the power upper limit at each time point, and whether the state of charge exceeds the capacity upper and lower limits at each time point). If satisfied, the corresponding operating energy efficiency value of the particle is calculated as its fitness; otherwise, a penalty is imposed on the particle's fitness, or the particle is skipped. Subsequently, the individual optimal position and the global optimal position are updated based on the fitness value of each particle. Then, based on the individual optimal position and the global optimal position, the velocity and position of each particle are updated according to the particle swarm update formula. Through the above iterative process, the particle swarm gradually gathers towards the optimal solution region. When the preset iteration termination condition is reached, the power sequence corresponding to the global optimal position is output as the optimal operation scheduling strategy.

[0124] In this embodiment, by transforming the optimized energy storage capacity and optimized energy storage power from the configuration optimization results into operational scheduling constraints, a clear physical feasible domain is defined for operational scheduling. This ensures that the formulation of operational scheduling strategies is always within the physical capabilities of the equipment, avoiding operational risks such as equipment overload and insufficient capacity caused by scheduling instructions exceeding the configuration boundaries. Simultaneously, by optimizing scheduling within the aforementioned constraints with the goal of maximizing operational energy efficiency, the energy storage system can fully realize its operational potential within the physical capabilities defined by the configuration scheme, thereby maximizing operational benefits.

[0125] In some implementations, S520 above, determining the charging and discharging power of the energy storage system at each time node within the constraint boundary and generating an operation scheduling strategy includes the following steps:

[0126] Based on load change trends, determine the peak load periods and / or valley load periods of the energy storage system within the preset operating period; based on electricity price change trends, determine the peak electricity price periods and / or valley electricity price periods within the preset operating period; based on the peak load periods and / or peak electricity price periods, determine the discharge power and discharge period of the energy storage system within the constraint boundaries; based on the valley load periods and / or valley electricity price periods, determine the charging power and charging period of the energy storage system within the constraint boundaries; based on the discharge power, discharge period, charging power, and charging period at each time node, generate an operation scheduling strategy.

[0127] Load variation trends reflect the electricity load level of the target object at various time points within the preset operating period and how it changes over time. By analyzing load variation trends, periods with high load levels (i.e., peak load periods) and periods with low load levels (i.e., valley load periods) can be identified. Peak load periods correspond to time intervals where the target object's electricity consumption is concentrated, and the power grid supply pressure is high during these periods; valley load periods typically correspond to time intervals where the target object's electricity consumption is less, and the power grid supply is relatively abundant during these periods.

[0128] As an example, based on the load forecast values ​​at each time point in the load change trend, peak load periods and valley load periods are identified according to preset load peak and valley determination rules (e.g., the load value exceeds a certain threshold or is in the high range of the load curve).

[0129] Electricity price trends reflect the electricity price level at various time points within the future preset operating period and how it changes over time. By analyzing electricity price trends, periods with high electricity prices (i.e., peak electricity price periods) and periods with low electricity prices (i.e., trough electricity price periods) can be identified. Peak electricity price periods correspond to times when grid load is high and power supply resources are relatively tight, resulting in higher electricity purchase costs during these periods. Trough electricity price periods correspond to times when grid load is low and power supply resources are relatively abundant, resulting in lower electricity purchase costs during these periods.

[0130] As an example, based on the predicted electricity prices at each time point in the electricity price change trend, the peak and trough periods of electricity prices are identified according to the preset peak and trough determination rules (e.g., the electricity price exceeds a certain threshold or is in the high range of the electricity price curve).

[0131] Based on peak load periods and / or peak electricity price periods, the discharge power and discharge periods of the energy storage system are determined within the constraint boundaries. Specifically, both peak load periods and peak electricity price periods are candidate periods requiring discharge support from the energy storage system. During peak load periods, the energy storage system can reduce the net peak load of the target object and lower demand charges by discharging. During peak electricity price periods, the energy storage system can replace purchasing electricity from the grid at higher prices by discharging, reducing electricity costs. The benefits of discharging are particularly significant when peak load periods and peak electricity price periods overlap. Within the aforementioned peak load periods and / or peak electricity price periods, the discharge power and the start and end times of the discharge are determined based on the current state of charge of the energy storage system and the power limit defined by the constraint boundaries.

[0132] Based on off-peak load periods and / or off-peak electricity prices, the charging power and charging periods of the energy storage system are determined within the constraint boundaries. Specifically, both off-peak load periods and off-peak electricity prices are suitable candidate periods for charging the energy storage system. During off-peak load periods, charging the energy storage system will not significantly increase the net load peak; during off-peak electricity prices, the electricity purchase cost for charging the energy storage system is lower. Within the aforementioned off-peak load periods and / or off-peak electricity prices, the charging power and the start and end times of charging are determined based on the current state of charge of the energy storage system and the upper limits of capacity and power defined by the constraint boundaries.

[0133] The charging and discharging power values ​​at each time point determined above are integrated in time sequence to form a complete charging and discharging power time sequence scheme within the preset operating period, which is then used as the output of the operation scheduling strategy.

[0134] In this embodiment, by comprehensively utilizing load change trends and electricity price change trends, suitable periods for discharging and charging are identified from the load side and the electricity price side, respectively. This enables the energy storage system's charging and discharging decisions to be optimized in two dimensions: peak shaving and valley filling, and peak-valley arbitrage. As a result, the system maximizes its operational energy efficiency while meeting configuration boundary constraints.

[0135] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0136] Based on the same inventive concept, this application also provides a control device for an energy storage system to implement the control method of the energy storage system described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of the one or more control device embodiments of the energy storage system provided below can be found in the limitations of the control method of the energy storage system above, and will not be repeated here.

[0137] In one exemplary embodiment, such as Figure 5 As shown, a control device for an energy storage system is provided, comprising: an acquisition module 501, a first determination module 502, a first optimization module 503, a second determination module 504, a second optimization module 505, and a control module 506, wherein:

[0138] The acquisition module 501 is used to acquire historical operating data of the target object of the energy storage system;

[0139] The first determining module 502 is used to determine multiple typical energy consumption scenarios of the target object based on historical operating data;

[0140] The first optimization module 503 is used to take multiple typical energy consumption scenarios as constraints and take the optimal performance index of the energy storage system as the first optimization objective to determine the configuration optimization result.

[0141] The second determining module 504 is used to determine the predicted running data of the target object in a future preset running period based on historical running data;

[0142] The second optimization module 505 is used to take the configuration optimization results as constraints and, based on the predicted operating data, to generate an operating scheduling strategy for the energy storage system with the goal of achieving optimal operating energy efficiency of the energy storage system within a preset operating period.

[0143] The control module 506 is used to control the energy storage system to execute the operation scheduling strategy.

[0144] In some embodiments, the first determining module 502 is further configured to cluster historical operating data to obtain multiple cluster centers; and determine typical energy consumption scenarios based on the cluster centers; wherein, one cluster center corresponds to one typical energy consumption scenario.

[0145] In some embodiments, the first optimization module 503 is further configured to determine the boundary conditions that the energy storage system should meet when operating in each typical energy consumption scenario; establish an objective function with the goal of achieving the optimal performance index of the energy storage system within a preset full life cycle; and solve the objective function under the boundary conditions to obtain the configuration optimization result of the energy storage system.

[0146] In some embodiments, the first optimization module 503 is further configured to obtain multiple candidate configuration parameter groups; substitute each candidate configuration parameter group into each typical energy consumption scenario; determine the candidate configuration parameter group that satisfies the boundary conditions corresponding to each typical energy consumption scenario and makes the objective function optimal as the target configuration parameter group; and determine the configuration optimization result based on the target configuration parameter group.

[0147] In some embodiments, the configuration optimization results include optimized energy storage capacity and optimized energy storage power. The second optimization module 505 is further configured to determine the constraint boundaries for the operation scheduling of the energy storage system based on the optimized energy storage capacity and optimized energy storage power; wherein the constraint boundaries include at least one of an upper limit for energy storage capacity, an upper limit for energy storage power, and a state of charge limit; based on predicted operating data, with maximizing the operating energy efficiency of the energy storage system within a preset operating period as the second optimization objective, the charging and discharging power of the energy storage system at each time node is determined within the constraint boundaries, and an operation scheduling strategy is generated.

[0148] In some embodiments, the predicted operating data includes load change trends and electricity price change trends. The second optimization module 505 is further configured to: determine the peak load period and / or valley load period of the energy storage system within a preset operating period based on the load change trend; determine the peak electricity price period and / or valley electricity price period within the preset operating period based on the electricity price change trend; determine the discharge power and discharge period of the energy storage system within a constraint boundary based on the peak load period and / or peak electricity price period; determine the charging power and charging period of the energy storage system within a constraint boundary based on the valley load period and / or valley electricity price period; and generate an operation scheduling strategy based on the discharge power, discharge period, charging power, and charging period at each time point.

[0149] The various modules in the control device of the aforementioned energy storage system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0150] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media to run. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a control method for an energy storage system.

[0151] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0152] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the control method of the energy storage system described in any of the above method embodiments.

[0153] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the control method of the energy storage system described in any of the above method embodiments.

[0154] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the control method for the energy storage system described in any of the above method embodiments.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A control method for an energy storage system, characterized in that, include: Obtain historical operating data of the target object of the energy storage system; Based on the historical operating data, multiple typical energy consumption scenarios for the target object are determined; Using multiple typical energy consumption scenarios as constraints, and taking the optimal performance index of the energy storage system as the first optimization objective, the configuration optimization result is determined. Based on the historical operating data, predict the operating data of the target object within a future preset operating period is determined; Using the configuration optimization results as constraints, and based on the predicted operating data, with the second optimization objective being to achieve optimal operating energy efficiency of the energy storage system within the preset operating period, an operating scheduling strategy for the energy storage system is generated. Control the energy storage system to execute the operation scheduling strategy.

2. The control method according to claim 1, characterized in that, The determination of multiple typical energy consumption scenarios for the target object based on the historical operating data includes: The historical operational data is clustered to obtain multiple cluster centers; The typical energy consumption scenario is determined based on the cluster centers; wherein, one cluster center corresponds to one typical energy consumption scenario.

3. The control method according to claim 1, characterized in that, The process of determining the configuration optimization result by taking the typical energy consumption scenario as a constraint and achieving the optimal performance index of the energy storage system as the first optimization objective includes: Determine the boundary conditions that the energy storage system should satisfy when operating in each of the typical energy consumption scenarios; Establish an objective function with the goal of achieving the optimal performance indicators of the energy storage system throughout its preset life cycle; The objective function is solved under the given boundary conditions to obtain the configuration optimization result of the energy storage system.

4. The control method according to claim 3, characterized in that, The step of solving the objective function under the boundary conditions to obtain the configuration optimization result of the energy storage system includes: Retrieve multiple candidate configuration parameter groups; Substitute each of the candidate configuration parameter groups into each of the typical energy consumption scenarios; The candidate configuration parameter group that satisfies the boundary conditions corresponding to each typical energy consumption scenario and makes the objective function optimal is determined as the target configuration parameter group; The configuration optimization result is determined based on the target configuration parameter set.

5. The control method according to claim 1, characterized in that, The configuration optimization results include optimized energy storage capacity and optimized energy storage power; the step of using the configuration optimization results as boundary conditions, and based on the predicted operating data, to generate an operation scheduling strategy for the energy storage system with the second optimization objective of achieving optimal operating energy efficiency within a preset operating period, includes: Based on the optimized energy storage capacity and the optimized energy storage power, the constraint boundaries for the operation and scheduling of the energy storage system are determined; wherein, the constraint boundaries include at least one of the upper limit of energy storage capacity, the upper limit of energy storage power, and the state of charge limit. Based on the predicted operating data, with the maximization of the operating energy efficiency of the energy storage system within the preset operating period as the second optimization objective, the charging and discharging power of the energy storage system at each time node is determined within the constraint boundary, and the operating scheduling strategy is generated.

6. The control method according to claim 5, characterized in that, The predicted operational data includes load change trends and electricity price change trends; determining the charging and discharging power of the energy storage system at each time node within the constraint boundaries and generating the operational scheduling strategy includes: The peak load period and / or valley load period of the energy storage system within the preset operating period are determined based on the load change trend. Based on the electricity price change trend, determine the peak electricity price period and / or the trough electricity price period within the preset operating time; Based on the peak load period and / or the peak electricity price period, determine the discharge power and discharge period of the energy storage system within the constraint boundary; Based on the off-peak load period and / or the off-peak electricity price period, determine the charging power and charging period of the energy storage system within the constraint boundary; The operation scheduling strategy is generated based on the discharge power, discharge period, charging power, and charging period at each time point.

7. A control device for an energy storage system, characterized in that, include: The acquisition module is used to acquire historical operating data of the target object of the energy storage system; The first determining module is used to determine multiple typical energy consumption scenarios of the target object based on the historical operating data; The first optimization module is used to take multiple typical energy consumption scenarios as constraints and take the optimal performance index of the energy storage system as the first optimization objective to determine the configuration optimization result. The second determining module is used to determine the predicted operating data of the target object in a future preset operating period based on the historical operating data; The second optimization module is used to take the configuration optimization result as a constraint and, based on the predicted operating data, to generate an operating scheduling strategy for the energy storage system with the second optimization objective of achieving optimal operating energy efficiency of the energy storage system within the preset operating period. The control module is used to control the energy storage system to execute the operation scheduling strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images