Optimized energy scheduling method for centralized shared energy storage

Abstract

The invention provides an optimized energy scheduling method for centralized shared energy storage, and relates to the technical field of energy storage optimization, and the method comprises the steps: obtaining a power system monitoring data set, carrying out the energy scheduling target feature fitting, constructing a prediction shared energy storage scheduling scene, obtaining a plurality of energy storage unit monitoring data sets, and then carrying out the energy scheduling decision registration, and determining a shared energy storage scheduling decision, performing fitting correction optimization to output a shared energy storage scheduling scheme, and finally performing energy scheduling on the centralized shared energy storage system according to the shared energy storage scheduling scheme. According to the invention, the technical problem that the energy scheduling efficiency and the stable operation of the power system are further influenced due to inaccurate state monitoring of the power system caused by untimely data acquisition, insufficient data processing capability and insufficient advanced scheduling decision method in the prior art can be solved; effective energy scheduling is carried out on the centralized shared energy storage system according to the shared energy storage scheduling scheme, and the stability of a power system is improved.

Description

Technical Field

[0001] The present application relates to the technical field of energy storage optimization, and in particular to an optimized energy scheduling method for centralized shared energy storage. Background Art

[0002] In recent years, the shared energy storage model has gradually emerged. This model refers to a centralized large-scale independent energy storage power station invested and built by a third party. In addition to meeting the needs of its own power station, it also provides services for other new energy power stations. The emergence of this model effectively integrates the decentralized energy storage resources on the power supply side, the grid side, and the user side, and improves the utilization rate of energy storage resources and the regulation capacity of the grid system. With the increasing complexity of the power system, energy optimization and scheduling has become an important means to improve energy utilization efficiency, reduce energy costs, reduce imbalances between supply and demand, and improve power supply reliability. The application of optimized energy scheduling methods can achieve coordination and optimization of various links such as power supply, transmission and consumption, thereby improving the overall performance of the power system.

[0003] At present, existing power system monitoring and dispatching methods often face problems such as untimely data collection, limited data processing capabilities, and inaccurate dispatching decisions. Traditional power system monitoring may rely on manual inspections or relatively basic automated data collection systems, which results in insufficient guarantees for the real-time and accuracy of data acquisition. At the same time, in terms of data processing, the lack of efficient algorithms and models limits the ability to analyze and predict the state of the power system in real time. In addition, existing energy dispatching methods are usually based on rules or simple heuristic algorithms, which make it difficult to achieve global optimal resource allocation and accurate dispatching decisions.

[0004] In summary, the existing technology has technical problems such as untimely data collection, insufficient data processing capabilities, and inadequately advanced dispatch decision-making methods, which lead to inaccurate power system status monitoring, further affecting the efficiency of energy dispatch and the stable operation of the power system. Summary of the invention

[0005] The purpose of this application is to provide an optimized energy scheduling method for centralized shared energy storage, in order to solve the technical problems of the prior art such as untimely data collection, insufficient data processing capabilities and insufficiently advanced scheduling decision methods, which lead to inaccurate power system status monitoring and further affect the efficiency of energy scheduling and the stable operation of the power system. Effective energy scheduling of the centralized shared energy storage system according to the shared energy storage scheduling plan will help improve the stability of the power system.

[0006] In view of the above problems, the present application provides an optimized energy scheduling method for centralized shared energy storage.

[0007] The present application provides an optimized energy scheduling method for centralized shared energy storage, wherein the method includes: a real-time monitoring module of an interactive power system to obtain a power system monitoring data set; fitting energy scheduling target characteristics of a centralized shared energy storage system according to the power system monitoring data set to construct a predicted shared energy storage scheduling scenario; connecting an Internet of Things monitoring module of the centralized shared energy storage system to obtain multiple energy storage unit monitoring data sets; based on the multiple energy storage unit monitoring data sets, aligning energy scheduling decisions of the centralized shared energy storage system according to the predicted shared energy storage scheduling scenario to determine a shared energy storage scheduling decision; fitting, correcting and optimizing the shared energy storage scheduling decision according to energy scheduling constraint rules to output a shared energy storage scheduling plan; and energy scheduling of the centralized shared energy storage system according to the shared energy storage scheduling plan.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: Through the real-time monitoring module of the interactive power system, a power system monitoring data set is obtained; according to the power system monitoring data set, the energy scheduling target characteristics of the centralized shared energy storage system are fitted to construct a predicted shared energy storage scheduling scenario; the Internet of Things monitoring module of the centralized shared energy storage system is connected to obtain multiple energy storage unit monitoring data sets; based on the multiple energy storage unit monitoring data sets, the energy scheduling decision of the centralized shared energy storage system is aligned according to the predicted shared energy storage scheduling scenario, and the shared energy storage scheduling decision is determined; according to the energy scheduling constraint rules, the shared energy storage scheduling decision is fitted, corrected and optimized, and a shared energy storage scheduling plan is output; according to the shared energy storage scheduling plan, the centralized shared energy storage system is energy scheduled, which effectively solves the technical problems of untimely data collection, insufficient data processing capability and insufficiently advanced scheduling decision methods in the prior art, resulting in inaccurate power system status monitoring, further affecting the efficiency of energy scheduling and the stable operation of the power system, and effectively scheduling the centralized shared energy storage system according to the shared energy storage scheduling plan is helpful to improve the stability of the power system.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 A flow chart of an optimized energy dispatching method for centralized shared energy storage in this application; Figure 2 A schematic diagram of a process for generating a predicted shared energy storage scheduling scenario in the optimized energy scheduling method for centralized shared energy storage used in this application. DETAILED DESCRIPTION

[0012] This application solves the technical problems of inaccurate power system status monitoring, further affecting the efficiency of energy dispatch and stable operation of the power system, by providing an optimized energy dispatching method for centralized shared energy storage. The application solves the technical problems of inaccurate power system status monitoring, further affecting the efficiency of energy dispatch and stable operation of the power system, such as untimely data collection, insufficient data processing capability and inadequately advanced dispatching decision methods in the prior art, by providing an optimized energy dispatching method for centralized shared energy storage. Effective energy dispatching of the centralized shared energy storage system according to the shared energy storage dispatching plan helps to improve the stability of the power system.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] Embodiment 1 Please refer to the attached Figure 1 The present application provides an optimized energy scheduling method for centralized shared energy storage, wherein the method specifically comprises the following steps: S1: Real-time monitoring module of interactive power system, obtaining power system monitoring data set; Specifically, the real-time monitoring module of the interactive power system is responsible for real-time monitoring and collection of various operating data of the power system to form a power system monitoring data set. This module continuously collects key parameters such as voltage, current, power factor, frequency, etc. in the power grid through various sensors and measuring devices, such as voltage transformers, current transformers, power meters, etc. The real-time monitoring module collects the operating data of the power system in real time through various sensors. These data include but are not limited to key parameters such as voltage, current, power, temperature, frequency, etc.

[0015] S2: fitting the energy dispatch target characteristics of the centralized shared energy storage system according to the power system monitoring data set, and constructing a predicted shared energy storage dispatch scenario; Specifically: Extract features related to energy scheduling from the power system monitoring data set. These features include grid load, power generation, electricity price, renewable energy generation, charging and discharging status of energy storage system, grid frequency changes, etc. Next, use the extracted features to fit the target features. Use statistical learning methods or machine learning algorithms, such as linear regression, support vector machines, neural networks, etc., to establish a relationship model between features and energy storage scheduling targets. For example, a model can be trained to predict the charging and discharging needs of energy storage systems in a certain period of time in the future. Based on the fitted relationship model, a predictive shared energy storage scheduling scenario is constructed. These scenarios include different load demands, electricity price fluctuations, renewable energy generation, etc. By simulating these scenarios, the scheduling needs of energy storage systems under different circumstances can be predicted.

[0016] S3: Connecting to the Internet of Things monitoring module of the centralized shared energy storage system to obtain a plurality of energy storage unit monitoring data sets; Specifically, determine the IoT communication protocols, such as MQTT, CoAP, etc., that are compatible with the centralized shared energy storage system. Connect each energy storage unit to the IoT monitoring module through the determined IoT communication protocol to ensure that each module can accurately collect and transmit data. The IoT monitoring module monitors the energy storage unit in real time and collects key parameters including voltage, current, temperature, and charge and discharge status.

[0017] S4: Based on the plurality of energy storage unit monitoring data sets, the centralized shared energy storage system is aligned with energy scheduling decisions according to the predicted shared energy storage scheduling scenario to determine a shared energy storage scheduling decision; Specifically, the monitoring data sets from different energy storage units are integrated to ensure that all data are consistent in time and format. The timestamps of the data sets are aligned. The monitoring data is used to evaluate the key performance indicators of each energy storage unit, such as the health status, charging and discharging efficiency, and remaining capacity. Through comparative analysis, energy storage units with excellent performance or potential problems are identified. According to the predicted shared energy storage dispatch scenario, factors such as energy demand, electricity price fluctuations, and renewable energy supply in the future are analyzed. Combining historical data with current monitoring data, the dispatch demand of the energy storage system in the future is predicted. Based on the predicted demand and the performance analysis of the energy storage unit, a preliminary energy dispatch plan is formulated. The preliminary plan is fine-tuned by comprehensively considering the real-time status, charging and discharging rate, and capacity limit of the energy storage unit. Ensure that the dispatch decision meets the safe operation specifications of the power grid and avoids damage to the energy storage unit caused by excessive charging and discharging. Under the premise of meeting the grid demand and the performance constraints of the energy storage unit, the dispatch decision is optimized to maximize the overall energy efficiency. The decision includes determining which energy storage units are charged and discharged when, and the power and duration of charging and discharging.

[0018] S5: performing fitting correction optimization on the shared energy storage scheduling decision according to the energy scheduling constraint rules, and outputting a shared energy storage scheduling plan; Specifically, grid safety constraints ensure that dispatch decisions do not cause safety issues such as grid overload and voltage over-limit. Energy storage unit operation constraints consider the charging and discharging rate, capacity limit, minimum operation and downtime of energy storage units. Economic constraints ensure that dispatch decisions are economically feasible, such as considering charging and discharging costs, electricity price fluctuations, etc. Take the shared energy storage dispatch decision as the initial plan and build a mathematical optimization model in combination with constraints. The objective function can be minimizing system operating costs, maximizing energy efficiency, or other relevant indicators. The model is fitted using historical data and real-time monitoring data to ensure that the model can accurately reflect the dynamic characteristics of the actual system. The initial dispatch decision is corrected based on the fitting results to meet various constraints. Optimization algorithms such as linear programming, nonlinear programming, and genetic algorithms are used to solve the optimization model. Based on the optimization results, a corrected and optimized shared energy storage dispatch plan is output. The plan includes key information such as the charging and discharging plan, time node, power, and duration of each energy storage unit.

[0019] S6: Perform energy scheduling for the centralized shared energy storage system according to the shared energy storage scheduling plan.

[0020] Specifically, the plan in the scheduling scheme is converted into specific control instructions. Before executing the scheduling, the energy storage system is fully checked to ensure that it is in good working condition. Confirm that the current status of the energy storage unit, such as power and temperature, is consistent with the starting conditions in the scheduling scheme. The converted control instructions are sent to the corresponding energy storage unit through the control center of the centralized shared energy storage system. After receiving the instructions, the energy storage unit starts to execute the operation according to the predetermined charging and discharging plan.

[0021] Further, if Figure 2 As shown, step S2 of the present application also includes: Dynamically fitting the power system monitoring data set based on a preset future time zone window to obtain a predicted power dynamic data set; Performing a dynamic change comparison based on the power system monitoring data set and the predicted power dynamic data set, and outputting a fitted power dynamic change comparison result; Inputting the fitted power dynamic change comparison result into a pre-built energy dispatch target fitting module to obtain a plurality of predicted energy storage dispatch target characteristic data; Data fusion is performed based on the multiple predicted energy storage scheduling target characteristic data to generate the predicted shared energy storage scheduling scenario.

[0022] Specifically, the historical data in the power system monitoring data set is trained using time series analysis, machine learning models or other statistical methods to predict the power dynamics in a future time zone window. By fitting the model, a predicted power dynamic data set is generated, which contains the predicted state of the power system in the future preset time zone window, such as predicted load, power generation, etc. The actual power system monitoring data set is compared with the predicted power dynamic data set to analyze the differences and trends between the two. A comparison result is output, showing the degree of fit and difference between the predicted value and the actual value. The energy scheduling target fitting module is a pre-built model or algorithm for predicting energy storage scheduling target characteristics based on the input power dynamic changes. By inputting the comparison result, the module will output multiple predicted target feature data related to energy storage scheduling, such as predicted energy storage demand, charging and discharging timing, etc. The multiple predicted energy storage scheduling target feature data are processed comprehensively to obtain a more comprehensive and accurate energy storage scheduling scenario prediction. The predicted shared energy storage scheduling scenario is the final generated scenario, which integrates multiple predicted target feature data.

[0023] Furthermore, the present application also includes: Performing joint record backtracking on the power system and the centralized shared energy storage system to obtain a plurality of energy dispatch target analysis record sets, each of which includes a power dynamic change comparison record set and an energy storage dispatch target characteristic data record set; Performing supervised training on the multiple energy scheduling target analysis record sets respectively to construct multiple energy scheduling target feature prediction channels that meet energy scheduling target prediction accuracy constraints; The multiple energy scheduling target feature prediction channels are used as multiple parallel prediction nodes, and the multiple parallel prediction nodes are merged to generate the energy scheduling target fitting module.

[0024] Specifically, the historical data of the power system and the centralized shared energy storage system are integrated and analyzed. By backtracking and recording the operating data and dispatching decisions of both in the past period of time, multiple energy dispatching target analysis record sets are formed. Each of the multiple energy dispatching target analysis record sets contains a power dynamic change comparison record set, which reflects the state and change of the power system at different time points, and an energy storage dispatching target characteristic data record set, which records the dispatching target and characteristic data of the energy storage system at the corresponding time point. Using the collected record sets as training data, supervised learning is performed on each energy dispatching target analysis record set. The known output, namely the energy storage dispatching target characteristic data, is used to train the model so that it can accurately predict the future energy storage dispatching target. Through training, multiple prediction channels that meet the energy dispatching target prediction accuracy constraints are constructed. Each channel is based on specific data features and model parameter optimization, aiming to improve the prediction accuracy of future energy storage dispatching targets. The constructed multiple energy dispatching target characteristic prediction channels are regarded as multiple parallel prediction nodes. Each node can independently predict the future energy storage dispatching target. In order to improve the stability and accuracy of the prediction, these parallel prediction nodes are merged to form an integrated energy dispatching target fitting module. This module can comprehensively consider the outputs of different prediction channels and give a more robust and accurate prediction result.

[0025] Furthermore, step S4 of the present application also includes: Collecting energy dispatch records according to the centralized shared energy storage system to obtain a shared energy dispatch record set; Performing energy scheduling solution registration on the shared energy scheduling record set according to the multiple energy storage unit monitoring data sets and the predicted shared energy storage scheduling scenario to obtain a registered energy scheduling solution space; Performing scheduling solution confidence calculation according to the registered energy scheduling solution space to obtain a plurality of registered scheduling solution confidence coefficients; Arranging the registered energy scheduling solution space in descending order according to the multiple registered scheduling solution confidence coefficients to obtain a preferred registered energy scheduling solution set that satisfies a predetermined sequence constraint; Scheduling solutions are fused according to the preferred aligned energy scheduling solution set to generate the shared energy storage scheduling decision.

[0026] Specifically, historical energy dispatch records are collected from the centralized shared energy storage system. These records include key information such as the charging and discharging time, power, and power of the energy storage unit to form a shared energy dispatch record set. Multiple energy storage unit monitoring data sets are used to reflect the real-time status and performance of the energy storage unit and predict the shared energy storage dispatch scenario. The shared energy dispatch record set is aligned based on the future dispatch scenario constructed based on the predicted data. The historical dispatch records are matched with the current state of the energy storage unit and the future dispatch requirements. Through the alignment, a solution space is obtained, which contains a variety of possible energy dispatch solutions. The confidence is calculated for each solution in the aligned energy dispatch solution space. The confidence may be based on a variety of factors, such as the historical performance of the solution, the degree of fit with the predicted scenario, the state of the energy storage unit, etc. The calculated confidence is expressed in the form of a coefficient, which is used to quantify the reliability and superiority of each dispatch solution. According to the confidence coefficient, the solutions in the aligned energy dispatch solution space are sorted in descending order. From the sorted solution space, the dispatch solutions that meet the predetermined sequence constraints, such as the top N solutions with the highest confidence, are selected to form a preferred set. The dispatch solutions in the optimal energy dispatch solution set are fused. The fusion may involve weighted averaging, voting mechanisms, or other optimization algorithms to produce a final dispatch solution that combines the advantages of each optimal solution. The final solution generated by the fusion is the shared energy storage dispatch decision, which takes into account the status, performance, and future dispatch requirements of the energy storage unit, and aims to achieve the optimal dispatch of the energy storage system.

[0027] Furthermore, the present application also includes: Extracting a first shared energy scheduling record group according to the shared energy scheduling record set, wherein the first shared energy scheduling record group includes monitoring record samples of each energy storage unit, shared energy storage scheduling scenario record samples, and energy scheduling solution record samples; According to the plurality of energy storage unit monitoring data sets, corresponding similarity identification is performed on the monitoring record samples of each energy storage unit to determine a similarity coefficient of the state of the sample energy storage unit; Performing similarity identification on the shared energy storage scheduling scenario record samples according to the predicted shared energy storage scheduling scenario, and determining a sample scheduling scenario similarity coefficient; Perform weighted fusion according to the sample energy storage unit state similarity coefficient and the sample scheduling scenario similarity coefficient to generate a sample energy scheduling feature registration coefficient; If the sample energy scheduling feature registration coefficients satisfy the energy scheduling feature registration constraints, the energy scheduling solution record samples are added to the registered energy scheduling solution space.

[0028] Specifically, a set of records is selected from the shared energy dispatch record set, which includes monitoring record samples of each energy storage unit, record samples of the shared energy storage dispatch scenario, and corresponding energy dispatch solution record samples. Using multiple energy storage unit monitoring data sets, similarity analysis is performed on the monitoring record samples of each energy storage unit. This process is to find the historical record sample that is most similar to the current energy storage unit state. A coefficient calculated by the similarity recognition algorithm is used to quantify the similarity between the current energy storage unit state and the historical record sample. The predicted shared energy storage dispatch scenario is compared with the shared energy storage dispatch scenario record sample to find the most similar historical dispatch scenario. The sample dispatch scenario similarity coefficient reflects the similarity between the predicted dispatch scenario and the historical record sample. The sample energy storage unit state similarity coefficient and the sample dispatch scenario similarity coefficient are comprehensively considered and weighted fused by assigning them different weights. A coefficient obtained after weighted fusion integrates the similarity of the energy storage unit state and the dispatch scenario, and is used to evaluate the matching degree of the energy dispatch solution record sample with the current actual situation. A standard or threshold is set to determine whether the sample energy dispatch feature registration coefficient meets the requirements, that is, whether it is similar enough to be included in the registered energy dispatch solution space. When the sample energy scheduling feature registration coefficient meets the constraint conditions, the corresponding energy scheduling solution record sample is added to this space. This space will eventually contain a series of energy scheduling solutions that match the current actual situation.

[0029] Furthermore, step S5 of the present application also includes: Activate the energy scheduling simulation module, and perform energy scheduling fitting on the centralized shared energy storage system in combination with the shared energy storage scheduling decision to obtain a decision fitting scheduling job data set; Perform energy scheduling evaluation according to the decision fitting scheduling job data set, and construct a decision fitting scheduling evaluation score sequence; Determining whether the decision fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule, wherein the energy scheduling constraint rule includes a predetermined scheduling evaluation interval sequence; If the decision-fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule, the shared energy storage scheduling decision is added to the shared energy storage scheduling plan.

[0030] Specifically, a simulation module dedicated to simulating energy scheduling is started or activated. This module can simulate the operating environment of the actual energy storage system and test and verify the scheduling decision. The generated shared energy storage scheduling decision is applied to the simulation module to simulate the actual scheduling process. After the scheduling decision is executed through the simulation module, a job data set will be generated, which reflects the execution effect and various performance indicators of the scheduling decision in the simulation environment. Based on the decision-fitting scheduling job data set, the effect of the scheduling decision is evaluated. The evaluation includes multiple aspects such as scheduling efficiency, energy storage utilization, and system stability. According to the evaluation results, a score is assigned to each evaluation indicator, and a score sequence is formed. This sequence objectively reflects the performance of the scheduling decision in various aspects. Energy scheduling constraint rules This is a set of preset rules and standards for evaluating whether the scheduling decision meets the predetermined performance requirements. It includes a predetermined scheduling evaluation interval sequence, that is, the acceptable range of scores for each evaluation indicator. The decision-fitting scheduling evaluation score sequence is compared with the predetermined scheduling evaluation interval sequence to determine whether the score of the scheduling decision falls within the acceptable range. If the decision-fitting scheduling evaluation score sequence meets the energy scheduling constraint rules, it means that the performance of the scheduling decision in the simulation environment meets the expected standards. Shared energy storage dispatch decisions that meet the conditions will be added to the final shared energy storage dispatch plan as a reference or execution basis for actual dispatch.

[0031] Furthermore, the present application also includes: Constructing an energy scheduling evaluation module, wherein the energy scheduling evaluation module includes a multidimensional energy scheduling evaluation channel, and the multidimensional energy scheduling evaluation channel includes an energy utilization efficiency evaluation channel, a scheduling target achievement rate evaluation channel, a scheduling operation efficiency evaluation channel, and a scheduling safety evaluation channel; The decision fitting scheduling job data set is input into the energy scheduling evaluation module to obtain the decision fitting scheduling evaluation score sequence, wherein the decision fitting scheduling evaluation score sequence includes an energy utilization efficiency evaluation score, a scheduling target achievement rate evaluation score, a scheduling job efficiency evaluation score and a scheduling safety evaluation score.

[0032] Specifically, a comprehensive energy scheduling evaluation module is constructed, which can evaluate the energy scheduling effect from multiple dimensions. Energy utilization efficiency evaluation channel This channel mainly evaluates the energy utilization efficiency during the scheduling process, such as the charging and discharging efficiency of the energy storage system, the energy conversion efficiency, etc. The efficiency of energy utilization is evaluated by analyzing the relevant data in the decision-fitting scheduling operation data set, such as power consumption, input and output power of the energy storage system, etc. Scheduling target achievement rate evaluation channel This channel evaluates the degree to which the scheduling decision achieves the preset scheduling target. The target achievement rate is calculated by comparing the actual scheduling results in the operation data set with the preset scheduling target. Scheduling operation efficiency evaluation channel This channel focuses on the execution efficiency of the scheduling operation, including the speed of issuing scheduling commands and the response speed of the energy storage system. The operation efficiency is evaluated by analyzing the execution time of the scheduling command and the system response time in the operation data set. Scheduling safety evaluation channel This channel mainly evaluates the safety of the scheduling process, including whether the system runs smoothly and whether there are safety hazards such as overload or short circuit. The safety of scheduling is evaluated by analyzing the system status parameters, fault records and other information in the data set. Next, the decision-fitting scheduling job data set obtained through the simulation module is input into the constructed energy scheduling evaluation module. Each evaluation channel will process and analyze the data set respectively, and then give the corresponding evaluation score. Finally, a decision-fitting scheduling evaluation score sequence will be obtained, which contains scores in four aspects. The energy utilization efficiency evaluation score reflects the efficiency of energy utilization during the scheduling process. The scheduling target achievement rate evaluation score reflects the achievement of the preset target by the scheduling decision. The scheduling operation efficiency evaluation score shows the execution efficiency of the scheduling operation. The scheduling safety evaluation score represents the safety of the scheduling process.

[0033] Furthermore, the present application also includes: If the decision-fitting scheduling evaluation score sequence does not satisfy the energy scheduling constraint rule, multiple rounds of random mutation are performed according to the shared energy storage scheduling decision to obtain a scheduling decision mutation space; Extracting a first variable energy storage scheduling decision according to the scheduling decision variation space; Performing a fitting energy scheduling evaluation on the first variant energy storage scheduling decision according to the energy scheduling simulation module and the energy scheduling evaluation module to generate a first variant decision fitting scheduling evaluation score sequence; Determining whether the first variation decision fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule; If the first variant decision fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule, adding the first variant energy storage scheduling decision to the shared energy storage scheduling plan; If the first variation decision fitting scheduling evaluation score sequence does not satisfy the energy scheduling constraint rule, the energy scheduling constraint rule is used as the optimization target, and the scheduling decision variation space is iteratively optimized in combination with the energy scheduling simulation module and the energy scheduling evaluation module to generate the shared energy storage scheduling plan.

[0034] Specifically, if the initial shared energy storage scheduling decision fitting evaluation score sequence does not meet the energy scheduling constraint rules, it means that the decision does not meet the expected standards in some aspects. Perform multiple rounds of random mutation on the original shared energy storage scheduling decision, and introduce some random changes in the decision in the hope of producing better results. In this way, a scheduling decision variation space containing multiple mutated energy storage scheduling decisions can be generated. Select a mutated energy storage scheduling decision from the scheduling decision variation space, which is called the first mutated energy storage scheduling decision. Use the constructed energy scheduling simulation module and energy scheduling evaluation module to fit the energy scheduling evaluation of the first mutated energy storage scheduling decision. This will generate a first mutated decision fitting scheduling evaluation score sequence, which reflects the performance of the mutated decision in various evaluation indicators. Compare the first mutated decision fitting scheduling evaluation score sequence with the energy scheduling constraint rules. If the first mutated decision fitting scheduling evaluation score sequence meets the energy scheduling constraint rules, it means that this mutated energy storage scheduling decision has met the expected standards. At this time, add this first mutated energy storage scheduling decision to the shared energy storage scheduling scheme. If the first mutated decision fitting scheduling evaluation score sequence still does not meet the energy scheduling constraint rules, it means that further optimization is needed. At this time, the energy dispatch constraint rules are used as the optimization target, and the energy dispatch simulation module and the energy dispatch evaluation module are combined to iteratively optimize the scheduling decision variation space. During the iteration process, multiple variation decisions that meet the constraint rules may be generated, and these decisions will be added to the shared energy storage scheduling plan.

[0035] In summary, the optimized energy scheduling method for centralized shared energy storage provided by this application has the following technical effects: Through the real-time monitoring module of the interactive power system, a power system monitoring data set is obtained; according to the power system monitoring data set, the energy scheduling target characteristics of the centralized shared energy storage system are fitted to construct a predicted shared energy storage scheduling scenario; the Internet of Things monitoring module of the centralized shared energy storage system is connected to obtain multiple energy storage unit monitoring data sets; based on the multiple energy storage unit monitoring data sets, the energy scheduling decision of the centralized shared energy storage system is aligned according to the predicted shared energy storage scheduling scenario, and the shared energy storage scheduling decision is determined; according to the energy scheduling constraint rules, the shared energy storage scheduling decision is fitted, corrected and optimized, and a shared energy storage scheduling plan is output; according to the shared energy storage scheduling plan, the centralized shared energy storage system is energy scheduled, which effectively solves the technical problems of untimely data collection, insufficient data processing capability and insufficiently advanced scheduling decision methods in the prior art, resulting in inaccurate power system status monitoring, further affecting the efficiency of energy scheduling and the stable operation of the power system, and effectively scheduling the centralized shared energy storage system according to the shared energy storage scheduling plan is helpful to improve the stability of the power system.

[0036] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0037] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An optimized energy dispatching method for centralized shared energy storage, characterized in that: The method comprises: Interactive power system real-time monitoring module to obtain power system monitoring data set; Fitting energy dispatch target characteristics of the centralized shared energy storage system according to the power system monitoring data set to construct a predicted shared energy storage dispatch scenario; Connecting to the Internet of Things monitoring module of the centralized shared energy storage system to obtain multiple energy storage unit monitoring data sets; Based on the multiple energy storage unit monitoring data sets, the centralized shared energy storage system is aligned with energy scheduling decisions according to the predicted shared energy storage scheduling scenario to determine a shared energy storage scheduling decision; According to the energy dispatch constraint rules, the shared energy storage dispatch decision is fitted, corrected and optimized, and a shared energy storage dispatch plan is output; Energy scheduling is performed on the centralized shared energy storage system according to the shared energy storage scheduling plan.

2. The method according to claim 1, characterized in that According to the power system monitoring data set, the energy dispatch target characteristics of the centralized shared energy storage system are fitted to construct a predicted shared energy storage dispatch scenario, including: Dynamically fitting the power system monitoring data set based on a preset future time zone window to obtain a predicted power dynamic data set; Performing a dynamic change comparison based on the power system monitoring data set and the predicted power dynamic data set, and outputting a fitted power dynamic change comparison result; Inputting the fitted power dynamic change comparison result into a pre-built energy dispatch target fitting module to obtain a plurality of predicted energy storage dispatch target characteristic data; Data fusion is performed based on the multiple predicted energy storage scheduling target characteristic data to generate the predicted shared energy storage scheduling scenario.

3. The method according to claim 2, characterized in that The method comprises: Performing joint record backtracking on the power system and the centralized shared energy storage system to obtain a plurality of energy dispatch target analysis record sets, each of which includes a power dynamic change comparison record set and an energy storage dispatch target characteristic data record set; Performing supervised training on the multiple energy scheduling target analysis record sets respectively to construct multiple energy scheduling target feature prediction channels that meet energy scheduling target prediction accuracy constraints; The multiple energy scheduling target feature prediction channels are used as multiple parallel prediction nodes, and the multiple parallel prediction nodes are merged to generate the energy scheduling target fitting module.

4. The method according to claim 1, characterized in that Based on the multiple energy storage unit monitoring data sets, the centralized shared energy storage system is aligned with energy scheduling decisions according to the predicted shared energy storage scheduling scenario to determine a shared energy storage scheduling decision, including: Collecting energy dispatch records according to the centralized shared energy storage system to obtain a shared energy dispatch record set; Performing energy scheduling solution registration on the shared energy scheduling record set according to the multiple energy storage unit monitoring data sets and the predicted shared energy storage scheduling scenario to obtain a registered energy scheduling solution space; Performing scheduling solution confidence calculation according to the registered energy scheduling solution space to obtain a plurality of registered scheduling solution confidence coefficients; Arranging the registered energy scheduling solution space in descending order according to the multiple registered scheduling solution confidence coefficients to obtain a preferred registered energy scheduling solution set that satisfies a predetermined sequence constraint; Scheduling solutions are fused according to the preferred aligned energy scheduling solution set to generate the shared energy storage scheduling decision.

5. The method according to claim 4, characterized in that According to the plurality of energy storage unit monitoring data sets and the predicted shared energy storage scheduling scenario, the shared energy scheduling record set is subjected to energy scheduling solution alignment to obtain an aligned energy scheduling solution space, including: Extracting a first shared energy scheduling record group according to the shared energy scheduling record set, wherein the first shared energy scheduling record group includes monitoring record samples of each energy storage unit, shared energy storage scheduling scenario record samples, and energy scheduling solution record samples; According to the plurality of energy storage unit monitoring data sets, corresponding similarity identification is performed on the monitoring record samples of each energy storage unit to determine a similarity coefficient of the state of the sample energy storage unit; Performing similarity identification on the shared energy storage scheduling scenario record samples according to the predicted shared energy storage scheduling scenario, and determining a sample scheduling scenario similarity coefficient; Perform weighted fusion according to the sample energy storage unit state similarity coefficient and the sample scheduling scenario similarity coefficient to generate a sample energy scheduling feature registration coefficient; If the sample energy scheduling feature registration coefficients satisfy the energy scheduling feature registration constraints, the energy scheduling solution record samples are added to the registered energy scheduling solution space.

6. The method according to claim 1, characterized in that According to the energy dispatch constraint rules, the shared energy storage dispatch decision is fitted, corrected and optimized, and a shared energy storage dispatch plan is output, including: Activate the energy scheduling simulation module, and perform energy scheduling fitting on the centralized shared energy storage system in combination with the shared energy storage scheduling decision to obtain a decision fitting scheduling job data set; Perform energy scheduling evaluation according to the decision fitting scheduling job data set, and construct a decision fitting scheduling evaluation score sequence; Determining whether the decision fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule, wherein the energy scheduling constraint rule includes a predetermined scheduling evaluation interval sequence; If the decision-fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule, the shared energy storage scheduling decision is added to the shared energy storage scheduling plan.

7. The method according to claim 6, characterized in that Energy scheduling evaluation is performed according to the decision fitting scheduling job data set, and a decision fitting scheduling evaluation score sequence is constructed, including: Constructing an energy scheduling evaluation module, wherein the energy scheduling evaluation module includes a multidimensional energy scheduling evaluation channel, and the multidimensional energy scheduling evaluation channel includes an energy utilization efficiency evaluation channel, a scheduling target achievement rate evaluation channel, a scheduling operation efficiency evaluation channel, and a scheduling safety evaluation channel; The decision fitting scheduling job data set is input into the energy scheduling evaluation module to obtain the decision fitting scheduling evaluation score sequence, wherein the decision fitting scheduling evaluation score sequence includes an energy utilization efficiency evaluation score, a scheduling target achievement rate evaluation score, a scheduling job efficiency evaluation score and a scheduling safety evaluation score.

8. The method according to claim 7, characterized in that Determining whether the decision fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule includes: If the decision-fitting scheduling evaluation score sequence does not satisfy the energy scheduling constraint rule, multiple rounds of random mutation are performed according to the shared energy storage scheduling decision to obtain a scheduling decision mutation space; Extracting a first variable energy storage scheduling decision according to the scheduling decision variation space; Performing a fitting energy scheduling evaluation on the first variant energy storage scheduling decision according to the energy scheduling simulation module and the energy scheduling evaluation module to generate a first variant decision fitting scheduling evaluation score sequence; Determining whether the first variation decision fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule; If the first variant decision fitting scheduling evaluation score sequence satisfies the energy scheduling constraint rule, adding the first variant energy storage scheduling decision to the shared energy storage scheduling plan; If the first variation decision fitting scheduling evaluation score sequence does not satisfy the energy scheduling constraint rule, the energy scheduling constraint rule is used as the optimization target, and the scheduling decision variation space is iteratively optimized in combination with the energy scheduling simulation module and the energy scheduling evaluation module to generate the shared energy storage scheduling plan.

Images