Multi-source energy storage power grid dispatching cooperation method, device and equipment and storage medium

Abstract

The invention discloses a multi-source energy storage power grid dispatching cooperation method, device and equipment and a storage medium, and belongs to the field of power systems, and the method comprises the steps: collecting multi-source state data in each energy storage unit in real time; obtaining the maximum available capacity of each energy storage unit at the current moment according to the preset initial maximum capacity of each energy storage unit and the multi-source state data; obtaining a battery health parameter of each energy storage unit according to the maximum available capacity; calculating target charging and discharging power of each energy storage unit according to the maximum available capacity and the battery health parameters; and dynamically distributing the target charging and discharging power of each energy storage unit, and performing regulation and control. Therefore, by implementing the method, the problems that in the prior art, deep fusion of a power grid dispatching system still faces insufficient safety, cooperative dispatching and intelligent level, and power grid frequency and voltage composite fluctuation caused by multi-source and cross-scale random disturbance cannot be processed when high-proportion renewable energy source access is coped can be solved.

Description

Technical Field

[0001] This invention relates to the field of power systems, and in particular to a multi-source energy storage grid dispatching and coordination method, apparatus, equipment and storage medium. Background Technology

[0002] As the global energy structure accelerates its transition to renewable energy, improving the flexibility and dispatch capabilities of power grids has become a core issue in energy management. Due to the volatility and intermittency of renewable energy sources such as wind and solar power, power systems face significant challenges in real-time balancing, dispatch optimization, and stability assurance.

[0003] While existing technologies combining energy storage and grid dispatch have improved the flexibility and stability of grid operation to some extent, large-scale promotion and in-depth application have revealed risks of thermal runaway and overload for some energy storage units during high-power grid-connected operation, requiring additional protection measures during grid dispatch. Furthermore, the grid connection of multiple types of energy storage units may trigger power quality fluctuations, posing a challenge to system stability. Moreover, the unified dispatch and optimization of multi-level, multi-source, heterogeneous energy storage resources remains a weakness of existing dispatch systems. Current technologies are still insufficient in cross-regional and cross-timescale coordination optimization and fault self-healing capabilities. Although some degree of automation and intelligent management has been achieved, most dispatch systems still rely on rule bases and empirical models, making it difficult to cope with dynamic optimization under complex operating conditions. Power load forecasting, scenario simulation, and adaptive dispatch based on artificial intelligence and large-scale models are still in the exploratory stage and have not yet achieved engineering-scale applications. Summary of the Invention

[0004] This invention provides a multi-source energy storage grid dispatch coordination method, device, equipment, and storage medium, which can solve the technical problems of insufficient security, coordinated dispatch, and intelligence level in the deep integration of existing grid dispatch systems, and the inability to handle the composite fluctuations of grid frequency and voltage caused by multi-source, cross-scale random disturbances when a high proportion of renewable energy is connected.

[0005] This invention provides a multi-source energy storage grid dispatch and coordination method, comprising: Real-time acquisition of multi-source status data within each energy storage unit; The preset initial maximum capacity of each energy storage unit and the multi-source state data are input into the preset battery current capacity prediction model, and the maximum available capacity of each energy storage unit at the current moment is output. Based on the maximum available capacity and combined with the energy storage health prediction model, the battery health parameters of each energy storage unit are output. Calculate the target charge / discharge power of each energy storage unit based on the maximum available capacity and the battery health parameters; The target charging and discharging power of each energy storage unit is dynamically allocated and regulated, and fault diagnosis and monitoring are continuously performed based on the multi-source status data of each energy storage unit collected during the regulation process.

[0006] As a preferred embodiment, the step of inputting the preset initial maximum capacity of each energy storage unit and the multi-source state data into a preset battery current capacity prediction model, and outputting the maximum available capacity of each energy storage unit at the current moment, includes: Based on the multi-source state data of each energy storage unit, the first fitting parameter between the battery material and the operating state of each energy storage unit and the second fitting parameter between the depth of charge and discharge and the capacity loss are determined. Based on the first fitting parameters and the second fitting parameters, combined with the preset initial maximum capacity of each energy storage unit, the data is input into the preset battery current capacity prediction model to obtain the capacity decay value of each energy storage unit at the current moment. Based on the capacity decay value, the maximum available capacity of each energy storage unit at the current moment is calculated.

[0007] As a preferred embodiment, the step of determining a first fitting parameter between the battery material and the operating condition for each energy storage unit, and a second fitting parameter between the depth of charge / discharge and capacity loss, based on multi-source state data of each energy storage unit, includes: The multi-source state data of each energy storage unit is input into the deep learning model, and the first fitting parameter between the battery material and the operating state corresponding to each energy storage unit and the second fitting parameter between the charge and discharge depth and the capacity loss are output. The multi-source state data includes: battery material characteristics, current operating conditions, current throughput capacity, and number of cycles.

[0008] As a preferred embodiment, the method for constructing the deep learning model includes: Historical multi-source state data of energy storage units are acquired, and historical digital twin models of each energy storage unit are constructed based on the historical multi-source state data. Based on the historical digital twin model, the historical first fitting parameter between the battery material and the operating condition corresponding to each energy storage unit, and the historical second fitting parameter between the depth of charge and discharge and the capacity loss are determined. Build the initial deep learning model; Using the historical multi-source state data as input and the historical first fitting parameters and the historical second fitting parameters as output, the initial deep learning model is iteratively trained to obtain the trained deep learning model.

[0009] As a preferred embodiment, calculating the target charge / discharge power of each energy storage unit based on the maximum available capacity and the battery health parameters specifically includes: Based on the maximum available capacity and the battery health parameters, determine the revenue weight, over-temperature and over-current weight, and lifetime weight; Based on the aforementioned revenue weight, over-temperature and over-current weight, and lifetime weight, the target power function for charging and discharging of each energy storage unit is calculated. The target charge and discharge power of each energy storage unit is calculated based on the target charge and discharge power function.

[0010] As a preferred embodiment, before dynamically allocating and regulating the target charge / discharge power of each energy storage unit, the method further includes: The internal temperature and internal resistance of each energy storage unit are monitored in real time, and the target charging and discharging power adjustment of each energy storage unit is simulated. During the simulation, the temperature rise and voltage drop of each energy storage unit are determined based on the real-time monitored internal temperature and internal resistance of each energy storage unit. Energy storage units whose temperature rise exceeds the preset temperature rise threshold or whose internal voltage is lower than the cutoff voltage are extracted as energy storage units to be corrected. The target charge and discharge power of the energy storage unit to be corrected is derated, and the simulation is repeated until the temperature rise of the energy storage unit does not exceed the preset temperature rise threshold and the internal voltage of the energy storage unit is not lower than the cutoff voltage during the simulation.

[0011] Accordingly, the present invention also provides a multi-source energy storage grid dispatching and coordination device, comprising: a data acquisition module, a capacity module, a health parameter module, a charging and discharging module, and a control module; The acquisition module is used to acquire multi-source status data inside each energy storage unit in real time; The capacity module is used to input the preset initial maximum capacity of each energy storage unit and the multi-source state data into the preset battery current capacity prediction model, and output the maximum available capacity of each energy storage unit at the current moment. The health parameter module is used to output the battery health parameters of each energy storage unit based on the maximum available capacity and in conjunction with the energy storage health prediction model. The charging and discharging module is used to calculate the target charging and discharging power of each energy storage unit based on the maximum available capacity and the battery health parameters. The control module is used to dynamically allocate and control the target charging and discharging power of each energy storage unit, and to continuously perform fault diagnosis and monitoring based on the multi-source status data of each energy storage unit collected during the control process.

[0012] As a preferred option, it also includes: a simulation module; The simulation module is used to monitor the internal temperature and internal resistance of each energy storage unit in real time, and to simulate the target charge and discharge power adjustment of each energy storage unit. During the simulation, based on the real-time monitored internal temperature and internal resistance of each energy storage unit, the temperature rise and voltage drop of each energy storage unit are determined, and energy storage units whose temperature rise exceeds a preset temperature rise threshold or whose internal voltage is lower than the cutoff voltage are extracted as energy storage units to be corrected. The target charge and discharge power of the energy storage units to be corrected is derated, and the simulation is repeated until the temperature rise of the energy storage unit does not exceed the preset temperature rise threshold and the internal voltage of the energy storage unit is not lower than the cutoff voltage during the simulation.

[0013] Another embodiment of the present invention provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps of the multi-source energy storage grid dispatch coordination method provided by the present invention.

[0014] Another embodiment of the present invention provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform the steps of the multi-source energy storage grid dispatch coordination method provided by the present invention.

[0015] The following benefits can be obtained by implementing the present invention: This invention acquires multi-source state data from each energy storage unit, and then calculates the maximum available capacity of each energy storage unit at the current moment by combining it with a preset battery current capacity prediction model. It also calculates the battery health parameters of each energy storage unit by combining it with an energy storage health prediction model. This enables real-time estimation and lifetime prediction of the System-on-Chips (SoC) and System-on-H (SOH) of the energy storage units and the system. Furthermore, it calculates the target charge / discharge power of each energy storage unit and dynamically allocates and regulates the target charge / discharge power of each unit. Thus, under high-proportion renewable energy access, it can collect and process multi-source data from each energy storage unit. Even when faced with combined fluctuations in grid frequency and voltage caused by multi-source, cross-scale random disturbances, it can still stably regulate the energy storage units without being affected by other units, improving the stability of multi-level grid dispatch and increasing the efficiency of coordinated multi-energy storage unit regulation. Attached Figure Description

[0016] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1This is a flowchart illustrating a multi-source energy storage grid scheduling and coordination method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a multi-source energy storage grid dispatching and coordination device provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0020] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0023] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0024] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0025] See Figure 1 To address the shortcomings in security, collaborative scheduling, and intelligence levels in the deep integration of existing power grid dispatching systems, and to cope with the technical problem of handling composite fluctuations in power grid frequency and voltage caused by multi-source, cross-scale random disturbances under high-proportion renewable energy access, an embodiment of the present invention provides a multi-source energy storage power grid dispatching collaborative method, including steps S101-S106: S101: Real-time acquisition of multi-source status data within each energy storage unit.

[0026] In this embodiment, each energy storage unit is connected to the system through a standardized interface, and the intelligent BMS collects core operating parameters in real time to form a dataset of multi-source status data: Where n is the amount of data in the dataset, and i is the current time step i.

[0027] The dataset includes dimensions such as energy storage unit status data, dynamic characteristic data, frequency-related data, voltage-related data, and power-related data. Core status data includes: State of Charge (SoC), State of Health (SoH), internal temperature (T), terminal voltage (V), and charging / discharging current (I). Dynamic characteristic data includes: internal resistance (estimated through real-time disturbance response), cycle count, and cumulative throughput. Frequency-related data includes: system frequency at the grid connection point and rate of change of frequency (RoCoF). Voltage-related data includes: bus voltage at the grid connection point, three-phase imbalance, and harmonic content. Power-related data includes: active / reactive power flow at the grid connection point and line load factor.

[0028] Furthermore, the multi-source state data also includes: disturbance source prediction data (ultra-short-term prediction), namely, renewable energy: wind speed and solar intensity prediction data for the next 15 minutes to 1 hour, which are converted into power prediction curves, and load prediction curves for key industrial users / charging station clusters on the load side. In addition, it also includes external environment and market data, namely ambient temperature (affecting the efficiency and lifespan of energy storage units), real-time electricity prices, and ancillary service (such as frequency regulation) price signals.

[0029] S102: Input the preset initial maximum capacity of each energy storage unit and the multi-source state data into the preset battery current capacity prediction model, and output the maximum available capacity of each energy storage unit at the current moment.

[0030] As a preferred embodiment, the step of inputting the preset initial maximum capacity of each energy storage unit and the multi-source state data into a preset battery current capacity prediction model, and outputting the maximum available capacity of each energy storage unit at the current moment, includes: Based on the multi-source state data of each energy storage unit, the first fitting parameter between the battery material and the operating state of each energy storage unit and the second fitting parameter between the depth of charge and discharge and the capacity loss are determined. Based on the first fitting parameters and the second fitting parameters, combined with the preset initial maximum capacity of each energy storage unit, the data is input into the preset battery current capacity prediction model to obtain the capacity decay value of each energy storage unit at the current moment. Based on the capacity decay value, the maximum available capacity of each energy storage unit at the current moment is calculated.

[0031] In this embodiment, battery materials and operating conditions are used to describe the capacity loss caused by cycle aging: ; Where n is the number of cycles, and A and α are the first fitting parameters related to the battery material and operating conditions.

[0032] Depth of charge / discharge (DoD) affects capacity loss, describing the impact of DoD on capacity. Where B and β are the corresponding second fitting parameters.

[0033] In this embodiment, the preset battery current capacity prediction model is: in, This is the preset initial maximum capacity of the battery when it leaves the factory. This represents the capacity decay value.

[0034] Furthermore, using this capacity decay value and the preset initial maximum capacity of the energy storage unit, the current maximum available capacity of the energy storage unit can be calculated.

[0035] As a preferred embodiment, the step of determining a first fitting parameter between the battery material and the operating condition for each energy storage unit, and a second fitting parameter between the depth of charge / discharge and capacity loss, based on multi-source state data of each energy storage unit, includes: The multi-source state data of each energy storage unit is input into the deep learning model, and the first fitting parameter between the battery material and the operating state corresponding to each energy storage unit and the second fitting parameter between the charge and discharge depth and the capacity loss are output. The multi-source state data includes: battery material characteristics, current operating conditions, current throughput capacity, and number of cycles.

[0036] As a preferred embodiment, the method for constructing the deep learning model includes: Historical multi-source state data of energy storage units are acquired, and historical digital twin models of each energy storage unit are constructed based on the historical multi-source state data. Based on the historical digital twin model, the historical first fitting parameter between the battery material and the operating condition corresponding to each energy storage unit, and the historical second fitting parameter between the depth of charge and discharge and the capacity loss are determined. Build the initial deep learning model; Using the historical multi-source state data as input and the historical first fitting parameters and the historical second fitting parameters as output, the initial deep learning model is iteratively trained to obtain the trained deep learning model.

[0037] In this embodiment, based on historical and real-time monitoring data, a deep learning model (such as LSTM or Transformer) combined with a physical model is used to predict the health status parameters of the energy storage unit. Traditional methods require offline complete charge-discharge tests to obtain E_max(t), while this embodiment utilizes the aforementioned multi-source state data and analyzes the minute changes in voltage, current, temperature, and other characteristics during the charge-discharge process using a deep learning model (such as LSTM). It estimates and identifies the fitting parameters in real-time and online, and then determines E_max(t) by determining the attenuation capacity, thereby achieving dynamic and accurate evaluation of the SoH (Solar H).

[0038] In this embodiment, historical multi-source state data of the energy storage unit is acquired, and an electrochemical model of the battery, such as an equivalent circuit model (ECM) or an electrochemical model (such as a P2D model), is constructed based on the physicochemical principles of the battery. Using historical data, a data-driven model is constructed through machine learning or statistical methods, thus combining the physical model and the data-driven model to form a hybrid model, thereby improving the model's accuracy and generalization ability. Furthermore, regression analysis (such as least squares) or machine learning methods (such as random forests or neural networks) are used to fit the historical data, determining the fitting parameters. The accuracy of the fitting parameters is evaluated through residual analysis, cross-validation, and other methods, and the fitting parameters are continuously updated based on new data to improve the model's adaptability and accuracy. This determines the first fitting parameter between the battery material and the operating condition, and the second fitting parameter between the depth of charge / discharge and capacity loss. Historical multi-source state data is divided into training, validation, and test sets. A model architecture is built using a deep learning framework (such as TensorFlow or PyTorch), model parameters are randomly initialized, and hyperparameters such as learning rate and batch size are set. The input data is determined to be historical multi-source state data, and the output data are the first and second historical fitting parameters. Then, the model is trained using the training, validation, and test sets, i.e., the model is trained using the input data so that the model can predict the output parameters. The prediction accuracy of the model is evaluated using metrics such as mean squared error (MSE) and mean absolute error (MAE).

[0039] S103: Based on the maximum available capacity and combined with the energy storage health prediction model, output the battery health parameters of each energy storage unit.

[0040] In this embodiment, the energy storage health prediction model is as follows: Where E_max(t) is the maximum usable capacity of the battery at the current moment, and E_max,init is the initial maximum capacity of the battery when it was manufactured. These are the battery health parameters for the energy storage unit.

[0041] S104: Calculate the target charge / discharge power of each energy storage unit based on the maximum available capacity and the battery health parameters.

[0042] As a preferred embodiment, calculating the target charge / discharge power of each energy storage unit based on the maximum available capacity and the battery health parameters specifically includes: Based on the maximum available capacity and the battery health parameters, determine the revenue weight, over-temperature and over-current weight, and lifetime weight; Based on the aforementioned revenue weight, over-temperature and over-current weight, and lifetime weight, the target power function for charging and discharging of each energy storage unit is calculated. The target charge and discharge power of each energy storage unit is calculated based on the target charge and discharge power function.

[0043] In this embodiment, the intelligent dispatch system dynamically allocates charging and discharging power based on predicted SoC, SoH, external load, market electricity prices, and renewable energy fluctuations. The objectives, such as revenue, over-temperature and over-current, and lifetime, can be flexibly adjusted through multi-objective optimization weights (revenue weight, over-temperature and over-current weight, and lifetime weight). This formula is a multi-objective optimization function constructed by the present invention to solve a specific scheduling problem. Its form is the standard weighted summation form in optimization theory.

[0044] It is important to explain the meaning of the objective function and the dynamic adaptive adjustment mechanism of the weights λ. The objective function is defined as follows: it quantifies three dimensions—"benefits" (e.g., peak shaving and valley filling benefits), "over-temperature and over-current" (e.g., avoiding over-temperature and over-current risks), and "lifespan" (e.g., reducing battery wear)—and constructs them into a unified optimization objective. The weights are dynamically adjusted using AI-driven mechanisms. In this embodiment, the weights λ1, λ2, and λ3 are not fixed but dynamically adjusted by a reinforcement learning agent based on real-time grid conditions (e.g., the severity of frequency fluctuations) and energy storage health status (SoH prediction). For example, when severe grid frequency fluctuations are detected, the agent will significantly increase λ2 (safety weight) to prioritize grid stability, even at the cost of some economic efficiency; when the battery SoH is low, the agent will increase λ3 (lifespan weight) to adopt a smoother charging and discharging strategy to extend its lifespan. The specific adjustment logic can be set manually.

[0045] S105: Dynamically allocate and regulate the target charging and discharging power of each energy storage unit, and continuously perform fault diagnosis and monitoring based on the multi-source status data of each energy storage unit collected during regulation.

[0046] As a preferred embodiment, before dynamically allocating and regulating the target charging and discharging power of each energy storage unit, step S106 is further included: S106: Monitor the internal temperature and internal resistance of each energy storage unit in real time, and simulate the target charge and discharge power adjustment for each energy storage unit; during the simulation, determine the temperature rise and voltage drop of each energy storage unit based on the real-time monitored internal temperature and internal resistance, and extract the energy storage units whose temperature rise exceeds the preset temperature rise threshold or whose internal voltage is lower than the cutoff voltage as the energy storage units to be corrected; reduce the target charge and discharge power of the energy storage units to be corrected, and re-simulate until the temperature rise of the energy storage unit does not exceed the preset temperature rise threshold and the internal voltage of the energy storage unit is not lower than the cutoff voltage during the simulation.

[0047] In this embodiment, for a single energy storage unit, its internal temperature T_cell and internal resistance R_in are monitored in real time, and the target charge / discharge power P_cmd in the scheduling command is received. Before executing P_cmd, the model performs a rapid simulation (millisecond level) to predict the temperature rise ΔT_pred and voltage drop ΔV_pred that may result from executing the command within the next 1-5 seconds. If the model predicts that T_cell + ΔT_pred will exceed the safety threshold (preferably 55°C), or V_cell - ΔV_pred will fall below the cutoff voltage, the system will proactively derating the target charge / discharge power P_cmd to limit it within the safety boundary before issuing the control order for the target charge / discharge power.

[0048] Furthermore, cluster-level collaborative safety control can be achieved by monitoring the SoH, temperature, and current distribution of all units within an energy storage cluster (composed of multiple units connected in series and parallel). Employing a consensus-based equalization control strategy, the system calculates the health status and temperature differences of each unit within the cluster in real time. When a unit (such as cell_i) is found to have a slightly faulty or aged condition leading to a temperature increase or a decrease in SoH, the system does not simply disconnect it. Instead, it dynamically reduces the current share borne by the cell by adjusting the active equalization circuit of the branch containing that cell, and smoothly transfers this current to other healthy units within the cluster. Simultaneously, the thermal management system is activated to precisely cool cell_i at a specific point, ensuring stable output power for the entire cluster while preventing the deterioration and spread of the fault.

[0049] Furthermore, by monitoring voltage and current fluctuations and high-frequency transient signals at the grid connection point of the system through a high-speed synchronous phasor measurement unit (PMU), when the system detects transient characteristics indicating serious faults such as internal short circuits (e.g., a sharp increase in high-frequency components), protection is immediately triggered, including: physically isolating the faulty energy storage cluster or branch from the main circuit through a solid-state circuit breaker (SSC) within 50 milliseconds; at the same time, the cloud-based dispatch platform immediately senses the decrease in available capacity, and the AI ​​dispatch model recalculates the optimal power allocation scheme within seconds, instructing the remaining healthy energy storage units to take on part or all of the power shortfall, minimizing the impact on the power grid and achieving system fault self-healing.

[0050] In this embodiment, the introduction of blockchain and smart contracts for multi-source energy storage ensures the transparency and traceability of energy flow and transaction data. In scenarios requiring the suppression of multi-source random disturbances, it is often necessary to aggregate a large number of energy storage resources belonging to different entities (such as power grid companies, third-party operators, and individual users) to participate together. In this case, the role of blockchain and smart contracts is particularly crucial. For example, the power grid dispatch center issues a frequency regulation task to address the rapid frequency drop caused by photovoltaic cloud shading. Multiple energy storage aggregators respond and organize their distributed energy storage resources to provide support.

[0051] In this embodiment, the response data of each participating energy storage unit—including "response time (UTC timestamp)," "response power (kW)," "duration (ms)," and "grid connection point frequency data"—is encrypted, signed, packaged into a transaction, and broadcast to the consortium blockchain jointly maintained by the power grid and various aggregators. Once the data is on the blockchain and reaches consensus, it cannot be tampered with. The power grid dispatch center, aggregators, and even end users can trace and verify the actual contribution of any energy storage unit at any time, solving the problems of data tampering and unclear responsibility identification in traditional centralized systems. Based on the automated and transparent settlement of smart contracts, a smart contract can be deployed on the blockchain before the frequency regulation task is issued. The contract clearly defines the settlement rules, which can be set manually according to needs. When an energy storage unit completes a frequency regulation support, its on-chain contribution data automatically triggers the smart contract's settle function. The contract automatically calculates compensation according to preset rules and completes the transfer of value (such as digital tokens or settlement vouchers).

[0052] Furthermore, all operational data, forecast results, and scheduling strategies are synchronized to the cloud platform, enabling visualized operation and maintenance, remote decision-making, and large-scale data analysis support, thereby enhancing the system's intelligence and adaptability.

[0053] This invention also provides a multi-scale (from distributed unit to grid level) multi-source energy storage and grid dispatching collaborative system and method, which is highly modular, intelligent, safe, and economical, and can achieve efficient energy dispatching, health management, and system adaptive optimization in multiple scenarios. The overall architecture includes the following core modules: The multi-source heterogeneous energy storage access unit is used to support the unified access of multiple types of energy storage resources (distributed battery units, secondary utilization energy storage modules, fluid energy storage devices, etc.). It adopts a modular interface design for easy expansion and replacement.

[0054] The Intelligent Monitoring and Health Management System (iBMS) is used to collect parameters such as SoC (State of Charge), SoH (State of Health), temperature, voltage, and current in real time from the connected energy storage units, build a complete operating dataset, and combine deep learning algorithms for dynamic prediction and anomaly identification.

[0055] This multi-level energy dispatch and optimization platform is designed for various scenarios, including residential, commercial, industrial, and regional power grids, supporting flexible energy dispatch and optimization. The platform can be integrated with business models such as Virtual Power Plants (VPPs), Energy Storage as a Service (ESaaS), and energy sharing platforms to create multi-party collaboration and market interaction capabilities.

[0056] The safety and environmental protection unit is used to build a multi-level active safety mechanism to realize functions such as thermal management, overload protection, anomaly detection, and automatic isolation, ensuring the safety and stability of the system under highly fluctuating operating conditions.

[0057] The cloud-based data and collaborative operation and maintenance platform is used to interconnect with the cloud platform through the Internet of Things to realize the collection of operational data, global scheduling and decision-making, visualization and remote maintenance, thereby improving the system's intelligent operation and maintenance level and data-driven capabilities.

[0058] like Figure 2 As shown, based on the above method embodiments, corresponding apparatus embodiments are provided; One embodiment of the present invention provides a multi-source energy storage grid dispatching and coordination device, including: a data acquisition module 201, a capacity module 202, a health parameter module 203, a charging and discharging module 204, and a control module 205; The acquisition module 201 is used to acquire multi-source status data inside each energy storage unit in real time. The capacity module 202 is used to input the preset initial maximum capacity of each energy storage unit and the multi-source state data into the preset battery current capacity prediction model, and output the maximum available capacity of each energy storage unit at the current moment. The health parameter module 203 is used to output the battery health parameters of each energy storage unit based on the maximum available capacity and in conjunction with the energy storage health prediction model. The charging and discharging module 204 is used to calculate the target charging and discharging power of each energy storage unit based on the maximum available capacity and the battery health parameters. The control module 205 is used to dynamically allocate and control the target charging and discharging power of each energy storage unit, and to continuously perform fault diagnosis and monitoring based on the multi-source status data of each energy storage unit collected during the control process.

[0059] As a preferred option, it also includes: simulation module 206; The simulation module 206 is used to monitor the internal temperature and internal resistance of each energy storage unit in real time, and to simulate the target charge and discharge power adjustment of each energy storage unit. During the simulation, based on the real-time monitored internal temperature and internal resistance of each energy storage unit, the temperature rise and voltage drop of each energy storage unit are determined, and energy storage units whose temperature rise exceeds a preset temperature rise threshold or whose internal voltage is lower than the cutoff voltage are extracted as energy storage units to be corrected. The target charge and discharge power of the energy storage units to be corrected is derated, and the simulation is repeated until the temperature rise of the energy storage unit does not exceed the preset temperature rise threshold and the internal voltage of the energy storage unit is not lower than the cutoff voltage during the simulation.

[0060] As a preferred embodiment, the step of inputting the preset initial maximum capacity of each energy storage unit and the multi-source state data into a preset battery current capacity prediction model, and outputting the maximum available capacity of each energy storage unit at the current moment, includes: Based on the multi-source state data of each energy storage unit, the first fitting parameter between the battery material and the operating state of each energy storage unit and the second fitting parameter between the depth of charge and discharge and the capacity loss are determined. Based on the first fitting parameters and the second fitting parameters, combined with the preset initial maximum capacity of each energy storage unit, the data is input into the preset battery current capacity prediction model to obtain the capacity decay value of each energy storage unit at the current moment. Based on the capacity decay value, the maximum available capacity of each energy storage unit at the current moment is calculated.

[0061] As a preferred embodiment, the step of determining a first fitting parameter between the battery material and the operating condition for each energy storage unit, and a second fitting parameter between the depth of charge / discharge and capacity loss, based on multi-source state data of each energy storage unit, includes: The multi-source state data of each energy storage unit is input into the deep learning model, and the first fitting parameter between the battery material and the operating state corresponding to each energy storage unit and the second fitting parameter between the charge and discharge depth and the capacity loss are output. The multi-source state data includes: battery material characteristics, current operating conditions, current throughput capacity, and number of cycles.

[0062] As a preferred embodiment, the method for constructing the deep learning model includes: Historical multi-source state data of energy storage units are acquired, and historical digital twin models of each energy storage unit are constructed based on the historical multi-source state data. Based on the historical digital twin model, the historical first fitting parameter between the battery material and the operating condition corresponding to each energy storage unit, and the historical second fitting parameter between the depth of charge and discharge and the capacity loss are determined. Build the initial deep learning model; Using the historical multi-source state data as input and the historical first fitting parameters and the historical second fitting parameters as output, the initial deep learning model is iteratively trained to obtain the trained deep learning model.

[0063] As a preferred embodiment, calculating the target charge / discharge power of each energy storage unit based on the maximum available capacity and the battery health parameters specifically includes: Based on the maximum available capacity and the battery health parameters, determine the revenue weight, over-temperature and over-current weight, and lifetime weight; Based on the aforementioned revenue weight, over-temperature and over-current weight, and lifetime weight, the target power function for charging and discharging of each energy storage unit is calculated. The target charge and discharge power of each energy storage unit is calculated based on the target charge and discharge power function.

[0064] As a preferred embodiment, before dynamically allocating and regulating the target charge / discharge power of each energy storage unit, the method further includes: The internal temperature and internal resistance of each energy storage unit are monitored in real time, and the target charging and discharging power adjustment of each energy storage unit is simulated. During the simulation, the temperature rise and voltage drop of each energy storage unit are determined based on the real-time monitored internal temperature and internal resistance of each energy storage unit. Energy storage units whose temperature rise exceeds the preset temperature rise threshold or whose internal voltage is lower than the cutoff voltage are extracted as energy storage units to be corrected. The target charge and discharge power of the energy storage unit to be corrected is derated, and the simulation is repeated until the temperature rise of the energy storage unit does not exceed the preset temperature rise threshold and the internal voltage of the energy storage unit is not lower than the cutoff voltage during the simulation.

[0065] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can realize the multi-source energy storage grid dispatch and coordination method provided by any of the above-described method embodiments of the present invention.

[0066] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0067] Based on the above embodiments of the multi-source energy storage grid dispatch coordination method, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the multi-source energy storage grid dispatch coordination method of any embodiment of the present invention.

[0068] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0069] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0070] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0071] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the multi-source energy storage grid dispatch coordination method described in any of the above-described method embodiments of the present invention.

[0072] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0073] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A multi-source energy storage grid scheduling coordination method, characterized in that, The method comprises the following steps: real-time acquisition of multi-source state data inside each energy storage unit; inputting the preset initial maximum capacity of each energy storage unit and the multi-source state data into a preset battery current capacity prediction model to output the maximum available capacity of each energy storage unit at the current time; outputting the battery health parameters of each energy storage unit according to the maximum available capacity and the energy storage health prediction model; calculating the target charge-discharge power of each energy storage unit according to the maximum available capacity and the battery health parameters; dynamically allocating and regulating the target charge-discharge power of each energy storage unit, and continuously diagnosing and monitoring the faults of each energy storage unit according to the collected multi-source state data of each energy storage unit during the regulation.

2. The multi-source energy storage grid dispatch coordination method of claim 1, wherein, The method of inputting the preset initial maximum capacity of each energy storage unit and the multi-source state data into a preset battery current capacity prediction model to output the maximum available capacity of each energy storage unit at the current time comprises the following steps: determining the first fitting parameters between the battery material and the working condition state corresponding to each energy storage unit and the second fitting parameters of the capacity loss caused by the depth of charge and discharge according to the multi-source state data of each energy storage unit; inputting the first fitting parameters and the second fitting parameters into the preset battery current capacity prediction model to obtain the capacity attenuation value of each energy storage unit at the current time according to the preset initial maximum capacity of each energy storage unit; calculating the maximum available capacity of each energy storage unit at the current time according to the capacity attenuation value.

3. The multi-source energy storage grid dispatch coordination method of claim 2, wherein, The method of determining the first fitting parameters between the battery material and the working condition state corresponding to each energy storage unit and the second fitting parameters of the capacity loss caused by the depth of charge and discharge according to the multi-source state data of each energy storage unit comprises the following steps: inputting the multi-source state data of each energy storage unit into the deep learning model to output the first fitting parameters between the battery material and the working condition state corresponding to each energy storage unit and the second fitting parameters of the capacity loss caused by the depth of charge and discharge; wherein the multi-source state data comprises battery material characteristics, current working condition, current throughput power and cycle number.

4. The multi-source energy storage grid dispatch coordination method of claim 3, wherein, The method for constructing the deep learning model comprises the following steps: obtaining historical multi-source state data of the energy storage unit, and constructing a historical digital twin model of each energy storage unit according to the historical multi-source state data; determining the historical first fitting parameters between the battery material and the working condition state corresponding to each energy storage unit and the historical second fitting parameters of the capacity loss caused by the depth of charge and discharge according to the historical digital twin model; constructing an initial deep learning model; iteratively training the initial deep learning model by taking the historical multi-source state data as input and taking the historical first fitting parameters and the historical second fitting parameters as output to obtain the trained deep learning model.

5. The multi-source energy storage grid dispatch coordination method of claim 4, wherein, The method for calculating the target charge-discharge power of each energy storage unit according to the maximum available capacity and the battery health parameters comprises the following steps: determining the income weight, the over-temperature and over-current weight, and the life weight according to the maximum available capacity and the battery health parameters; calculating the charge-discharge target power function of each energy storage unit according to the income weight, the over-temperature and over-current weight, and the life weight; According to the charge-discharge target power function, the target charge-discharge power of each energy storage unit is calculated.

6. The multi-source energy storage grid dispatch coordination method of any one of claims 1-5, wherein, Before the target charge-discharge power of each energy storage unit is dynamically allocated and regulated, the method further comprises: The internal temperature and internal resistance of each energy storage unit are monitored in real time, and simulation of target charge-discharge power adjustment of each energy storage unit is performed. During the simulation, the temperature rise and voltage drop of each energy storage unit are determined according to the real-time monitored internal temperature and internal resistance of each energy storage unit, and the energy storage unit whose temperature rise exceeds a preset temperature rise threshold or whose internal voltage is lower than a cut-off voltage is extracted as a to-be-corrected energy storage unit. The target charge-discharge power of the to-be-corrected energy storage unit is derated, and the simulation is performed again until the temperature rise of the energy storage unit does not exceed the preset temperature rise threshold and the internal voltage of the energy storage unit is not lower than the cut-off voltage.

7. A multi-source energy storage power grid dispatching coordination device, characterized in that, It comprises: a collection module, a capacity module, a health parameter module, a charge-discharge module, and a regulation module; The collection module is configured to collect multi-source state data inside each energy storage unit in real time. The capacity module is configured to input the preset initial maximum capacity of each energy storage unit and the multi-source state data into a preset battery current capacity prediction model, and output the maximum available capacity of each energy storage unit at the current time. The health parameter module is configured to output the battery health parameter of each energy storage unit according to the maximum available capacity and in combination with an energy storage health prediction model. The charge-discharge module is configured to calculate the target charge-discharge power of each energy storage unit according to the maximum available capacity and the battery health parameter. The regulation module is configured to dynamically allocate and regulate the target charge-discharge power of each energy storage unit, and continuously perform fault diagnosis and monitoring according to the collected multi-source state data of each energy storage unit during the regulation. 8.The multi-source energy storage grid dispatching collaboration device of claim 7, wherein, It further comprises: a simulation module; The simulation module is configured to monitor the internal temperature and internal resistance of each energy storage unit in real time, and perform simulation of target charge-discharge power adjustment of each energy storage unit. During the simulation, the temperature rise and voltage drop of each energy storage unit are determined according to the real-time monitored internal temperature and internal resistance of each energy storage unit, and the energy storage unit whose temperature rise exceeds a preset temperature rise threshold or whose internal voltage is lower than a cut-off voltage is extracted as a to-be-corrected energy storage unit. The target charge-discharge power of the to-be-corrected energy storage unit is derated, and the simulation is performed again until the temperature rise of the energy storage unit does not exceed the preset temperature rise threshold and the internal voltage of the energy storage unit is not lower than the cut-off voltage.

9. A terminal device, comprising: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the computer program is executed by the processor, the method for coordinating the dispatching of a multi-source energy storage power grid as claimed in any one of claims 1-6 is implemented.

10. A computer-readable storage medium, characterized in that, It comprises: a stored computer program, wherein when the computer program is running, the device where the computer readable storage medium is located is controlled to perform the method for coordinating the dispatching of a multi-source energy storage power grid as claimed in any one of claims 1-6.

Images