Distributed energy storage safety supervision method and system based on big data, and cloud platform

Abstract

The invention provides a distributed energy storage safety supervision method and system based on big data and a cloud platform, and belongs to the technical field of energy storage safety, and the method comprises the steps: collecting first-level data of a PCS layer and second-level data of a BMS layer based on a distributed energy storage system, and carrying out the data fusion of the first-level data and the second-level data; performing cloud dynamic risk assessment on the distributed energy storage system according to a data fusion result, calling a matching strategy by using a risk assessment result, performing multi-system linkage based on the matching strategy, and obtaining a linkage effect; according to the method, multi-dimensional evaluation is carried out on the linkage effect, optimization adjustment is carried out on the optimization strategy, meanwhile, safety warning is carried out according to the linkage effect, corresponding protection measures are triggered to form safety supervision, active safety protection of the energy storage system is achieved, the response speed is increased, the fault rate is reduced, and the safety and intelligent level are comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the field of energy storage safety technology, and in particular to a distributed energy storage safety supervision method, system and cloud platform based on big data. Background Art

[0002] As the proportion of intermittent renewable energy such as wind power and photovoltaics increases, distributed energy storage systems (such as battery energy storage) have become key facilities for grid frequency regulation and peak shaving. The separation of BMS and PCS data in existing technologies leads to misjudgment of risks, and static strategies cannot adapt to changes such as battery degradation and grid fluctuations.

[0003] Therefore, the present invention provides a distributed energy storage safety supervision method, system and cloud platform based on big data. Summary of the invention

[0004] The distributed energy storage safety supervision method, system and cloud platform based on big data provided by the present invention construct a panoramic system status through multi-source data fusion, dynamically evaluate short-term / long-term risks in the cloud and generate optimization strategies, which are issued for execution after digital twin simulation verification; the linkage effect is fed back to the strategy iteration through multi-dimensional evaluation, and a perception-decision-execution-optimization closed loop is formed in combination with dynamic threshold alarms, so as to realize active safety protection of the energy storage system, improve response speed, reduce failure rate, and comprehensively improve safety and intelligence level.

[0005] The distributed energy storage safety supervision method based on big data provided by the present invention includes: Step 1: Based on the distributed energy storage system, the first-level data of the PCS layer and the second-level data of the BMS layer are collected, and the first-level data and the second-level data are fused; Step 2: Perform cloud-based dynamic risk assessment on the distributed energy storage system based on the data fusion results, use the risk assessment results to call the matching strategy, perform multi-system linkage based on the matching strategy, and obtain the linkage effect; Step 3: Conduct a multi-dimensional evaluation of the linkage effect, optimize and adjust the optimization strategy, issue a security alert based on the linkage effect, and trigger corresponding protection measures to form security supervision.

[0006] The distributed energy storage safety supervision method based on big data provided by the present invention determines the data acquisition layer based on the technical architecture of the distributed energy storage system, collects the first-level data of the PCS layer and the second-level data of the BMS layer, and processes the first-level data and the second-level data, including: Designing a first data item about the PCS layer based on the distributed energy storage system, determining a first acquisition unit and a first communication mode according to the first data item, and then collecting first-level data; Design a second data item about the BMS layer based on the distributed energy storage system, determine a second acquisition unit and a second communication method according to the first data item, and then collect second-level data; Cross-level data fusion is performed on the first-level data and the second-level data.

[0007] The distributed energy storage safety supervision method based on big data provided by the present invention performs cross-level data fusion on the first-level data and the second-level data, including: Performing a first scene label association on the first-level data to obtain a first association result, and performing a second scene label association on the second-level data to obtain a second association result; Determining a conflict type of the distributed energy storage system according to the first association result and the second association result, and determining a dynamic conflict monitoring algorithm based on the conflict type; Performing data coupling on the first-level data and the second-level data based on the first association result and the second association result to obtain a coupling result; Extract the first feature vector of the first-level data, extract the second feature vector of the second-level data, match the corresponding fusion method from the feature-fusion method table, and use the fusion method to perform data fusion on the first feature vector and the second feature vector based on the coupling result and the dynamic conflict monitoring algorithm.

[0008] The distributed energy storage safety supervision method based on big data provided by the present invention performs cloud-based dynamic risk assessment on the distributed energy storage system according to the data fusion result, uses the risk assessment result to call the matching strategy, performs multi-system linkage based on the matching strategy, and obtains the linkage effect, including: The cloud platform receives the data fusion results, uses the risk assessment model to assess the short-term and long-term risks of the distributed energy storage system, and obtains the risk assessment results; Using the risk assessment result to match the prefabricated strategy from the rule library, if the match fails, calling the reinforcement learning model to generate a temporary strategy, combining the prefabricated strategy and the temporary strategy to obtain a matching strategy; Convert the matching strategy into standard instructions, split the standard instructions, and perform multi-system linkage according to the splitting results, and set up a fault-tolerant mechanism; A digital twin model is constructed based on the data fusion results, and the matching strategy and the multi-system linkage process are simulated and verified using the digital twin model, and the linkage effect is determined according to the verification results.

[0009] The distributed energy storage safety supervision method based on big data provided by the present invention sets a fault tolerance mechanism, including: Unit fault-tolerant measures are formulated according to the unit structure existing in the distributed energy storage system, multi-level linkage fault-tolerant measures are formulated according to the linkage of multiple systems, and a fault-tolerant mechanism is set up by combining the unit fault-tolerant measures and the multi-level linkage fault-tolerant measures.

[0010] The distributed energy storage safety supervision method based on big data provided by the present invention builds a digital twin model based on data fusion results, uses the digital twin model to simulate and verify the matching strategy and the multi-system linkage process, and determines the linkage effect according to the verification results, including: Superimpose the simulation verification curve and the actual execution curve to calculate the fitting result; Decomposing the matching strategy into strategy actions that can be mapped to the digital twin model, performing causal inference on the strategy actions and the existence linkage, and calculating the relevant results; quantifying the strategic actions and the existence linkage into a directed graph based on the correlation results and the fitting results, analyzing the directed graph, and determining the critical path, the invalid actions, the positive feedback loop and the negative feedback loop; Perform a first optimization on the matching strategy based on the critical path and the invalid action, perform a second optimization on the matching strategy based on the positive feedback loop and the negative feedback loop, and determine the optimization strategy by combining the first optimization and the second optimization; The matching strategy and optimization strategy are verified by synchronous simulation using a digital twin model to obtain a linkage effect.

[0011] The distributed energy storage safety supervision method based on big data provided by the present invention performs multi-dimensional evaluation on the linkage effect, optimizes and adjusts the optimization strategy, and issues safety alarms according to the linkage effect, and triggers corresponding protection measures to form safety supervision, including: Determine the evaluation dimension of the linkage effect from the effect-evaluation table in combination with the data fusion result, obtain the historical linkage effect to optimize the dynamic threshold, and determine the multi-dimensional evaluation result of the linkage effect based on the evaluation dimension and the threshold optimization; The cause of the linkage effect is determined according to the multi-dimensional evaluation result, and an alarm is issued for failed linkage. The execution device is verified based on the cause, and the execution device is safely supervised.

[0012] The distributed energy storage safety supervision system based on big data provided by the present invention includes: Fusion module: collects the first-level data of the PCS layer and the second-level data of the BMS layer based on the distributed energy storage system, and performs data fusion on the first-level data and the second-level data; Linkage module: Perform cloud-based dynamic risk assessment on the distributed energy storage system based on the data fusion results, use the risk assessment results to call the matching strategy, perform multi-system linkage based on the matching strategy, and obtain the linkage effect; Supervision module: conducts multi-dimensional evaluation on the linkage effect, optimizes and adjusts the optimization strategy, issues security alerts based on the linkage effect, and triggers corresponding protection measures to form security supervision.

[0013] The distributed energy storage safety supervision cloud platform based on big data provided by the present invention includes a distributed energy storage system and a digital twin model: The distributed energy storage system includes a PCS layer and a BMS layer; The digital twin model includes simulation of the linkage process and simulation of risks existing during the operation of the distributed energy storage system.

[0014] Compared with the existing technology, the beneficial effects of the present application are as follows: the panoramic status of the system is constructed through the fusion of multi-source data, the short-term / long-term risks are dynamically evaluated in the cloud and optimization strategies are generated, which are issued for execution after verification by digital twin simulation; the linkage effect is fed back to the strategy iteration through multi-dimensional evaluation, and a perception-decision-execution-optimization closed loop is formed in combination with dynamic threshold alarms, so as to realize active safety protection of the energy storage system, improve response speed, reduce failure rate, and comprehensively improve safety and intelligence levels.

[0015] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0016] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a distributed energy storage safety supervision method based on big data provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a distributed energy storage safety supervision system based on big data provided by an embodiment of the present invention; Figure 3 It is a structural diagram of a distributed energy storage safety supervision cloud platform based on big data provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of the technical structure of the energy storage system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0019] Embodiment 1: The embodiment of the present invention provides a distributed energy storage safety supervision method based on big data, such as Figure 1 As shown, including: Step 1: Based on the distributed energy storage system, the first-level data of the PCS layer and the second-level data of the BMS layer are collected, and the first-level data and the second-level data are fused; Step 2: Perform cloud-based dynamic risk assessment on the distributed energy storage system based on the data fusion results, use the risk assessment results to call the matching strategy, perform multi-system linkage based on the matching strategy, and obtain the linkage effect; Step 3: Conduct a multi-dimensional evaluation of the linkage effect, optimize and adjust the optimization strategy, issue a security alert based on the linkage effect, and trigger corresponding protection measures to form security supervision.

[0020] In this embodiment, the distributed energy storage system refers to an energy management system composed of multiple distributed energy storage units, such as Figure 4As shown, the battery unit is the battery pack, which uses lithium iron phosphate batteries, with a single cell of 314Ah, 16 cells in series in each unit, and a storage capacity of 1004.8wh. The battery management system BMS is a three-level architecture, namely BMU sub-control unit, BCU main control unit, BAU general control unit, BMU: Each battery unit integrates a BMU sub-control unit, which collects the voltage and temperature of the single cell and uploads them to the BCU; at the same time, it receives the fan start and stop instructions issued by the BCU. BCU: Collect the total voltage on the battery side, the total voltage on the PCS side, the charge and discharge current, estimate the SOC, etc.; control the main positive, main negative, and pre-charge contactors to close or open; receive battery data with BMU through CAN; exchange information with BAU through CAN; battery protection logic judgment; BAU: collect the working position status of each switch and the position status of the rotary switch; exchange information with BCU through CAN; upload battery information with PCS through CAN communication; control the PCS working mode through 485 communication with PCS, and control the PCS work through time strategy; upload data information with LCD through 485 and receive LCD setting information; read meter data through 485 communication with metering meter; exchange data with data terminal through 232 and receive background time synchronization information at the same time; the integrated design of the master control unit BAU of the energy management system EMS and the battery management BMS reduces the technical architecture links and saves costs. Set the charge and discharge strategy through the touch screen display unit, and the strategy is sent to the master control unit BAU / EMS. The master control unit executes according to the strategy and sends the corresponding instructions to PCS.

[0021] In this embodiment, the PCS layer is a power conversion system layer, such as a certain brand of 500kW bidirectional converter, which is responsible for AC / DC power conversion and grid interaction.

[0022] In this embodiment, the BMS layer is a battery management system layer, such as an intelligent management system of a 24-string lithium battery pack.

[0023] In this embodiment, cross-level data fusion is to establish semantic association between PCS and BMS data through scene label association, and identify system-level conflict types; select dynamic monitoring algorithms based on conflict features to achieve data coupling and feature vector fusion, for example, the real-time 500kW discharge demand of PCS is integrated with the battery pack SOC=80% data reported by BMS, and the optimal discharge power threshold of 400kW is calculated through the optimization algorithm. For example, the Beidou satellite clock is used to achieve microsecond time alignment, and then deep data coupling is achieved through feature vector extraction and deep learning models, and finally the system-level optimization control strategy is output.

[0024] In this embodiment, the first-level data are the real-time operating parameters of the power conversion system, which reflect the grid interaction and energy conversion status; the second-level data are the core battery parameters monitored by the battery management system, which reflect the health and safety status of the battery cells.

[0025] In this embodiment, the data fusion result is a standardized data set that has been integrated across systems, such as a conclusion of a dischargeable power of 400kW generated by fusing a 500kW discharge command from the PCS with 80% SOC data reported by the BMS.

[0026] In this embodiment, the risk assessment result is a quantitative output of the system safety status. For example, the short-term risk shows that the probability of overheating of battery pack 3 within 10 minutes is 72%, and the long-term risk predicts that the battery pack capacity will decay to 82% after 6 months.

[0027] In this embodiment, the matching strategy is the final execution plan, which may be a direct call of a prefabricated strategy or a combination of a prefabricated strategy and a temporary strategy.

[0028] In this embodiment, the input of the digital twin model is the simulation initial conditions including real-time data (current battery temperature) and strategy parameters (the load reduction range to be executed); the output of the digital twin model is predictive existence linkage, such as showing that after the current strategy is executed, the temperature will drop to a safe range within 8 minutes.

[0029] In this embodiment, multi-system linkage is a collaborative execution across subsystems, typically such as the joint action of adjusting PCS power, BMS protection threshold, and air conditioning cooling power at the same time.

[0030] In this embodiment, the linkage effect is the actual system response after the strategy is executed. For example, the load reduction instruction causes the battery temperature to drop by 8° C. within 30 minutes without affecting the stability of the power grid.

[0031] In this embodiment, the cloud platform analyzes short-term and long-term risks in real time by integrating data-driven risk assessment models; generates optimal strategies based on rule bases and reinforcement learning, which are broken down into multi-system collaborative instructions after digital twin simulation verification, and embedded with fault-tolerant mechanisms to achieve closed-loop control of evaluation-decision-making-verification-execution.

[0032] In this embodiment, a dynamic evaluation system is constructed by integrating real-time data and historical effects, and linkage performance is quantified based on multi-dimensional indicators; a threshold self-optimization algorithm is used to identify anomalies, locate the root cause of the fault and trigger accurate alarms.

[0033] In this embodiment, the multi-dimensional evaluation is a multi-angle quantitative analysis system for the linkage effect of the energy storage system. By integrating data features and dynamic threshold optimization, the effectiveness of the linkage strategy is comprehensively evaluated from multiple orthogonal dimensions.

[0034] In this embodiment, the protection measures include a fire extinguishing system. The energy storage cabinet is equipped with an aerosol fire extinguishing system, and each output unit has an integrated aerosol fire extinguishing system. For charge and discharge protection, the battery management system BMS adopts a three-level protection strategy for battery overcharge and over-discharge protection. The three-level strategy for single battery voltage is too high or too low is: level one alarm, level two limiting the charge and discharge current, and level three prohibiting charge and discharge. For temperature protection, the battery management system BMS collects the temperature of the single battery voltage and also adopts a three-level protection strategy. For ambient temperature, the energy storage device adopts air cooling technology and selects intelligent air conditioning to adjust the temperature in the energy storage cabinet. Smoke alarm: A smoke alarm is provided on the top of the energy storage product. This device is one of the highest-level alarm devices. Once triggered, it will immediately stop all states of the energy storage device and notify the on-duty manager's mobile phone through a short message. For water intrusion alarm, a water intrusion alarm is provided at the bottom of the energy storage product. This device is one of the highest-level alarm devices. Once triggered, it will immediately stop all states of the energy storage device and notify the on-duty manager's mobile phone through a short message.

[0035] The working principle and beneficial effects of the above technical solution are: building a panoramic system status through multi-source data fusion, dynamically evaluating short-term / long-term risks in the cloud and generating optimization strategies, which are issued for execution after digital twin simulation verification; the linkage effect is fed back to the strategy iteration through multi-dimensional evaluation, and combined with dynamic threshold alarms to form a perception-decision-making-execution-optimization closed loop, so as to realize active safety protection of the energy storage system, improve response speed, reduce failure rate, and comprehensively improve safety and intelligence levels.

[0036] Embodiment 2: The embodiment of the present invention provides a distributed energy storage safety supervision method based on big data, determines the data collection layer based on the technical architecture of the distributed energy storage system, collects the first-level data of the PCS layer and the second-level data of the BMS layer, and processes the first-level data and the second-level data, including: Designing a first data item about the PCS layer based on the distributed energy storage system, determining a first acquisition unit and a first communication mode according to the first data item, and then collecting first-level data; Design a second data item about the BMS layer based on the distributed energy storage system, determine a second acquisition unit and a second communication method according to the first data item, and then collect second-level data; Cross-level data fusion is performed on the first-level data and the second-level data.

[0037] In this embodiment, the first data item refers to key operating parameters of the PCS layer, such as AC side voltage, output power, efficiency, harmonic distortion rate and other data.

[0038] In this embodiment, the first acquisition unit is a hardware device for acquiring the PCS data, for example, a Hall sensor is used in conjunction with an FPGA high-speed acquisition card to achieve 10kHz sampling.

[0039] In this embodiment, the first communication mode is a PCS layer data transmission protocol, for example, using the Modbus TCP protocol superimposed on a 5G wireless redundant channel to ensure that the transmission delay is less than 5ms.

[0040] In this embodiment, the second data item refers to key parameters monitored by the BMS, including single cell voltage, temperature, SOC, SOH and other data.

[0041] In this embodiment, the second acquisition unit is a dedicated device for acquiring BMS data, for example, a TI BQ76952 analog front-end chip is used in conjunction with a CAN bus communication module.

[0042] In this embodiment, the second communication method is a BMS layer data transmission protocol, for example, a communication architecture using a CAN bus as the main and RS-485 as the backup, with a transmission rate of 250 kbps.

[0043] The working principle and beneficial effects of the above technical solution are: by structured definition of key data items of the PCS layer and the BMS layer, matching dedicated acquisition units and communication protocols, efficient collection of multi-source heterogeneous data can be achieved; cross-system data fusion is completed based on time-space alignment and feature coupling, and a unified state perception system is built to cover the full link parameters of charging and discharging, eliminate monitoring blind spots, and have strong data integrity. The modular design supports rapid access to new data items, which helps to improve scalability.

[0044] Embodiment 3: The embodiment of the present invention provides a distributed energy storage safety supervision method based on big data, which performs cross-level data fusion on the first-level data and the second-level data, including: Performing a first scene label association on the first-level data to obtain a first association result, and performing a second scene label association on the second-level data to obtain a second association result; Determining a conflict type of the distributed energy storage system according to the first association result and the second association result, and determining a dynamic conflict monitoring algorithm based on the conflict type; Performing data coupling on the first-level data and the second-level data based on the first association result and the second association result to obtain a coupling result; Extract the first feature vector of the first-level data, extract the second feature vector of the second-level data, match the corresponding fusion method from the feature-fusion method table, and use the fusion method to perform data fusion on the first feature vector and the second feature vector based on the coupling result and the dynamic conflict monitoring algorithm.

[0045] In this embodiment, the first scenario label association refers to the process of labeling the PCS layer data (such as power, voltage, etc.) with a working condition label. For example, an overload risk label is labeled for data whose output power continuously exceeds 90% of the rated value.

[0046] In this embodiment, the first association result is structured data formed after tag association, such as a PCS data set marked as overload risk, including dimensions such as timestamp, power value, and duration.

[0047] In this embodiment, the second scene label association is a process of scene classification of BMS layer data (such as temperature, SOC, etc.). For example, data with a battery temperature exceeding 45°C and SOC>95% is marked as a precursor to thermal runaway.

[0048] In this embodiment, the second correlation result is a labeled output of the BMS data, such as the thermal runaway precursor data set in the above example, which includes features such as temperature curves and voltage fluctuations.

[0049] In this embodiment, data coupling is a process of establishing a physical association between two types of data, for example, aligning and logically matching the overload time point of the PCS with the temperature data of the BMS at the same time.

[0050] In this embodiment, the coupling result is an intermediate product after data association, such as finding a timing association rule that the BMS temperature rises by 2° C. after the PCS is overloaded for 5 minutes.

[0051] In this embodiment, the first feature vector is a feature set extracted from PCS data, such as a vector consisting of [power fluctuation amplitude, efficiency reduction rate, harmonic distortion rate].

[0052] In this embodiment, the second feature vector is a feature set extracted from the BMS data, such as a vector consisting of [maximum temperature, SOC drop rate, voltage dispersion].

[0053] In this embodiment, the feature-fusion method table is a predefined fusion method matching rule base. For example, when the conflict type is power-temperature conflict, a weighted fusion algorithm is used, and when the conflict type is SOC-efficiency conflict, a neural network fusion is used.

[0054] In this embodiment, the fusion method is a specific integration algorithm, such as using the entropy weight method to determine the weight ratio of power and temperature data.

[0055] In this embodiment, the dynamic conflict monitoring algorithm is an algorithm for identifying system conflicts in real time. For example, when it is detected that the PCS required power > the BMS available power, a power supply shortage conflict is triggered, and a sliding window algorithm is used to continuously monitor the conflict evolution trend.

[0056] In this embodiment, the difference between data fusion and data coupling is that data coupling is to establish an association relationship between data (such as time alignment), for example, aligning the power mutation moment of the PCS with the temperature recording time of the BMS; data fusion is to deeply integrate the associated data, for example, generating a system health index through Kalman filtering of power and temperature data.

[0057] In this embodiment, the role of the dynamic conflict monitoring algorithm in data fusion is that the dynamic conflict monitoring algorithm is the intelligent arbitration center of data fusion, and the fusion quality is guaranteed through multi-dimensional technology.

[0058] The working principle and beneficial effects of the above technical solution are: establishing semantic association between PCS and BMS data through scene label association to identify system-level conflict types; selecting dynamic monitoring algorithms based on conflict features to achieve data coupling and feature vector fusion, and finally using adaptive fusion methods to generate unified data representation, improve conflict recognition rate, and enhance data consistency.

[0059] Embodiment 4: The embodiment of the present invention provides a distributed energy storage safety supervision method based on big data, performs cloud-based dynamic risk assessment on the distributed energy storage system according to the data fusion result, uses the risk assessment result to call the matching strategy, performs multi-system linkage based on the matching strategy, and obtains the linkage effect, including: The cloud platform receives the data fusion results, uses the risk assessment model to assess the short-term and long-term risks of the distributed energy storage system, and obtains the risk assessment results; Using the risk assessment result to match the prefabricated strategy from the rule library, if the match fails, calling the reinforcement learning model to generate a temporary strategy, combining the prefabricated strategy and the temporary strategy to obtain a matching strategy; Convert the matching strategy into standard instructions, split the standard instructions, and perform multi-system linkage according to the splitting results, and set up a fault-tolerant mechanism; A digital twin model is constructed based on the data fusion results, and the matching strategy and the multi-system linkage process are simulated and verified using the digital twin model, and the linkage effect is determined according to the verification results.

[0060] In this embodiment, the cloud platform is an energy storage system management center deployed on a cloud server. For example, a certain energy storage cloud platform uses Alibaba Cloud ECS instances to process data from multiple energy storage sites in real time.

[0061] In this embodiment, short-term risks are sudden threats that require immediate response, such as battery thermal runaway warnings, grid frequency mutations, and other immediate risks.

[0062] In this embodiment, the long-term risk is a systemic risk that develops gradually, such as battery pack capacity decay, insulation material aging, and other risks that require periodic monitoring.

[0063] In this embodiment, the rule base is a set of predefined policies, including hundreds of policy rules such as forcibly switching to charging mode when SOC<20%.

[0064] In this embodiment, the prefabricated strategy is a standardized response plan stored in the rule base, such as a preset process of starting the liquid cooling system + reducing the load by 50% when the temperature is detected to be greater than 50°C.

[0065] In this embodiment, the reinforcement learning model is an adaptive strategy generation algorithm, such as a model trained based on the DQN framework, which autonomously generates a frequency regulation strategy when encountering a new grid fluctuation pattern.

[0066] In this embodiment, the temporary strategy is a dynamic solution for unforeseen overload scenarios, such as a battery scheduling solution generated during a sudden power outage to prioritize ICU power supply.

[0067] In this embodiment, the fault-tolerance mechanism is a fault response plan system, which includes dual protections of hardware redundancy (spare PCS module) and software fault tolerance (instruction retry mechanism).

[0068] In this embodiment, standard instructions are standardized control commands that can be executed by devices, such as setting the output power of device PCS-07 to 300kW±5%; instruction splitting is to decompose complex strategies into device-level operations, such as decomposing system load reduction into sub-instructions such as PCS power reduction + BMS current limiting + air conditioning frequency increase; the splitting result is the operation sequence after instruction decomposition, including metadata such as execution device ID, parameter values, timing requirements, etc.

[0069] In this embodiment, simulation verification is to test the feasibility of the strategy in a virtual environment, for example, to verify whether the load reduction strategy will cause the grid voltage to exceed the limit.

[0070] In this embodiment, the verification result is a quantitative indicator of the simulation output, including evaluation data such as success rate, estimated energy consumption, and equipment loss.

[0071] The working principle and beneficial effects of the above technical solution are: the cloud platform analyzes short-term and long-term risks in real time by integrating data-driven risk assessment models; generates optimal strategies based on rule bases and reinforcement learning, which are broken down into multi-system collaborative instructions after digital twin simulation verification, and embedded with fault-tolerant mechanisms to achieve closed-loop control of evaluation-decision-making-verification-execution, with comprehensive risk coverage and high strategy reliability.

[0072] Embodiment 5: The embodiment of the present invention provides a distributed energy storage safety supervision method based on big data, setting a fault tolerance mechanism, including: Unit fault-tolerant measures are formulated according to the unit structure existing in the distributed energy storage system, multi-level linkage fault-tolerant measures are formulated according to the linkage of multiple systems, and a fault-tolerant mechanism is set up by combining the unit fault-tolerant measures and the multi-level linkage fault-tolerant measures.

[0073] In this embodiment, the unit structure is the smallest functional module that can operate independently in the distributed energy storage system, and has complete energy storage and conversion capabilities, such as a single battery energy storage cabinet (including battery pack, BMS, cooling system), PCS converter module (including IGBT unit, control board, filter circuit), photovoltaic inverter and its supporting DC / DC converter.

[0074] In this embodiment, the unit fault tolerance measure is a fault isolation and self-recovery solution designed for a single functional module to ensure that local faults do not affect the basic functions of the unit. For example, at the battery module level: when a single cell is short-circuited, the BMS triggers the fuse to cut off the fault circuit and enables the backup battery pack at the same time (such as a certain brand of energy storage cabinet configured with N+1 redundant batteries). When the temperature sensor fails, it switches to the adjacent sensor data + AI prediction compensation (error <±1°C).

[0075] In this embodiment, the multi-level linkage fault-tolerant measure is a cross-unit coordinated fault response strategy to solve the problem of system-level functional chain breaks. For example, grid frequency interruption recovery: when the main PCS fails, the dispatching system automatically transfers the load to the backup PCS, and the BMS adjusts the battery pack output priority (such as a microgrid system that achieves seamless switching within 200ms); cooling system failure emergency: after detecting an air-conditioning failure, the BMS is linked to limit the charging and discharging power to 50%, and at the same time, the backup air duct shared cooling of the adjacent energy storage cabinet is started (such as a project that uses an air cooling + liquid cooling hybrid redundant design); communication interruption fault tolerance: when the cloud control loses contact, the edge gateway automatically switches to the local preset strategy (such as SOC balancing mode), and caches the data for transmission after the communication is restored.

[0076] The working principle and beneficial effects of the above technical solution are: through the hierarchical design of the fault-tolerant mechanism, local fault isolation is achieved at the unit level, global function maintenance is ensured at the system level, and the fault-tolerant strategy is dynamically switched in combination with real-time status monitoring to form a multi-level protection system combining point and surface, thereby achieving accurate isolation of faults.

[0077] Embodiment 6: The embodiment of the present invention provides a distributed energy storage safety supervision method based on big data, constructs a digital twin model based on data fusion results, uses the digital twin model to simulate and verify the matching strategy and the multi-system linkage process, and determines the linkage effect according to the verification results, including: Superimpose the simulation verification curve and the actual execution curve to calculate the fitting result; Decomposing the matching strategy into strategy actions that can be mapped to the digital twin model, performing causal inference on the strategy actions and the existence linkage, and calculating the relevant results; quantifying the strategic actions and the existence linkage into a directed graph based on the correlation results and the fitting results, analyzing the directed graph, and determining the critical path, the invalid actions, the positive feedback loop and the negative feedback loop; Perform a first optimization on the matching strategy based on the critical path and the invalid action, perform a second optimization on the matching strategy based on the positive feedback loop and the negative feedback loop, and determine the optimization strategy by combining the first optimization and the second optimization; The matching strategy and optimization strategy are verified by synchronous simulation using a digital twin model to obtain a linkage effect.

[0078] In this embodiment, ,in, represents the dynamic time warping distance function; represents the simulation verification curve; Represents the actual execution curve; represents the simulation parameter value corresponding to the kth monitoring point; represents the actual execution parameter value corresponding to the k-th monitoring point; N represents the total number of monitoring points; k represents the k-th monitoring point; represents the adjustment weight coefficient of the curve distribution morphology difference function and the dynamic time warping distance function; represents the energy normalization factor of the actual execution curve; represents the curve distribution morphology difference function; F represents the fitting result. If F<0.7, it means that the simulation parameters are mismatched. For example, a certain energy storage station finds that the BMS temperature sampling module is damaged through the decrease of F value.

[0079] In this embodiment, causal inference is to analyze the cause-effect relationship between the strategy action and the system response, and exclude the influence of confounding factors. For example, dual machine learning is used to estimate the causal effect of a 10% PCS load reduction on a 3°C drop in battery temperature, and the Granger causality test (p<0.05 to determine causality) is performed.

[0080] In this embodiment, the strategic action is an executable control instruction or parameter adjustment, for example, limiting the charging current to 0.5C and starting the maximum air volume cooling of air conditioner No. 3.

[0081] In this embodiment, the relevant results are indicators that quantify the correlation between actions and effects, for example, the Pearson correlation coefficient r=0.82 (the linear correlation strength between liquid cooling power↑ and temperature difference↓), and the information gain IG=0.6 (the contribution of the BMS balancing strategy to SOC consistency).

[0082] In this embodiment, a directed graph is a representation of the system dynamics using nodes (actions / effects) and edges (causal relationships).

[0083] In this embodiment, the invalid action is an action that has no significant impact on the target, for example, the gain of temperature control by switching the backup sensor is only 0.05.

[0084] In this embodiment, positive feedback is a self-reinforcing cycle (such as cooling ↑ → temperature ↓ → allowing higher power ↑ → cooling demand ↑); negative feedback: a self-inhibiting cycle (such as overload protection → power ↓ → income ↓ → investment reduction → equipment aging ↑).

[0085] In this embodiment, the first optimization is to strengthen the critical path and eliminate invalid actions, such as increasing the weight of liquid cooling power (critical path action) and canceling the battery pack rotation strategy (invalid action). The second optimization is to use the feedback loop to adjust the system stability, such as setting a power growth limit for the positive feedback loop to prevent loss of control, and introducing a compensation mechanism for the negative feedback loop to break the vicious cycle.

[0086] In this embodiment, the optimization strategy is a set of control rules after comprehensive optimization.

[0087] In this embodiment, the linkage is the actual collaborative behavior between subsystems. For example, when the BMS limits the current, the PCS reduces the power synchronously and the air conditioner increases the cooling.

[0088] In this embodiment, the linkage effect is the change in system state after the linkage strategy is executed, for example, a positive effect: the temperature drops by 8°C within 30 minutes, and there is no grid fluctuation; a negative effect: frequent power adjustment causes a battery cycle life loss of +2%.

[0089] The working principle and beneficial effects of the above technical solution are: through comparative analysis of digital twin simulation and actual operation data, the causal relationship between strategy actions and linkage effects is quantified; the key paths and feedback mechanisms are identified using directed graphs, and strategy parameters and logic are optimized in stages. Finally, the optimal control solution is output through twin verification, thereby realizing dynamic iteration and upgrading of the strategy and improving strategy accuracy.

[0090] Embodiment 7: The embodiment of the present invention provides a distributed energy storage safety supervision method based on big data, performs a multi-dimensional evaluation on the linkage effect, optimizes and adjusts the optimization strategy, and issues a safety alarm according to the linkage effect, and triggers corresponding protection measures to form safety supervision, including: Determine the evaluation dimension of the linkage effect from the effect-evaluation table in combination with the data fusion result, obtain the historical linkage effect to optimize the dynamic threshold, and determine the multi-dimensional evaluation result of the linkage effect based on the evaluation dimension and the threshold optimization; The cause of the linkage effect is determined according to the multi-dimensional evaluation result, and an alarm is issued for failed linkage. The execution device is verified based on the cause, and the execution device is safely supervised.

[0091] In this embodiment, the evaluation dimension is a set of multi-angle indicators that quantify the linkage effect, such as safety: the number of times the temperature exceeds the standard (such as the cumulative daily duration of >50°C); efficiency: command response delay (such as the average time from PCS reception to execution); economy: single linkage cost (such as the converted amount of fire extinguishing agent consumption).

[0092] In this embodiment, the historical linkage effect is the recorded data of the execution of similar strategies in the past, for example, the average cooling rate (°C / min) of the load reduction + strong cooling strategy in the past 30 days, and the historical value of the maximum discharge current allowed for the same battery pack at SOC=20%.

[0093] In this embodiment, the dynamic threshold is a decision boundary that is adaptive to the system state, and the threshold optimization is a method of adjusting the threshold based on historical data.

[0094] In this embodiment, the multi-dimensional evaluation result is the comprehensive output of the scores of each dimension, and the alarm is a graded notification of abnormal linkage. For example, the first-level alarm (SMS + sound and light): the temperature linkage of battery cabinet No. 3 fails and has been forced to shut down; the second-level alarm (system pop-up window): PCS-05 response delay exceeds 200ms.

[0095] In this embodiment, the execution device is a physical device that directly executes control instructions in the distributed energy storage system, including a PCS converter, a PCS converter, a PCS converter, an air conditioning system, a circuit breaker / contactor, and a backup power switch.

[0096] The working principle and beneficial effects of the above technical solution are: building a dynamic evaluation system by integrating real-time data and historical effects, and quantifying linkage performance based on multi-dimensional indicators; using threshold self-optimization algorithms to identify anomalies, locate the root cause of faults and trigger precise alarms, and simultaneously verify the status of execution equipment to form an evaluation-diagnosis-disposal closed-loop management.

[0097] Embodiment 8: The embodiment of the present invention provides a distributed energy storage safety supervision system based on big data, such as Figure 2 As shown, including: Fusion module: collects the first-level data of the PCS layer and the second-level data of the BMS layer based on the distributed energy storage system, and performs data fusion on the first-level data and the second-level data; Linkage module: Perform cloud-based dynamic risk assessment on the distributed energy storage system based on the data fusion results, use the risk assessment results to call the matching strategy, perform multi-system linkage based on the matching strategy, and obtain the linkage effect; Supervision module: conducts multi-dimensional evaluation on the linkage effect, optimizes and adjusts the optimization strategy, issues security alerts based on the linkage effect, and triggers corresponding protection measures to form security supervision.

[0098] The working principle and beneficial effects of the above technical solution are: building a panoramic system status through multi-source data fusion, dynamically evaluating short-term / long-term risks in the cloud and generating optimization strategies, which are issued for execution after digital twin simulation verification; the linkage effect is fed back to the strategy iteration through multi-dimensional evaluation, and combined with dynamic threshold alarms to form a perception-decision-making-execution-optimization closed loop, so as to realize active safety protection of the energy storage system, improve response speed, reduce failure rate, and comprehensively improve safety and intelligence levels.

[0099] Embodiment 9: The embodiment of the present invention provides a distributed energy storage safety supervision cloud platform based on big data, such as Figure 3 As shown, the cloud platform includes a distributed energy storage system and a digital twin model: The distributed energy storage system includes a PCS layer and a BMS layer; The digital twin model includes simulation of the linkage process and simulation of risks existing during the operation of the distributed energy storage system.

[0100] The working principle and beneficial effects of the above technical solution are: the digital twin model synchronizes PCS layer and BMS layer data in real time, verifies the feasibility of the linkage strategy through multi-physical field coupling simulation, and predicts system risks based on historical data and machine learning, forming a closed-loop management of data-driven-simulation verification-dynamic optimization.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed energy storage safety supervision method based on big data, characterized in that: include: Step 1: Based on the distributed energy storage system, the first-level data of the PCS layer and the second-level data of the BMS layer are collected, and the first-level data and the second-level data are fused; Step 2: Perform cloud-based dynamic risk assessment on the distributed energy storage system based on the data fusion results, use the risk assessment results to call the matching strategy, perform multi-system linkage based on the matching strategy, and obtain the linkage effect; Step 3: Conduct a multi-dimensional evaluation of the linkage effect, optimize and adjust the optimization strategy, issue a security alert based on the linkage effect, and trigger corresponding protection measures to form security supervision.

2. The distributed energy storage safety supervision method based on big data according to claim 1 is characterized in that: The data collection layer is determined based on the technical architecture of the distributed energy storage system, the first-level data of the PCS layer and the second-level data of the BMS layer are collected, and the first-level data and the second-level data are processed, including: Designing a first data item about the PCS layer based on the distributed energy storage system, determining a first acquisition unit and a first communication mode according to the first data item, and then collecting first-level data; Design a second data item about the BMS layer based on the distributed energy storage system, determine a second acquisition unit and a second communication method according to the first data item, and then collect second-level data; Cross-level data fusion is performed on the first-level data and the second-level data.

3. The distributed energy storage safety supervision method based on big data according to claim 2 is characterized in that: The cross-level data fusion of the first-level data and the second-level data includes: Performing a first scene label association on the first-level data to obtain a first association result, and performing a second scene label association on the second-level data to obtain a second association result; Determining a conflict type of the distributed energy storage system according to the first association result and the second association result, and determining a dynamic conflict monitoring algorithm based on the conflict type; Performing data coupling on the first-level data and the second-level data based on the first association result and the second association result to obtain a coupling result; Extract the first feature vector of the first-level data, extract the second feature vector of the second-level data, match the corresponding fusion method from the feature-fusion method table, and use the fusion method to perform data fusion on the first feature vector and the second feature vector based on the coupling result and the dynamic conflict monitoring algorithm.

4. The distributed energy storage safety supervision method based on big data according to claim 1 is characterized in that: According to the data fusion results, the distributed energy storage system is dynamically assessed in the cloud, the matching strategy is called using the risk assessment results, multiple systems are linked based on the matching strategy, and the linkage effect is obtained, including: The cloud platform receives the data fusion results, uses the risk assessment model to assess the short-term and long-term risks of the distributed energy storage system, and obtains the risk assessment results; Using the risk assessment result to match the prefabricated strategy from the rule library, if the match fails, calling the reinforcement learning model to generate a temporary strategy, combining the prefabricated strategy and the temporary strategy to obtain a matching strategy; Convert the matching strategy into standard instructions, split the standard instructions, and perform multi-system linkage according to the splitting results, and set a fault tolerance mechanism; A digital twin model is constructed based on the data fusion results, and the matching strategy and the multi-system linkage process are simulated and verified using the digital twin model, and the linkage effect is determined according to the verification results.

5. The distributed energy storage safety supervision method based on big data according to claim 4 is characterized in that: Set up fault tolerance mechanisms, including: Unit fault-tolerant measures are formulated according to the unit structure existing in the distributed energy storage system, multi-level linkage fault-tolerant measures are formulated according to the linkage of multiple systems, and a fault-tolerant mechanism is set up by combining the unit fault-tolerant measures and the multi-level linkage fault-tolerant measures.

6. The distributed energy storage safety supervision method based on big data according to claim 4 is characterized in that: A digital twin model is constructed based on the data fusion results, and the matching strategy and the multi-system linkage process are simulated and verified using the digital twin model. The linkage effect is determined according to the verification results, including: Superimpose the simulation verification curve and the actual execution curve to calculate the fitting result; Decomposing the matching strategy into strategy actions that can be mapped to the digital twin model, performing causal inference on the strategy actions and the existence linkage, and calculating the relevant results; quantifying the strategic actions and the existence linkage into a directed graph based on the correlation results and the fitting results, analyzing the directed graph, and determining the critical path, the invalid actions, the positive feedback loop and the negative feedback loop; Perform a first optimization on the matching strategy based on the critical path and the invalid action, perform a second optimization on the matching strategy based on the positive feedback loop and the negative feedback loop, and determine the optimization strategy by combining the first optimization and the second optimization; The matching strategy and optimization strategy are verified by synchronous simulation using a digital twin model to obtain a linkage effect.

7. The distributed energy storage safety supervision method based on big data according to claim 6 is characterized in that: Conduct multi-dimensional evaluation of the linkage effect, optimize and adjust the optimization strategy, issue security alerts based on the linkage effect, and trigger corresponding protection measures to form security supervision, including: Determine the evaluation dimension of the linkage effect from the effect-evaluation table in combination with the data fusion result, obtain the historical linkage effect to optimize the dynamic threshold, and determine the multi-dimensional evaluation result of the linkage effect based on the evaluation dimension and the threshold optimization; The cause of the linkage effect is determined according to the multi-dimensional evaluation result, and an alarm is issued for failed linkage. The execution device is verified based on the cause, and the execution device is safely supervised.

8. A distributed energy storage safety supervision system based on big data, characterized by: include: Fusion module: collects the first-level data of the PCS layer and the second-level data of the BMS layer based on the distributed energy storage system, and performs data fusion on the first-level data and the second-level data; Linkage module: Perform cloud-based dynamic risk assessment on the distributed energy storage system based on the data fusion results, use the risk assessment results to call the matching strategy, perform multi-system linkage based on the matching strategy, and obtain the linkage effect; Supervision module: conducts multi-dimensional evaluation on the linkage effect, optimizes and adjusts the optimization strategy, issues security alerts based on the linkage effect, and triggers corresponding protection measures to form security supervision.

9. A distributed energy storage safety supervision cloud platform based on big data, characterized by: The cloud platform includes a distributed energy storage system and a digital twin model: The distributed energy storage system includes a PCS layer and a BMS layer; The digital twin model includes simulation of the linkage process and simulation of risks existing during the operation of the distributed energy storage system.

Images