Energy storage cabinet temperature control method and system based on big data

Abstract

The application provides a kind of energy storage cabinet temperature control method and system based on big data, it is related to computer technology field, is committed to improve the accuracy of energy storage cabinet temperature control, the method comprises: obtaining the first temperature information of energy storage cabinet historical time period, and the first temperature information is input into trained thermodynamic prediction model, obtains the second temperature information of future time period;According to the second temperature information, determine the high-risk area in energy storage cabinet;The temperature change rate of high-risk area in future time period is greater than preset change rate;Send enhanced cooling instruction to high-risk area, to indicate that target cooling unit corresponding to high-risk area increases cooling load;The cooling efficiency of target cooling unit is obtained, in the case where cooling efficiency is less than preset efficiency, the preset cooling load of target cooling unit is transferred to adjacent cooling unit.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and system for temperature control of energy storage cabinets based on big data. Background Technology

[0002] With the widespread application of renewable energy and the popularization of electric vehicles, energy storage technology has become a hot research topic in the energy field. As a key device for electrical energy storage, the stability and safety of energy storage cabinets are crucial to the operation of power systems. Especially in battery energy storage systems, battery temperature management directly affects battery efficiency, lifespan, and safety. Therefore, developing a technology that can precisely control the temperature of energy storage cabinets is of great significance for improving the overall performance of energy storage systems.

[0003] Currently, temperature control technology for energy storage cabinets mainly relies on traditional data acquisition and control technologies, such as collecting data through temperature sensors and controlling the temperature through simple temperature control algorithms. While these technologies can monitor and regulate the temperature of energy storage cabinets to some extent, they still have the following shortcomings in practical applications: First, existing data acquisition methods often use a single or a few sensors to monitor the temperature of the entire energy storage cabinet and then perform global temperature control based on this limited data. This approach ignores the differences between individual batteries and the complexity of battery states changing over time, resulting in insufficient temperature control and an inability to effectively extend battery life or improve system energy efficiency. Second, energy storage cabinets operate in diverse environments, from scorching deserts to frigid Arctic regions. Different geographical locations and seasonal changes bring huge temperature challenges, and existing data acquisition and control systems often struggle to accurately predict and adapt to changes in the external environment in real time. Especially under extreme weather conditions, control lag may increase the risk of battery thermal runaway. Furthermore, in large-scale energy storage systems, battery packs are deployed on a large scale. If precise temperature control cannot be implemented according to the specific needs of each battery or small area, energy waste may result. Summary of the Invention

[0004] To address the aforementioned technical issues, this application provides a big data-based method and system for controlling the temperature of energy storage cabinets, aiming to improve the accuracy of temperature control in energy storage cabinets.

[0005] In a first aspect, this application provides a method for temperature control of an energy storage cabinet based on big data. The method includes: acquiring first temperature information of the energy storage cabinet over a historical time period, and inputting the first temperature information into a trained thermodynamic prediction model to obtain second temperature information for a future time period; the thermodynamic prediction model is trained using a long short-term memory neural network algorithm, learning the heat distribution pattern inside the energy storage cabinet through historical temperature changes; determining high-risk areas in the energy storage cabinet based on the second temperature information; the temperature change rate of the high-risk area in the future time period is greater than a preset change rate; sending an enhanced cooling command to the high-risk area to instruct the target cooling unit corresponding to the high-risk area to increase its cooling load; acquiring the cooling efficiency of the target cooling unit, and transferring the preset cooling load of the target cooling unit to an adjacent cooling unit if the cooling efficiency is less than a preset efficiency.

[0006] In one possible implementation, obtaining the first temperature information of the energy storage cabinet over a historical period includes: obtaining temperature information collected by temperature sensors at multiple monitoring points inside the energy storage cabinet, continuously recording the temperature values ​​of each monitoring point through a preset data acquisition frequency, and obtaining the first temperature information.

[0007] In one possible implementation, the second temperature information includes the temperature of each monitoring point in the future time period output by the thermodynamic prediction model. Based on the second temperature information, the high-risk area in the energy storage cabinet is determined, including: calculating the temperature change of each monitoring point between adjacent time points through differential operation; if the temperature change of the monitoring point in a continuous time period is greater than the preset change rate, then the area corresponding to the monitoring point in the energy storage cabinet is determined as a high-risk area.

[0008] In one possible implementation, after sending an enhanced cooling command to the high-risk area, the method further includes: using a distributed temperature sensor array to collect temperature data of various areas inside the energy storage cabinet, and transmitting the collected temperature data to the central processing unit via the controller area network bus protocol to obtain the current temperature field of the energy storage cabinet; calculating the deviation between the current temperature field and the target temperature field, and adjusting the enhanced cooling command if the deviation is greater than a preset deviation value, until the deviation is less than the preset deviation value.

[0009] In one possible implementation, a distributed temperature sensor array is used to collect temperature data from various areas inside the energy storage cabinet, and the collected temperature data is transmitted to the central processing unit via the controller area network bus protocol to obtain the current temperature field of the energy storage cabinet. This includes: collecting temperature data from various areas inside the energy storage cabinet using a distributed temperature sensor array to obtain temperature data from each monitoring point; using cubic spline interpolation to fill the temperature gaps between monitoring points to generate a continuous temperature field distribution function, and using the temperature field distribution function as the current temperature field of the energy storage cabinet.

[0010] The technical solution provided in this application brings at least the following beneficial effects:

[0011] (1) This application discloses a temperature control method for energy storage cabinets based on big data. It uses a trained thermodynamic prediction model to predict the temperature information of the energy storage cabinet over a future period, providing important decision support for optimizing the thermal management strategy of the energy storage cabinet. This method can identify potential overheating risks in advance and trigger corresponding temperature control measures. Since the thermodynamic prediction model uses a long short-term memory neural network algorithm, trained by learning the heat distribution pattern inside the energy storage cabinet through historical temperature changes, the accuracy of the prediction results can be effectively guaranteed. Furthermore, this application can determine high-risk areas in the energy storage cabinet based on the prediction results and send enhanced cooling commands to these areas, instructing the target cooling units corresponding to the high-risk areas to increase their cooling load. This application can also obtain the cooling efficiency of the target cooling units. If the cooling efficiency is less than the preset efficiency, the preset cooling load of the target cooling unit is transferred to adjacent cooling units. This facilitates the rational allocation of cooling loads between cooling units and ensures the energy efficiency of the energy storage cabinet.

[0012] (2) The generation of the continuous temperature field distribution function provides important support for the thermal management of energy storage systems. Through this function, the system can predict the temperature value at any spatial location, identify potential hotspot areas, and provide a data basis for optimizing heat dissipation strategies and providing safety early warnings. This global temperature monitoring capability significantly improves the safety and reliability of energy storage cabinet operation.

[0013] (3) The optimal cooling efficiency allocation scheme takes into account the remaining cooling capacity and spatial relationship of each cooling unit. The system adopts a dynamic load balancing algorithm to ensure that high-efficiency units take priority in undertaking more cooling tasks, while avoiding overload operation of a single unit. This intelligent allocation mechanism can maximize the overall system's energy efficiency ratio while ensuring the cooling effect, and realize precise and energy-saving management of the energy storage cabinet temperature control.

[0014] Secondly, this application provides a temperature control system for an energy storage cabinet based on big data. The system includes a control device comprising an acquisition unit, a determination unit, and a control unit. The acquisition unit acquires first temperature information of the energy storage cabinet over a historical time period and inputs this first temperature information into a trained thermodynamic prediction model to obtain second temperature information for a future time period. The thermodynamic prediction model is trained using a long short-term memory neural network algorithm, learning the heat distribution pattern inside the energy storage cabinet through historical temperature changes. The determination unit determines high-risk areas within the energy storage cabinet based on the second temperature information. The temperature change rate of the high-risk area in the future time period is greater than a preset change rate. The control unit sends enhanced cooling commands to the high-risk areas to instruct the target cooling unit corresponding to the high-risk area to increase its cooling load. The control unit also acquires the cooling efficiency of the target cooling unit, and if the cooling efficiency is less than a preset efficiency, transfers the preset cooling load of the target cooling unit to an adjacent cooling unit.

[0015] In one possible implementation, the acquisition unit is specifically used to: acquire temperature information collected by temperature sensors at multiple monitoring points inside the energy storage cabinet, continuously record the temperature values ​​of each monitoring point through a preset data acquisition frequency, and obtain the first temperature information.

[0016] In one possible implementation, the second temperature information includes the temperature of each monitoring point in the future time period output by the thermodynamic prediction model. The determination unit is specifically used to: calculate the temperature change of each monitoring point between adjacent time points through differential operation; if the temperature change of the monitoring point in a continuous time period is greater than the preset change rate, then the area corresponding to the monitoring point in the energy storage cabinet is determined as a high-risk area.

[0017] Thirdly, this application provides an electronic device, including: a processor and a memory; the memory stores processor-executable instructions; when the processor is configured to execute the instructions, the electronic device implements the method described in the first aspect above.

[0018] Fourthly, this application provides a computer program product that, when run in an electronic device, causes the electronic device to execute the methods related to the first aspect described above, thereby implementing the methods of the first aspect.

[0019] Fifthly, this application provides a computer-readable storage medium comprising: software instructions; which, when executed in an electronic device, cause the electronic device to implement the method described in the first aspect.

[0020] The beneficial effects of the second to fifth aspects mentioned above can be referred to the first aspect, and will not be repeated here. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the structure of an energy storage cabinet system provided in an embodiment of this application;

[0023] Figure 2 A schematic diagram illustrating the composition of the electronic device provided in the embodiments of this application;

[0024] Figure 3 A flowchart illustrating the big data-based temperature control method for energy storage cabinets provided in this application embodiment;

[0025] Figure 4 This is a schematic diagram of the composition of the control device provided in the embodiments of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0027] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0028] Furthermore, in the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The term "and / or" in this document 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, in the description of the embodiments of this application, "multiple" refers to two or more.

[0029] Before providing a detailed explanation of the embodiments of this application, some related terms and technologies involved in the embodiments of this application will be introduced first.

[0030] As a core support for new energy systems, the safe and stable operation of energy storage technology directly affects the reliability of the entire power system. As a key carrier of energy storage systems, the internal temperature control level of energy storage cabinets has become a decisive factor restricting the large-scale application of energy storage technology. With the continuous increase in energy storage capacity and the increasing complexity of application scenarios, temperature management issues are becoming increasingly strategically important.

[0031] Currently, energy storage cabinet temperature control mainly relies on traditional passive heat dissipation and simple air-cooling systems. These methods generally suffer from response lag and insufficient control accuracy. Existing control strategies mostly use fixed parameter settings, which are difficult to adapt to complex and changing operating conditions, resulting in frequent local overheating and high energy consumption.

[0032] The fundamental challenge of temperature control in energy storage cabinets stems from the complexity and uncertainty of heat transfer processes. The dense arrangement of battery cells and uneven current distribution within the cabinet create a complex three-dimensional thermal field, with heat transfer between different material interfaces exhibiting strong nonlinear characteristics. This complex thermodynamic behavior results in highly dynamic temperature field changes in both time and space, making accurate prediction of the formation and evolution of hotspots extremely difficult. The lack of hotspot prediction capabilities further leads to the problem of blind control strategies; the control system cannot identify potential hazardous areas in advance and can only respond passively after temperature anomalies occur. More critically, there are complex interrelationships among the various temperature monitoring points within the cabinet. The mutual influence and dependencies between these nodes form a complex network structure, making it impossible for traditional methods to effectively identify key nodes that determine the overall temperature distribution and vulnerable points prone to failure.

[0033] In view of the above problems, this application provides a big data-based method for controlling the temperature of an energy storage cabinet. It uses big data technology to construct an accurate thermodynamic model to reveal the heat transfer pattern inside the energy storage cabinet, and uses data mining methods to identify key nodes in the temperature control network, thereby achieving accurate prediction of hot spots and dynamic optimization of cooling strategies.

[0034] The following describes in detail, with reference to the accompanying drawings, the energy storage cabinet temperature control method based on big data provided in the embodiments of this application.

[0035] The big data-based temperature control method for energy storage cabinets provided in this application can be applied to energy storage cabinet systems. Figure 1 A schematic diagram of one structure of the energy storage cabinet system is shown. For example... Figure 1 As shown, the energy storage cabinet system 10 includes an energy storage cabinet control device (hereinafter referred to as the control device) 11 and an energy storage cabinet 12. The control device 11 is communicatively connected to the energy storage cabinet 12.

[0036] The control device 11 can be any electronic device with data processing capabilities. For example, the control device 11 can be a server, a computer, or a server cluster consisting of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. Optionally, the server can be a central server, and the server can also be implemented on a cloud platform. For example, the cloud platform can include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, and multi-cloud, or any combination thereof. This application embodiment does not limit this.

[0037] The execution entity of the energy storage cabinet temperature control method based on big data provided in this application embodiment can be the aforementioned control device 11. As mentioned above, the control device 11 can be an electronic device with data processing capabilities, such as a computer or server. Optionally, the control device 11 can also be a processor (e.g., a central processing unit, CPU) in the aforementioned electronic device; or, the control device 11 can also be an application (APP) with model training capabilities installed in the aforementioned electronic device; or, the control device 11 can also be a functional module with model training capabilities in the aforementioned electronic device, etc. This application embodiment does not impose any limitations on this.

[0038] For simplicity, the following description will use the control device 11 as an electronic device.

[0039] Figure 2 This is a schematic diagram illustrating the composition of an electronic device provided in an embodiment of this application. For example... Figure 2 As shown, the electronic device may include: a processor 20, a memory 21, a communication line 22, a communication interface 23, and an input / output interface 24.

[0040] The processor 20, memory 21, communication interface 23 and input / output interface 24 can be connected via communication line 22.

[0041] Processor 20 is used to execute instructions stored in memory 21 to implement the fault analysis method provided in the following embodiments of this application. Processor 20 may be a CPU, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller (MCU), a programmable logic device (PLD), or any combination thereof. Processor 20 may also be any other device with processing capabilities, such as a circuit, device, or software module; this application embodiment does not limit this. In one example, processor 20 may include one or more CPUs, for example... Figure 2 CPU0 and CPU1 in the example. As an optional implementation, the electronic device may include multiple processors; for example, in addition to processor 20, it may also include processor 25. Figure 2 (The example shown is a dashed line).

[0042] The memory 21 is used to store instructions. For example, the instructions may be computer programs. Optionally, the memory 21 may be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions; it may also be a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions; it may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, etc. The embodiments of this application do not limit this.

[0043] It should be noted that the memory 21 can exist independently of the processor 20, or it can be integrated with the processor 20. The memory 21 can be located inside or outside the electronic device, and this embodiment does not impose any restrictions on this.

[0044] Communication line 22 is used to transmit information between the components included in the electronic device.

[0045] Communication interface 23 is used for communication with other devices or other communication networks. These other communication networks can be Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc. Communication interface 23 can be a module, circuit, transceiver, or any device capable of enabling communication.

[0046] Input / output interface 24 is used to enable human-computer interaction between the user and the electronic device. For example, it enables action interaction or information exchange between the user and the electronic device.

[0047] For example, the input / output interface 24 can be a mouse, keyboard, display screen, or touch screen. Action interaction or information exchange between the user and the electronic device can be achieved through a mouse, keyboard, display screen, or touch screen.

[0048] It should be noted that, Figure 2 The structures shown do not constitute a limitation on electronic devices, except... Figure 2 In addition to the components shown, electronic devices may include more or fewer components than illustrated, or combinations of certain components, or different component arrangements.

[0049] The following describes the big data-based temperature control method for energy storage cabinets provided in the embodiments of this application.

[0050] Figure 3 This is a flowchart illustrating a big data-based temperature control method for energy storage cabinets provided in an embodiment of this application. Optionally, this method can be implemented by a person with the above-mentioned... Figure 2 The electronic device with the hardware structure shown performs, such as Figure 3 As shown, the method includes S301 to S304.

[0051] S301. Obtain the first temperature information of the energy storage cabinet for a historical time period, and input the first temperature information into the trained thermodynamic prediction model to obtain the second temperature information for a future time period.

[0052] The thermodynamic prediction model is trained using a long short-term memory neural network algorithm, which learns the heat distribution patterns inside the energy storage tank by studying historical temperature changes. For example, the thermodynamic prediction model can be an LSTM model trained using historical temperature data that incorporates spatiotemporal characteristics.

[0053] As one possible implementation, electronic devices can acquire temperature information collected by temperature sensors at multiple monitoring points inside the energy storage cabinet, and continuously record the temperature values ​​of each monitoring point through a preset data acquisition frequency to obtain the first temperature information.

[0054] In some embodiments, the electronic device can use a long short-term memory neural network algorithm to train the temperature data matrix, learn the heat distribution pattern inside the energy storage cabinet through historical temperature change sequences, and construct a nonlinear heat transfer prediction model based on the temperature evolution characteristics under different operating conditions. If the model training error exceeds the preset accuracy requirement, the network parameters are readjusted to obtain a thermodynamic prediction model that can reflect the thermodynamic behavior of the energy storage cabinet.

[0055] Specifically, the electronic device receives the temperature data matrix from the energy storage cabinet, performs numerical transformation on the temperature data matrix using the maximum-minimum normalization method, and marks any temperature values ​​exceeding the preset working range as abnormal data points. A forward imputation algorithm is then used to complete the missing temperature records, resulting in a standardized temperature sequence dataset. Based on the standardized temperature sequence dataset, a fixed-length segmentation method is used, and the temperature sequence data is randomly sampled and divided into training and validation datasets according to a preset ratio to obtain neural network training sample pairs. The training sample pairs are received and the number of hidden layer nodes in the long short-term memory neural network is iteratively optimized using the backpropagation algorithm. If the decrease in the loss function value in the current training round is less than a preset convergence threshold, parameter updates are stopped, and the network weight parameter configuration that meets the error requirements is determined. Based on the network weight parameter configuration, the long short-term memory neural network is serialized and stored. The neural network is then deployed to the temperature prediction service module through the model loading interface to obtain a thermodynamic prediction model.

[0056] In one embodiment, the maximum and minimum value normalization process converts the internal temperature data of the energy storage cabinet from the original Celsius range into a standardized value between 0 and 1.

[0057] Specifically, when the temperature at a certain monitoring point of the energy storage cabinet is 45 degrees Celsius, while the normal operating temperature range set by the system is 10 degrees Celsius to 60 degrees Celsius, the normalized value is 0.7.

[0058] It should be noted that if the detected temperature value exceeds the preset working range, such as being below 5 degrees Celsius or above 65 degrees Celsius, the system will automatically mark these data points as outliers and process them using a forward fill algorithm.

[0059] For example, when the temperature sensor data is missing at time point 15, the forward imputation algorithm will use the valid temperature value from time point 14 to complete the data, ensuring the continuity of the temperature sequence data. This approach effectively maintains the integrity of the dataset, providing a stable input foundation for subsequent neural network training.

[0060] In one possible implementation, the time window segmentation method divides continuous temperature sequence data into segments of fixed length.

[0061] Specifically, the system sets each time window to contain 120 consecutive temperature sampling points, corresponding to a monitoring duration of 2 hours. Through random sampling, the system allocates 80% of the time window data to the training dataset and the remaining 20% ​​as the validation dataset, forming the sample pair structure required for neural network training.

[0062] For example, the number of hidden layer nodes in a Long Short-Term Memory (LSTM) neural network is iteratively optimized using the backpropagation algorithm. Initially, the hidden layer contains 64 nodes, and the system monitors the trend of the loss function value during training. When the loss function decreases by less than a preset convergence threshold of 0.001 for 10 consecutive training epochs, the system automatically stops the parameter update process. This adaptive convergence mechanism prevents overfitting and ensures the model has good generalization ability.

[0063] It should be noted that after the network weight parameters are configured, the system performs serialization and storage processing on the trained long short-term memory neural network.

[0064] Specifically, all weight matrices and bias vectors are converted to binary format and saved to a specified storage path. Through the model loading interface, the temperature prediction service module can quickly read these parameter configurations and reconstruct the neural network structure.

[0065] In one embodiment, the deployed thermodynamic prediction model can receive real-time temperature data input and output predictions of temperature change trends for future periods.

[0066] For example, when the system is input with temperature sequence data from the previous 60 minutes, the model can predict the temperature changes at each monitoring point within the next 30 minutes, with a prediction accuracy of over 95%. This predictive capability provides crucial decision support for optimizing the thermal management strategy of energy storage cabinets, enabling the early identification of potential overheating risks and triggering corresponding temperature control measures.

[0067] S302. Based on the second temperature information, identify the high-risk areas in the energy storage cabinet.

[0068] Among them, the rate of temperature change in high-risk areas will be greater than the preset rate of change in the future.

[0069] As one possible implementation, the second temperature information includes the temperature of each monitoring point over a future time period output by the thermodynamic prediction model. Electronic devices can calculate the temperature change of each monitoring point between adjacent time points using differential calculations. If the temperature change of a monitoring point over a continuous time period is greater than a preset rate of change, the area corresponding to that monitoring point within the energy storage cabinet is identified as a high-risk area.

[0070] In other embodiments, the electronic device can use an intelligent prediction model to calculate the temperature gradient change trend of each temperature monitoring point within a future time window, identify the location of potential hotspot areas based on the magnitude of the temperature gradient, dynamically update the prediction results using a sliding time window method, and mark a node as a high-risk area if the temperature gradient of a certain node continuously exceeds the dangerous threshold setting range, thereby determining the distribution of key temperature nodes that need to be monitored.

[0071] Specifically, the electronic device receives the temperature monitoring point numerical sequences output by the intelligent prediction module, calculates the temperature change between adjacent time points using a differential calculation method, and marks the node as active if the absolute value of the calculation result is greater than a preset gradient benchmark value, thus obtaining a node state matrix containing gradient amplitude information. Based on the node state matrix, a threshold comparison algorithm is used to filter the gradient amplitude values, and a spatial proximity calculation method is used to identify adjacent node groups with larger gradient amplitudes, obtaining a spatial distribution map of the coordinate information of the marked hotspot areas. A sliding time window mechanism is used to update the temperature gradient data in the spatial distribution map in real time. If the gradient value of a monitoring point exceeds the upper limit of the danger threshold in a continuous time period, a risk marking procedure is triggered to determine the risk level classification result of the node. Based on the risk level classification result, a priority sorting algorithm is used to rank all monitoring points by importance, resulting in a critical temperature node monitoring list sorted by risk level.

[0072] In one embodiment, the difference operation method identifies temperature change trends by calculating the difference between temperature values ​​at adjacent time points.

[0073] Specifically, when the temperature at a monitoring point in the energy storage cabinet is 42.5 degrees Celsius in the 10th minute and 44.2 degrees Celsius in the 11th minute, the temperature change calculated using differential calculation is 1.7 degrees Celsius. The system sets a gradient benchmark value of 1.5 degrees Celsius per minute. Because the calculated result exceeds this benchmark value, the node is automatically marked as active. This differential calculation mechanism effectively captures the dynamic temperature change characteristics inside the energy storage cabinet, providing an accurate data foundation for subsequent hotspot identification.

[0074] For example, the threshold comparison algorithm performs hierarchical filtering of gradient magnitudes in the node state matrix. The system divides gradient magnitudes into three levels: low-risk range (0.5 to 1.5 degrees Celsius per minute), medium-risk range (1.5 to 2.5 degrees Celsius per minute), and high-risk range (above 2.5 degrees Celsius per minute). The spatial proximity calculation method identifies node groups with large gradient magnitudes by analyzing the positional relationships of adjacent monitoring points. When three or more adjacent nodes are detected simultaneously in a high-risk state, the system marks this area as a hotspot and marks it with a specific color on the spatial distribution map.

[0075] In one possible implementation, a sliding time window mechanism continuously monitors temperature gradient data over a 15-minute time span. The system updates the data within the window every 5 minutes to ensure timely capture of the latest temperature trends. When the gradient value at a monitoring point exceeds the danger threshold of 3.0 degrees Celsius per minute for three consecutive time windows, a risk labeling program is automatically activated. This program categorizes the node's risk level into three levels: mild, moderate, and severe, based on the duration of exceeding the threshold and the magnitude of the gradient.

[0076] It should be noted that the priority ranking algorithm comprehensively considers multiple factors such as the node's risk level, historical anomaly frequency, and spatial importance. High-risk nodes are assigned the highest priority weight of 10, medium-risk nodes have a weight of 6, and low-risk nodes have a weight of 3. For nodes located in the core area of ​​the energy storage cabinet, the system adds two additional weight values. Through weighted calculation, the system generates a list of key temperature nodes for monitoring, ranked by risk level, ensuring that maintenance personnel can prioritize high-risk areas that require the most attention. This intelligent risk identification and ranking mechanism significantly improves the accuracy and response efficiency of energy storage cabinet thermal management.

[0077] S303. Send an enhanced cooling command to the high-risk area to instruct the target cooling unit corresponding to the high-risk area to increase the cooling load.

[0078] In some embodiments, the electronic device can directly send enhanced cooling commands to the cooling units in the high-risk areas of the energy storage cabinet to instruct the target cooling units corresponding to the high-risk areas to increase the cooling load.

[0079] The cooling unit of the energy storage cabinet is a core component ensuring its safe and efficient operation, directly affecting battery life, system stability, and safety. During charging and discharging, the battery pack in the energy storage cabinet generates a large amount of heat. Excessive temperature can lead to decreased battery performance, shortened lifespan, and even thermal runaway. The cooling unit uses heat dissipation or refrigeration technology to maintain the battery pack temperature within a safe range (typically 15℃~35℃).

[0080] In some embodiments, the electronic device formulates differentiated cooling control strategies through a node weight distribution map, dynamically adjusts the fan speed and cooling intensity of the corresponding area according to the temperature status of the core control node, and uses a proportional-integral-derivative controller to precisely adjust each cooling unit. If the temperature rise rate of the core node exceeds the warning threshold setting, an enhanced cooling mode is immediately activated to determine the optimal cooling efficiency allocation scheme.

[0081] Specifically, the electronic device receives temperature status data of core control nodes carrying spatial coordinates and temperature values ​​from the node weight distribution map. It uses a temperature gradient calculation formula to obtain the temperature change trend of each node. If the node's temperature gradient value is greater than a preset temperature change threshold, the node is marked as a high-temperature risk area, resulting in a high-temperature risk area distribution table. Based on the node coordinate information in the high-temperature risk area distribution table, a spatial mapping algorithm is used to determine the cooling unit number and fan device identifier corresponding to each high-temperature node. If the cooling demand coefficient exceeds the emergency cooling trigger threshold, an enhanced cooling command is sent to the corresponding area, obtaining a cooling unit control parameter configuration table. A proportional-integral-derivative controller receives the fan speed setpoint from the cooling unit control parameter configuration table and uses pulse-width modulation signals to control the fan motor speed of each cooling unit, obtaining a real-time fan speed adjustment command. Based on the speed values ​​in the real-time fan speed adjustment command, the power consumption and cooling efficiency ratio of each cooling unit are calculated. If the efficiency ratio of a certain cooling unit is lower than a preset efficiency benchmark value, the cooling load of that unit is reallocated to an adjacent high-efficiency cooling unit to determine the optimal cooling efficiency allocation scheme.

[0082] In one embodiment, the temperature gradient calculation is based on the ratio of the temperature difference between adjacent time points to the time interval to determine the node temperature change trend.

[0083] Specifically, when the temperature of a core control node rises from 38°C to 45°C within 5 minutes, its temperature gradient is 1.4°C per minute. The system has a preset temperature change threshold of 1.0°C per minute, therefore this node is automatically marked as a high-temperature risk area. This gradient calculation method can promptly identify dangerous areas with rapidly rising temperatures, providing an accurate data basis for subsequent cooling control.

[0084] For example, the high-temperature risk area distribution table records the three-dimensional coordinates of each risk node and the corresponding temperature gradient value. When the system detects that the temperature gradient of a node with coordinates of 150mm, 220mm, and 80mm reaches 1.6℃ per minute, the spatial mapping algorithm determines the corresponding cooling unit number as CU-07 and the associated fan device identifiers as FAN-07A and FAN-07B based on the preset equipment layout diagram. The cooling demand coefficient is calculated by the ratio of the temperature gradient value to the standard cooling capacity. When this coefficient reaches 2.3, it exceeds the emergency cooling trigger threshold of 2.0, and the system immediately sends an enhanced cooling command to the corresponding area.

[0085] S304. Obtain the cooling efficiency of the target cooling unit. If the cooling efficiency is less than the preset efficiency, transfer the preset cooling load of the target cooling unit to the adjacent cooling unit.

[0086] Specifically, a cooling unit consumes 85 watt-hours of power and reduces the temperature of the corresponding area by 8°C within 10 minutes, achieving a cooling efficiency of 0.094°C / min. When the system's preset efficiency benchmark is 0.12°C / min, this cooling unit's efficiency is substandard and load redistribution is required. The system will transfer 30% of the cooling load borne by this unit to adjacent high-efficiency cooling units CU-06 and CU-08, whose efficiency ratios are 0.15°C / min and 0.13°C / min, respectively.

[0087] In one embodiment, the optimal cooling efficiency allocation scheme considers the remaining cooling capacity and spatial relationship of each cooling unit. The system employs a dynamic load balancing algorithm to ensure that high-efficiency units prioritize undertaking more cooling tasks while avoiding overload operation of individual units. This intelligent allocation mechanism can maximize the overall system's energy efficiency ratio while ensuring cooling effectiveness, achieving precise and energy-saving management of the energy storage cabinet's temperature control.

[0088] It should be noted that a dynamic load balancing algorithm is an algorithm used in distributed systems or computer networks to dynamically adjust the allocation of tasks or requests based on the real-time status of the system. It aims to optimize resource utilization, improve system throughput, reduce response time, and avoid single-point overload. For example, the dynamic load balancing algorithm in this application embodiment can be a dynamic performance allocation algorithm. Its principle is to dynamically adjust the weights of nodes and allocate tasks based on their real-time performance indicators.

[0089] In some embodiments, after sending an enhanced cooling command to the high-risk area, the electronic device can also use a distributed temperature sensor array to collect temperature data from various areas inside the energy storage cabinet, and transmit the collected temperature data to the central processing unit via the controller area network bus protocol to obtain the current temperature field of the energy storage cabinet. Further, the electronic device calculates the deviation between the current temperature field and the target temperature field. If the deviation is greater than a preset deviation value, the enhanced cooling command is adjusted until the deviation is less than the preset deviation value.

[0090] Specifically, the electronic equipment uses a distributed temperature sensor array to collect real-time temperature data of various areas inside the energy storage cabinet. The temperature data is transmitted to the central processing unit via the CAN bus protocol to calculate the overall temperature distribution matrix of the energy storage cabinet. Based on the temperature distribution matrix data, the deviation between the current temperature field and the target temperature field is calculated. The deviation data is fitted using the least squares method to obtain the deviation trend curve. An adaptive weight adjustment mechanism is used to correct the proportional coefficient, integral coefficient, and derivative coefficient of the PID controller online. If the control response time exceeds the preset time limit, the integral coefficient is reduced and the proportional coefficient is increased to obtain the optimized control parameter combination. Based on the optimized control parameter combination, the stability index of the energy storage cabinet temperature control is recalculated. If the stability index value is lower than the preset performance benchmark value, a genetic algorithm is called to perform global optimization of the controller parameters.

[0091] In one embodiment, the distributed temperature sensor array typically employs PT1000 platinum resistance sensors or thermistors, deployed in a 3×4 grid layout within the energy storage cabinet. The spacing between each sensor node is approximately 200 mm to ensure spatial resolution for temperature acquisition. The sensor acquisition frequency is set to 10 times per second, and the temperature data is uploaded to the central processing unit via a CAN bus at a communication rate of 500 kbps, forming a 12×1 temperature data vector matrix.

[0092] Specifically, the temperature distribution matrix calculation process requires expanding discrete sensor data points into a continuous temperature field distribution using a bilinear interpolation algorithm. For example, when sensor A detects 45.2 degrees Celsius and the adjacent sensor B detects 47.8 degrees Celsius, the system calculates the temperature gradient between the two points and generates an estimated temperature value for the intermediate region. The target temperature field is typically set as a uniform 42-degree Celsius distribution, and the deviation is quantitatively evaluated using the Euclidean distance formula.

[0093] In one possible implementation, least squares fitting is used to predict temperature change trends by establishing a linear regression model of temperature deviation and time series. When the temperature deviation shows a monotonically increasing trend with a slope greater than 0.5 degrees Celsius per second over five consecutive sampling periods, the system is determined to be in a state of temperature runaway and requires emergency adjustment. The goodness of fit of the deviation trend curve is evaluated using the R-squared value; when the R-squared value is below 0.85, it indicates that the temperature change has nonlinear characteristics.

[0094] For example, the adaptive weight adjustment mechanism dynamically corrects the PID parameters based on the system response characteristics, with the initial proportional coefficient set to 1.2, integral coefficient to 0.8, and derivative coefficient to 0.3. When the control response time exceeds the preset 3-second limit, the system automatically reduces the integral coefficient to 0.5 and increases the proportional coefficient to 1.8 to avoid control lag caused by integral saturation. The adjustment range of the derivative coefficient is usually controlled within ±0.1 to prevent the system from being overly sensitive to noise.

[0095] It should be noted that the stability index evaluation uses the Lyapunov stability criterion, which determines the stability margin of the closed-loop control system by calculating the real part of the system's characteristic roots. When the stability index value is lower than the preset benchmark value of 0.6, it indicates that the current PID parameter combination may cause system oscillation or divergence. At this point, the genetic algorithm initiates a global optimization process, with a population size of 50 individuals, a crossover probability of 0.7, and a mutation probability of 0.1. After 100 generations of evolutionary iterations, the optimal parameter combination is found.

[0096] In one embodiment, the fitness function of the genetic algorithm comprehensively considers three dimensions: control accuracy, response speed, and energy efficiency, with a weighting ratio of 0.5:0.3:0.2. The optimized PID parameters can improve the temperature control accuracy of the energy storage cabinet to within ±0.5 degrees Celsius, shorten the response time to less than 1.5 seconds, and significantly improve the overall control performance.

[0097] In other embodiments, the electronic device can employ a distributed temperature sensor array to collect temperature data from various areas inside the energy storage cabinet, obtaining temperature data for each monitoring point. Furthermore, the electronic device uses cubic spline interpolation to fill in the temperature gaps between monitoring points, generating a continuous temperature field distribution function, and using this temperature field distribution function as the current temperature field of the energy storage cabinet.

[0098] Specifically, the system acquires real-time temperature values ​​from various temperature sensors inside the energy storage cabinet via the Controller Area Network (CAN) protocol. If the current data acquisition frequency is lower than a preset threshold, the sampling interval is automatically adjusted to meet the threshold requirements. Based on the real-time temperature values, the system performs spatial positioning according to the sensor location coordinates. Through three-dimensional coordinate transformation, the temperature values ​​of each monitoring point are mapped to their corresponding three-dimensional spatial locations, establishing a temperature data matrix T. The temperature data matrix is ​​then processed to be time-seriesd using timestamps. A sliding window mechanism is used to cache and store the temperature data matrix within continuous time periods, obtaining a basic dataset of temperature distribution with spatiotemporal correlation. Based on the temperature gradient information in the basic dataset of temperature distribution, cubic spline interpolation is used to fill in the temperature gaps between monitoring points, generating a continuous temperature field distribution function.

[0099] Specifically, in the energy storage cabinet temperature monitoring system, the CAN bus protocol serves as the core communication mechanism, enabling real-time data transmission from multiple temperature sensor nodes.

[0100] For example, if the system's preset data acquisition frequency is 10 times per second, and the actual acquisition frequency drops to 6 times per second, the system will automatically adjust the sampling interval from 100 milliseconds to 80 milliseconds to ensure that the data acquisition meets the monitoring accuracy requirements. This adaptive adjustment mechanism effectively guarantees the timeliness and completeness of temperature data.

[0101] Specifically, the spatial positioning process achieves precise positioning by mapping the physical coordinates of each sensor to three-dimensional space.

[0102] For example, 24 temperature sensors can be installed inside the energy storage cabinet, distributed in a three-dimensional space with a length of 2 meters, a width of 1.5 meters, and a height of 2 meters. Each sensor has unique xyz coordinates. Sensor T01 is located at coordinates 0.2, 0.3, 0.5, and sensor T02 is located at coordinates 0.8, 0.3, 0.5. In this way, a 24×3 position matrix is ​​established, which, combined with the real-time temperature value, forms a complete temperature data matrix T.

[0103] In one embodiment, the time-series processing uses a sliding window mechanism to cache and manage temperature data over consecutive time periods.

[0104] For example, by setting the window size to 300 seconds and sliding it every 30 seconds, the system can continuously save temperature distribution data for the most recent 5 minutes. Each data point is marked with a precise timestamp, such as 2024-01-15 14:30:25.123, forming a basic dataset with spatiotemporal correlation. This processing method enables the system to track temperature change trends and identify abnormal temperature rise patterns.

[0105] It should be noted that the temperature gradient information is calculated based on the ratio of the temperature difference between adjacent monitoring points to the spatial distance.

[0106] For example, when sensor T01 displays a temperature of 25.6℃ and sensor T02, 0.6 meters away, displays a temperature of 27.2℃, the temperature gradient between the two points is 2.67℃ / meter. The system identifies the spatial distribution characteristics of temperature changes by analyzing the gradient information of all adjacent nodes.

[0107] In one possible implementation, cubic spline interpolation can effectively fill the temperature gaps between monitoring points.

[0108] For example, given the temperature values ​​of four corner sensors (25.2℃, 26.8℃, 24.9℃, and 27.1℃), the temperature value at any point in the central region can be calculated using cubic spline interpolation. This interpolation method ensures the continuity and smoothness of the temperature field, avoiding abrupt data changes.

[0109] Understandably, the generation of the continuous temperature field distribution function provides crucial support for the thermal management of energy storage systems. Through this function, the system can predict temperature values ​​at any spatial location, identify potential hotspots, and provide a data foundation for optimizing heat dissipation strategies and issuing safety warnings. This global temperature monitoring capability significantly improves the safety and reliability of energy storage cabinet operation.

[0110] The technical solution provided in this application provides at least the following beneficial effects: This application discloses a temperature control method for energy storage cabinets based on big data. It uses a trained thermodynamic prediction model to predict the temperature information of the energy storage cabinet over a future period, providing important decision support for optimizing the thermal management strategy of the energy storage cabinet. This method can identify potential overheating risks in advance and trigger corresponding temperature control measures. Since the thermodynamic prediction model uses a long short-term memory neural network algorithm, trained by learning the heat distribution pattern inside the energy storage cabinet through historical temperature changes, the accuracy of the prediction results can be effectively guaranteed. Furthermore, this application can determine high-risk areas in the energy storage cabinet based on the prediction results and send enhanced cooling commands to these areas, instructing the target cooling units corresponding to the high-risk areas to increase their cooling load. This application can also obtain the cooling efficiency of the target cooling units. If the cooling efficiency is less than a preset efficiency, the preset cooling load of the target cooling unit is transferred to adjacent cooling units. This facilitates the rational allocation of cooling load among cooling units, ensuring the energy efficiency of the energy storage cabinet.

[0111] The foregoing primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] In an exemplary embodiment, this application also provides a control device. Figure 4 This is a schematic diagram illustrating the composition of the control device provided in an embodiment of this application. Figure 4As shown, the control device includes: an acquisition unit 401, a determination unit 402, and a control unit 403.

[0113] The acquisition unit 401 is used to acquire the first temperature information of the energy storage cabinet over a historical period and input the first temperature information into a trained thermodynamic prediction model to obtain the second temperature information for a future period. The thermodynamic prediction model is trained by using a long short-term memory neural network algorithm to learn the heat distribution pattern inside the energy storage cabinet through historical temperature changes. The determination unit 402 is used to determine the high-risk area in the energy storage cabinet based on the second temperature information. The temperature change rate of the high-risk area in the future period is greater than a preset change rate. The control unit 403 is used to send an enhanced cooling command to the high-risk area to instruct the target cooling unit corresponding to the high-risk area to increase the cooling load. The control unit 403 is also used to acquire the cooling efficiency of the target cooling unit and, if the cooling efficiency is less than the preset efficiency, transfer the preset cooling load of the target cooling unit to an adjacent cooling unit.

[0114] In one possible implementation, the acquisition unit 401 is specifically used to: acquire temperature information collected by temperature sensors at multiple monitoring points inside the energy storage cabinet, continuously record the temperature values ​​of each monitoring point through a preset data acquisition frequency, and obtain the first temperature information.

[0115] In one possible implementation, the second temperature information includes the temperature of each monitoring point in the future time period output by the thermodynamic prediction model. The determination unit 402 is specifically used to: calculate the temperature change of each monitoring point between adjacent time points through differential operation; if the temperature change of the monitoring point in a continuous time period is greater than the preset change rate, then the area corresponding to the monitoring point in the energy storage cabinet is determined as a high-risk area.

[0116] It should be noted that, Figure 4 The module division shown is illustrative and represents only one logical functional division; in actual implementation, other division methods are possible. For example, two or more functions can be integrated into a single processing module. These integrated modules can be implemented in hardware or as software functional units.

[0117] In an exemplary embodiment, this application also provides a computer-readable storage medium including software instructions that, when run on an electronic device, cause the electronic device to perform any of the methods provided in the above embodiments.

[0118] In an exemplary embodiment, this application also provides a computer program product containing computer execution instructions, which, when run on an electronic device, causes the electronic device to perform any of the methods provided in the above embodiments.

[0119] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer-executable instructions. When these computer-executable instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer-executable instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a solid-state disk (SSD), etc.

[0120] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0121] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0122] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for temperature control of an energy storage cabinet based on big data, characterized in that, The method includes: The first temperature information of the energy storage cabinet during a historical period is obtained, and the first temperature information is input into a trained thermodynamic prediction model to obtain the second temperature information for a future period. The thermodynamic prediction model is trained by using a long short-term memory neural network algorithm to learn the heat distribution pattern inside the energy storage cabinet through historical temperature changes. Based on the second temperature information, a high-risk area in the energy storage cabinet is determined; the temperature change rate of the high-risk area in the future time period is greater than a preset change rate. Send an enhanced cooling command to the high-risk area to instruct the target cooling unit corresponding to the high-risk area to increase the cooling load; The cooling efficiency of the target cooling unit is obtained. If the cooling efficiency is less than a preset efficiency, the preset cooling load of the target cooling unit is transferred to an adjacent cooling unit.

2. The method according to claim 1, characterized in that, The acquisition of the first temperature information of the energy storage cabinet over a historical time period includes: The temperature information collected by temperature sensors at multiple monitoring points inside the energy storage cabinet is obtained, and the temperature values ​​of each monitoring point are continuously recorded at a preset data acquisition frequency to obtain the first temperature information.

3. The method according to claim 2, characterized in that, The second temperature information includes the temperature of each monitoring point over a future time period output by the thermodynamic prediction model. The step of determining high-risk areas in the energy storage cabinet based on the second temperature information includes: The temperature change at each monitoring point between adjacent time points is calculated using differential calculation. If the temperature change at the monitoring point is greater than the preset rate of change over a continuous period of time, the area corresponding to the monitoring point in the energy storage cabinet is identified as the high-risk area.

4. The method according to claim 1, characterized in that, After sending the enhanced cooling command to the high-risk area, the method further includes: A distributed temperature sensor array is used to collect temperature data in various areas inside the energy storage cabinet, and the collected temperature data is transmitted to the central processing unit through the controller local area network bus protocol to obtain the current temperature field of the energy storage cabinet. Calculate the deviation between the current temperature field and the target temperature field. If the deviation is greater than a preset deviation, adjust the enhanced cooling command until the deviation is less than the preset deviation.

5. The method according to claim 4, characterized in that, The method involves using a distributed temperature sensor array to collect temperature data from various areas inside the energy storage cabinet, and transmitting the collected temperature data to the central processing unit via the controller area network bus protocol to obtain the current temperature field of the energy storage cabinet, including: A distributed temperature sensor array is used to collect temperature data in various areas inside the energy storage cabinet to obtain temperature data at each monitoring point. The temperature gap between monitoring points is numerically filled using cubic spline interpolation to generate a continuous temperature field distribution function, which is then used as the current temperature field of the energy storage cabinet.

6. A temperature control system for an energy storage cabinet based on big data, characterized in that, The system includes a control device, which includes an acquisition unit, a determination unit, and a control unit. The acquisition unit is used to acquire the first temperature information of the energy storage cabinet during a historical time period, and input the first temperature information into the trained thermodynamic prediction model to obtain the second temperature information for a future time period; the thermodynamic prediction model is trained by using a long short-term memory neural network algorithm to learn the heat distribution law inside the energy storage cabinet through historical temperature changes. The determining unit is used to determine the high-risk area in the energy storage cabinet based on the second temperature information; The rate of temperature change in the high-risk area during the future time period is greater than a preset rate of change. The control unit is used to send an enhanced cooling command to the high-risk area to instruct the target cooling unit corresponding to the high-risk area to increase the cooling load. The control unit is also configured to acquire the cooling efficiency of the target cooling unit, and if the cooling efficiency is less than a preset efficiency, transfer the preset cooling load of the target cooling unit to an adjacent cooling unit.

7. The system according to claim 6, characterized in that, The acquisition unit is specifically used for: The temperature information collected by temperature sensors at multiple monitoring points inside the energy storage cabinet is obtained, and the temperature values ​​of each monitoring point are continuously recorded at a preset data acquisition frequency to obtain the first temperature information.

8. The system according to claim 7, characterized in that, The second temperature information includes the temperature of each monitoring point over a future time period output by the thermodynamic prediction model. The determining unit is specifically used for: The temperature change at each monitoring point between adjacent time points is calculated using differential calculation. If the temperature change at the monitoring point is greater than the preset rate of change over a continuous period of time, the area corresponding to the monitoring point in the energy storage cabinet is identified as the high-risk area.

9. An electronic device, characterized in that, include: Processor and memory; The memory stores instructions that the processor can execute; When the processor is configured to execute the instructions, the electronic device performs the method as described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, The readable storage medium includes: software instructions; When the software instructions are executed in an electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-5.

Images