A method and system for dynamically balancing heat dissipation and power consumption of photovoltaic energy storage cabinets

Abstract

The present invention discloses a method and system for dynamically balancing the heat dissipation power consumption of a photovoltaic energy storage cabinet, belonging to the technical field of photovoltaic energy storage cabinets, and comprising: a temperature sensor network, a central control module, a heat dissipation device group, an energy management module and a user interface module; the temperature sensor network is deployed inside the photovoltaic energy storage cabinet and on key heating components to monitor and collect temperature data of each area in real time; the central control module is used to receive temperature data collected by the temperature sensor network, and identify abnormal temperature sensors after preprocessing the temperature data; a temperature prediction model is constructed to predict future temperature change trends, and a dynamic heat dissipation control strategy is generated according to the prediction results to realize intelligent regulation of the heat dissipation device group; the energy management module is used to monitor the energy consumption efficiency of the heat dissipation device group and determine whether to perform early warning processing on the heat dissipation device; the present application realizes the dynamic balanced configuration of the heat dissipation power consumption of the photovoltaic energy storage cabinet, optimizes the heat dissipation efficiency and reduces energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic energy storage cabinets, and more particularly to a method and system for dynamically balancing heat dissipation and power consumption of photovoltaic energy storage cabinets. Background Art

[0002] Photovoltaic power generation systems face problems such as unstable energy output and large grid load fluctuations during operation. In order to solve these problems, photovoltaic energy storage cabinets are used to intelligently store excess electrical energy and quickly release it when needed, thereby effectively balancing the grid load and improving the overall utilization rate of photovoltaic power generation. However, in actual applications, the heat dissipation problem of photovoltaic energy storage cabinets has become one of the key factors affecting their performance and life. Excessive temperature will not only increase the equipment failure rate, but also reduce the stability and reliability of the system, thereby affecting the economic benefits and long-term operating efficiency of the entire photovoltaic power generation system. Therefore, optimizing the heat dissipation design of photovoltaic energy storage cabinets is an important direction to improve their comprehensive performance.

[0003] The patent application with publication number CN118825491A discloses an intelligent control system for a photovoltaic energy storage cabinet, including a cabinet body, and also including: a battery mounting frame, which is fixedly connected to the cabinet body; a shielding door, which is rotatably connected to the cabinet body; and a ventilation mechanism, which is arranged on the cabinet body. The patent detects the temperature of multiple batteries through multiple temperature sensors, thereby improving the heat dissipation effect; however, it still fails to solve the problem of low heat dissipation efficiency and energy waste caused by abnormal temperature during the operation of the photovoltaic energy storage cabinet. Therefore, in order to overcome these limitations, the present invention proposes a method and system for dynamically balancing the heat dissipation power consumption of a photovoltaic energy storage cabinet. Summary of the invention

[0004] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a method and system for dynamically balancing the heat dissipation power consumption of a photovoltaic energy storage cabinet, which can realize the dynamic balancing configuration of the heat dissipation power consumption of the photovoltaic energy storage cabinet through intelligent monitoring and dynamic adjustment of the working state of the heat dissipation equipment, optimize the heat dissipation efficiency and reduce energy consumption.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balancing configuration system, comprising: a temperature sensor network, a central control module, a heat dissipation device group, an energy management module and a user interface module;

[0007] The temperature sensor network is deployed inside the photovoltaic energy storage cabinet and on key heat-generating components to monitor and collect temperature data in each area in real time;

[0008] The central control module is used to receive the temperature data collected by the temperature sensor network, perform data preprocessing on the temperature data, perform potential abnormal point detection, and then identify abnormal temperature sensors;

[0009] Build a temperature prediction model for abnormal temperature sensors to predict future temperature change trends, generate dynamic heat dissipation control strategies based on the prediction results, and issue instructions to the heat dissipation equipment group to achieve intelligent control of the heat dissipation equipment group;

[0010] The energy management module is used to monitor the energy consumption efficiency of the cooling equipment group and determine whether to issue early warning to the cooling equipment.

[0011] Specifically, the central control module includes a data processing unit, a data prediction unit and an instruction generation unit;

[0012] The data processing unit is used to mark the data source, group the data, and archive the data in time series order for the temperature data points in the temperature sensor received by the central control module to construct a temperature data set, and perform data preprocessing on the temperature data set;

[0013] The data prediction unit is equipped with an intelligent trend analysis strategy, which is used to perform model fitting on the temperature data set after data preprocessing and predict the temperature change trend. Based on the prediction results, it is determined whether to trigger a temperature warning.

[0014] The instruction generation unit is configured with a dynamic heat dissipation control strategy, which is used to determine the heat dissipation demand of the photovoltaic energy storage cabinet according to the temperature change trend of the temperature sensor and generate control instructions for the heat dissipation device group.

[0015] Specifically, the specific steps of the intelligent trend analysis strategy include:

[0016] Configure the potential anomaly threshold, perform preliminary anomaly detection on each temperature sensor corresponding to the temperature data set, and mark the temperature data point of the temperature sensor as a potential anomaly point when it exceeds the potential anomaly threshold. Obtain the timestamp of the potential anomaly point of each temperature sensor;

[0017] Configuring Observation Thresholds , starting from the timestamp of the potential abnormal point, intercept the temperature data of the time period where the observation threshold is located, and calculate the temperature growth rate of the potential abnormal point. The calculation formula is as follows:

[0018] ;

[0019] in, The timestamp is The temperature growth rate of the potential abnormal point, The timestamp is Temperature data, The value of is [ , ], The timestamp is Temperature data, The timestamp is Temperature data, The timestamp is Temperature data, is a non-negative weight coefficient.

[0020] Specifically, the specific steps of the intelligent trend analysis strategy also include:

[0021] The data search is performed according to the time series starting from the timestamp of the potential abnormal point. When the temperature data is detected to be lower than the temperature data of the potential abnormal point, the temperature data and its timestamp are output to calculate the temperature growth amplitude and temperature growth range of the potential abnormal point. The calculation formula is as follows:

[0022] ;

[0023] ;

[0024] in, The timestamp is The temperature increase, The timestamp is The temperature growth range, The timestamp is Temperature data, is the timestamp of the first temperature data below the potential anomaly point;

[0025] The temperature data of each temperature sensor is quantitatively evaluated for abnormality, and the abnormality evaluation index is constructed by combining the temperature growth rate, temperature growth amplitude and temperature growth range, namely:

[0026] ;

[0027] in, The timestamp is The abnormal evaluation index value of , and is a non-negative weight coefficient;

[0028] Configure an abnormal threshold. When the abnormal evaluation index value of a potential abnormal point is greater than the abnormal threshold, the temperature sensor where the potential abnormal point is located is marked as an abnormal sensor.

[0029] Specifically, the specific steps of the intelligent trend analysis strategy also include:

[0030] The temperature sensors marked as abnormal sensors are fitted with data to build a fitting model. The temperature prediction model is established by combining the historical temperature data of the current temperature sensor, the historical temperature data of the surrounding sensors and the input of the photovoltaic energy storage cabinet. The model formula is as follows:

[0031] ;

[0032] in, It is A temperature sensor at time Temperature data, It is A temperature sensor at time Temperature data, q∈[1,Q], It is around The adjacent temperature sensors are Temperature data, p∈[1,P], The photovoltaic energy storage cabinet is at the moment Input, is the error term, which is used to represent the error of the temperature prediction model. is the number of historical temperature data points used to fit the temperature prediction model, is the number of neighboring temperature sensors used to fit the temperature prediction model, is a constant term, is the regression coefficient associated with the historical temperature data, is the temperature dependence coefficient of the ambient temperature sensor, is the regression coefficient of the photovoltaic energy storage cabinet input;

[0033] Configure the prediction threshold and temperature threshold, predict the temperature data within the prediction threshold time range according to the fitted temperature prediction model, and determine whether the temperature data of the temperature sensor within the prediction threshold exceeds the temperature threshold based on the prediction result. If it exceeds the set temperature threshold, generate warning information and issue a warning.

[0034] Specifically, the specific steps of the dynamic heat dissipation control strategy include:

[0035] Configure the distance threshold to evaluate the relative position relationship between the temperature sensor and the heat sink. For each pair of temperature sensor and heat sink, calculate the distance between them. If the distance from the heat sink to the temperature sensor is less than or equal to the distance threshold, the heat sink is considered to match the current temperature sensor. If the same heat sink matches multiple temperature sensors, the temperature sensor is selected based on the nearest principle.

[0036] The operating status of the heat dissipation device that matches the temperature sensor with the warning is obtained, and the operating status of the matching heat dissipation device is adjusted according to the temperature data of the temperature sensor with the warning, that is:

[0037] ;

[0038] ;

[0039] in, It is a heat dissipation device At the moment The fan speed at It is a heat dissipation device At the moment Coolant flow rate at and Heat dissipation equipment The maximum adjustment range of fan speed and coolant flow, It is a heat dissipation device At the moment Temperature data at is the maximum allowable temperature, is the standard temperature during normal operation. It is a heat dissipation device At the moment The fan speed at It is a heat dissipation device At the moment Coolant flow rate at .

[0040] Specifically, the specific steps of the dynamic heat dissipation control strategy also include:

[0041] Monitor the temperature data of the temperature sensor in real time, calculate the temperature deviation from the prediction result of the temperature prediction model, and calculate the deviation growth rate based on the temperature deviation;

[0042] Configure the deviation speed threshold. If the deviation growth rate is greater than the deviation speed threshold, adjust the operating status of the cooling device to reduce the workload, that is:

[0043] ;

[0044] ;

[0045] in, It is an adjusted cooling device At the moment The fan speed at It is an adjusted cooling device At the moment Coolant flow rate at It's time The deviation growth rate when It is a heat dissipation device Set the fan speed during standard operation. It is a heat dissipation device The coolant flow rate during standard operation is set. and are the non-negative weights for fan speed and coolant flow adjustment, is the maximum value function;

[0046] If the deviation growth rate is less than or equal to the deviation rate threshold, the operating state of the matching heat dissipation device continues to be adjusted according to the temperature data of the temperature sensor that currently has a warning.

[0047] Specifically, the energy management module includes an energy consumption monitoring unit, which is configured with a device optimization strategy. The device optimization strategy monitors the energy consumption efficiency of the heat dissipation device group and evaluates the working performance of the heat dissipation device to determine whether to issue an early warning to the heat dissipation device.

[0048] Specifically, the specific steps of the equipment optimization strategy include:

[0049] Configure the collection cycle. When the temperature sensor triggers an early warning, obtain the operating status, power consumption and temperature data of the heat dissipation device matching the temperature sensor every other collection cycle.

[0050] According to the operating status, power consumption and temperature change of the heat dissipation equipment, the energy efficiency of the heat dissipation equipment is calculated, that is:

[0051] ;

[0052] in, It is a heat dissipation device At the moment Energy efficiency when It is a heat dissipation device At the moment Temperature data at This is the moment when the temperature sensor triggers the warning. It is a heat dissipation device At the moment Temperature data at It is a heat dissipation device At the moment Power consumption, It is a heat dissipation device At the moment Power consumption

[0053] Configure the efficiency threshold. When the heat dissipation device is adjusted to the standard working state, calculate its comprehensive energy consumption efficiency. If the comprehensive energy consumption efficiency of the heat dissipation device is less than the efficiency threshold, the heat dissipation device warning is triggered.

[0054] A method for dynamically balancing the heat dissipation power consumption of a photovoltaic energy storage cabinet comprises the following steps:

[0055] Step S1: Install temperature sensors inside the photovoltaic energy storage cabinet and on key heat-generating components, build a temperature sensor network, and monitor and collect temperature data of each area in real time;

[0056] Step S2: continuously collecting temperature data and transmitting it to the central control module via wired or wireless means;

[0057] Step S3: After data preprocessing, the temperature data received by the central control module is detected for potential abnormal points, and then the abnormal temperature sensor is identified. A temperature prediction model is constructed for the abnormal temperature sensor to predict the future temperature change trend, and whether to trigger a temperature warning is determined based on the prediction results.

[0058] Step S4: determining the heat dissipation demand of the photovoltaic energy storage cabinet according to the temperature change trend predicted by the temperature sensor, and generating control instructions for the heat dissipation device group;

[0059] Step S5: sending control instructions to the heat dissipation device group through the communication interface, including adjusting the fan speed and adjusting the liquid cooling pump;

[0060] Step S6: monitoring the energy efficiency of the heat dissipation equipment group and determining whether to perform early warning processing on the heat dissipation equipment;

[0061] Step S7: The current temperature data, system status and energy consumption are displayed in real time through the user interface, providing an intuitive monitoring interface; when an abnormal situation is detected, visual and auditory alarm signals are issued, and detailed fault information is provided.

[0062] Beneficial effects of the present invention:

[0063] 1. Reduce unnecessary energy consumption by adjusting the operating status of the cooling equipment, ensuring that energy consumption is minimized while meeting cooling requirements. Real-time monitoring and intelligent control of cooling equipment improves energy utilization efficiency and cooling effects, and avoids equipment damage caused by overheating.

[0064] 2. Through the temperature prediction model and anomaly detection mechanism, potential heat dissipation problems can be discovered in advance to avoid equipment damage caused by excessive temperature. The central control module can identify abnormal temperature sensors and generate early warning information, and promptly notify the operation and maintenance personnel to handle it to ensure the stable operation of the system.

[0065] 3. The user interface module provides an intuitive monitoring interface and alarm function, allowing operation and maintenance personnel to view temperature data, system status and energy consumption in real time. When an abnormal situation is detected, visual and auditory alarm signals are automatically issued, and detailed fault information is provided, which improves the convenience of operation and maintenance and the overall reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a structural schematic diagram of a photovoltaic energy storage cabinet heat dissipation power consumption dynamic balancing configuration system of the present invention;

[0067] Figure 2 A flowchart of the steps of the intelligent trend analysis strategy of the present invention;

[0068] Figure 3 A flow chart of the steps of the dynamic heat dissipation control strategy of the present invention;

[0069] Figure 4 A flow chart of the steps of the device optimization strategy of the present invention;

[0070] Figure 5 The present invention is a flow chart of a method for dynamically balancing the heat dissipation and power consumption of a photovoltaic energy storage cabinet. DETAILED DESCRIPTION

[0071] Example 1

[0072] See also Figure 1 ,This embodiment introduces a photovoltaic energy storage cabinet heat dissipation power consumption dynamic balancing configuration system, including: a temperature sensor network, a central control module, a heat dissipation device group, an energy management module and a user interface module;

[0073] The temperature sensor network is deployed inside the photovoltaic energy storage cabinet and on key heat-generating components to monitor and collect temperature data in each area in real time. Among them, key heat-generating components include: inverter, battery pack, controller; temperature sensors are installed at key locations inside the photovoltaic energy storage cabinet and on major heat-generating components to ensure full coverage and accurate monitoring. Temperature data is continuously collected and transmitted to the central control module via wired or wireless means.

[0074] The central control module is used to receive the temperature data collected by the temperature sensor network, standardize the received temperature data, filter and denoise the data, and improve the data quality. Use algorithms to analyze data and evaluate the relationship between current heat dissipation demand and energy consumption. Based on historical data and real-time data, predict future temperature change trends and formulate countermeasures in advance. Generate dynamic heat dissipation control strategies based on data analysis results. Send specific control instructions to the heat dissipation equipment group through the communication interface, such as adjusting the fan speed, adjusting the liquid cooling pump, etc., continuously monitor the heat dissipation effect, and adjust the dynamic heat dissipation control strategy according to the actual effect to optimize system performance.

[0075] The heat dissipation equipment group is deployed inside the photovoltaic energy storage cabinet. According to the command feedback from the central control module, the operating status of the heat dissipation equipment is adjusted in real time, including adjusting the fan speed and coolant flow to achieve effective heat dissipation. The heat dissipation equipment includes fans, liquid cooling pumps, and phase change materials.

[0076] The energy management module is used to monitor the energy efficiency of the cooling equipment group and determine whether to issue early warnings to the cooling equipment; and to promptly remind maintenance personnel to replace the cooling equipment to reduce energy waste;

[0077] The user interface module is used to provide functions such as photovoltaic energy storage cabinet status display, parameter setting, and fault alarm, which is convenient for operation and maintenance personnel to operate; it displays the current temperature data, system status and energy consumption in real time, and provides an intuitive monitoring interface; when an abnormal situation is detected, it sends out visual and auditory alarm signals to alert operators and provide detailed fault information.

[0078] Preferably, the central control module includes a data processing unit, a data prediction unit and an instruction generation unit;

[0079] The data processing unit is used to process and manage the temperature data received from the temperature sensor, and to mark each received temperature data point, including the timestamp and temperature sensor ID, to clarify the data source to ensure the traceability and accuracy of the data; and to group the temperature data according to preset standards or rules, for example, by sensor location, type or monitoring object, to facilitate subsequent analysis and processing. In addition, in order to maintain the timeliness and integrity of the data, the data processing unit will also archive the temperature data in the order of the time series to construct a structured temperature data set; and perform data preprocessing on the temperature data set, including data standardization, data filtering and denoising;

[0080] The data prediction unit is equipped with an intelligent trend analysis strategy, which is used to fit the model to the temperature data set after data preprocessing and predict the temperature change trend. According to the prediction results, it is determined whether to trigger the temperature warning to give an early warning and ensure that the system operates within a safe temperature range.

[0081] The instruction generation unit is configured with a dynamic heat dissipation control strategy, which is used to determine the heat dissipation demand of the photovoltaic energy storage cabinet according to the temperature change trend of the temperature sensor, and generate control instructions for the heat dissipation device group to adjust the working state of the heat dissipation device group;

[0082] See also Figure 2 , preferably, the specific steps of the intelligent trend analysis strategy include:

[0083] Configure potential anomaly thresholds and perform preliminary anomaly detection on each temperature sensor corresponding to the temperature data set. When the temperature data point of a temperature sensor exceeds the potential anomaly threshold, it is marked as a potential anomaly point, and the timestamp of the potential anomaly point of each temperature sensor is obtained. By setting the potential anomaly threshold, potential abnormal temperature data points can be effectively preliminarily screened out, helping to quickly locate equipment or sensors that may have problems.

[0084] Configuring Observation Thresholds , starting from the timestamp of the potential abnormal point, intercept the temperature data of the time period where the observation threshold is located, and calculate the temperature growth rate of the potential abnormal point. The calculation formula is as follows:

[0085] ;

[0086] in, The timestamp is The temperature growth rate of the potential abnormal point, The timestamp is Temperature data, The value of is [ , ], The timestamp is Temperature data, The timestamp is Temperature data, The timestamp is Temperature data, It is a non-negative weight coefficient used to balance the impact of instantaneous temperature change and temperature change within the observation threshold on the temperature growth rate of the abnormal point; by calculating the temperature growth rate, the trend of temperature change can be identified. If the growth rate is abnormal, it may be a precursor to equipment failure or other abnormal conditions.

[0087] The data search is performed according to the time series starting from the timestamp of the potential abnormal point. When the temperature data is detected to be lower than the temperature data of the potential abnormal point, the temperature data and its timestamp are output to calculate the temperature growth amplitude and temperature growth range of the potential abnormal point. The calculation formula is as follows:

[0088] ;

[0089] ;

[0090] in, The timestamp is The temperature increase, The timestamp is The temperature growth range, The timestamp is Temperature data, It is the timestamp of the temperature data that is first lower than the potential abnormal point. By calculating the growth rate and range, we can understand the characteristics of temperature anomalies in more detail and help determine whether there is equipment overheating or other potential risks.

[0091] The temperature data of each temperature sensor is quantitatively evaluated for abnormality, and the abnormality evaluation index is constructed by combining the temperature growth rate, temperature growth amplitude and temperature growth range, namely:

[0092] ;

[0093] in, The timestamp is The abnormal evaluation index value of , and It is a non-negative weight coefficient used to adjust the impact of different factors on the comprehensive evaluation index. By quantifying the impact of different factors, including the temperature growth rate, amplitude, and range, the abnormality of each temperature sensor is scored to provide a basis for subsequent decision-making.

[0094] Configure the abnormal threshold. If the abnormal evaluation index value of the potential abnormal point is greater than the abnormal threshold, the temperature sensor where the potential abnormal point is located is marked as an abnormal sensor, otherwise it is marked as a normal sensor. According to the abnormal evaluation index, it is more objective to determine which temperature sensors have a higher abnormal risk and warn of potential faults in advance.

[0095] The temperature sensors marked as abnormal sensors are fitted with data to build a fitting model. The temperature prediction model is established by combining the historical temperature data of the current temperature sensor, the historical temperature data of the surrounding sensors and the input of the photovoltaic energy storage cabinet. The model formula is as follows:

[0096] ;

[0097] in, It is A temperature sensor at time Temperature data, It is A temperature sensor at time Temperature data, q∈[1,Q], It is around The adjacent temperature sensors are Temperature data, p∈[1,P], The photovoltaic energy storage cabinet is at the moment Input, is the error term, which is used to represent the error of the temperature prediction model. is the number of historical temperature data points used to fit the temperature prediction model, is the number of neighboring temperature sensors used to fit the temperature prediction model, is a constant term, is the regression coefficient associated with the historical temperature data, is the temperature dependence coefficient of the ambient temperature sensor, is the regression coefficient of the photovoltaic energy storage cabinet input; through the temperature prediction model, the future temperature trend of the abnormal temperature sensor is accurately estimated, thereby helping to better manage and maintain the equipment.

[0098] Configure the prediction threshold and temperature threshold. According to the fitted temperature prediction model, predict the temperature data within the prediction threshold time range. According to the prediction results, determine whether the temperature data of the temperature sensor within the prediction threshold exceeds the temperature threshold. If it exceeds the set temperature threshold, generate warning information and issue a warning. The warning information includes the following: abnormal temperature value and prediction time, possible impact or failure risk, handling suggestions or recommended actions, including: reducing load, checking equipment, starting the cooling system, etc., and the identification of related equipment or sensors; the warning information is sent to relevant personnel through various channels, including email, SMS, App notification or real-time display on the dashboard. Through an accurate temperature prediction model, potential temperature anomaly risks can be predicted in advance, so that a warning is issued before the temperature reaches a dangerous level. Take appropriate measures before the temperature anomaly occurs to prevent damage to the photovoltaic energy storage cabinet or accidents. The combination of temperature threshold setting and temperature prediction model prediction makes the system more intelligent, able to respond in real time and reduce the occurrence of unexpected failures. Through prediction, maintenance and management work can be planned in advance, thereby improving the availability and overall stability of the photovoltaic energy storage cabinet. By implementing the early warning system, resources can be allocated more targeted. For example, when it is predicted that some temperature sensors have potential temperature anomalies, maintenance personnel can be dispatched for inspection first, without wasting time on other normal equipment. Temperature prediction and early warning can reduce the shutdown or damage of photovoltaic energy storage cabinets due to sudden high temperatures. Taking measures such as cooling or adjusting loads in advance can effectively avoid unexpected shutdowns and improve the working efficiency and working time of photovoltaic energy storage cabinets.

[0099] See also Figure 3 Preferably, the specific steps of the dynamic heat dissipation control strategy include:

[0100] Configure the distance threshold to evaluate the relative position relationship between the temperature sensor and the heat sink. For each pair of temperature sensors and heat sinks, calculate the distance between them. If the distance from a heat sink to a specific temperature sensor is less than or equal to the distance threshold, the heat sink is considered to match the current temperature sensor. If the same heat sink matches multiple temperature sensors, the temperature sensor is selected based on the nearest principle. By setting the distance threshold, ensure that the heat sink only matches the temperature sensor that is most relevant to it. By calculating the relative distance between the temperature sensor and the heat sink, ensure the rationality and accuracy of the matching relationship. When multiple temperature sensors match the same heat sink, give priority to the temperature sensor that is closest to the heat sink, avoiding redundant operations and ensuring accurate temperature feedback.

[0101] Obtain the operating status of the cooling device that matches the temperature sensor with the warning, including fan speed and coolant flow rate; by obtaining the warning signal of the temperature sensor and synchronously obtaining the operating status of the related cooling device, the necessary data support is provided for subsequent adjustment operations. Ensure that each cooling device is adjusted in real time according to the feedback of the temperature sensor.

[0102] For temperature sensors with warnings, dynamically adjust the fan speed and coolant flow rate according to the maximum adjustment range of the matching cooling device to effectively reduce the temperature and avoid overheating of the device. According to the temperature data of the temperature sensor with warnings, adjust the operating status of the matching cooling device, that is:

[0103] ;

[0104] ;

[0105] in, It is a heat dissipation device At the moment The fan speed at It is a heat dissipation device At the moment Coolant flow rate at and Heat dissipation equipment The maximum adjustment range of fan speed and coolant flow, It is a heat dissipation device At the moment Temperature data at is the maximum allowable temperature, is the standard temperature during normal operation. It is a heat dissipation device At the moment The fan speed at It is a heat dissipation device At the moment Coolant flow rate at .

[0106] Monitor the temperature data of the temperature sensor in real time and calculate the temperature deviation from the prediction result of the temperature prediction model, that is:

[0107] ;

[0108] in, It is a heat dissipation device At the moment The temperature deviation at It is a heat dissipation device At the moment Temperature prediction data at It is a heat dissipation device At the moment By calculating the deviation between the current temperature of the temperature sensor where the cooling device is located and the temperature prediction model in real time, it can quickly identify abnormal temperature fluctuations and determine whether further adjustments to the cooling system are needed. Deviation detection ensures the cooling system's ability to respond quickly to changes in the external environment and internal load.

[0109] Calculate the deviation growth rate based on the temperature deviation to obtain the temperature change trend. The deviation growth rate calculation formula is as follows:

[0110] ;

[0111] in, It's time The deviation growth rate when For the moment The temperature deviation at For the moment The temperature deviation at The calculation of the temperature deviation growth rate helps the system analyze the trend of temperature changes. If the deviation growth rate is too fast, it means that the temperature change trend is intensifying, so as to judge whether the working state of the heat dissipation equipment needs to be adjusted.

[0112] Configure the deviation speed threshold. If the deviation growth rate is greater than the deviation speed threshold, it indicates that the cooling device is effective and the temperature continues to drop. Then adjust the operating status of the cooling device to reduce the workload, that is:

[0113] ;

[0114] ;

[0115] in, It is an adjusted cooling device At the moment The fan speed at It is an adjusted cooling device At the moment Coolant flow rate at It is a heat dissipation device At the moment The fan speed at It is a heat dissipation device At the moment Coolant flow rate at It's time The deviation growth rate when It is a heat dissipation device Set the fan speed during standard operation. It is a heat dissipation device The coolant flow rate during standard operation is set. and are the non-negative weights for fan speed and coolant flow adjustment, respectively, which are used to control the adjustment amplitude of fan speed and coolant flow. Dynamically adjust the workload of the cooling device according to the deviation growth rate and the set deviation speed threshold. When the temperature drops significantly, reduce the device load and save energy. Specifically, reduce the fan speed or coolant flow to reduce the energy consumption of the cooling device and reduce the risk of overheating. By adjusting the non-negative weights, the adjustment amplitude of the fan speed and coolant flow can also be precisely controlled, so as to respond to temperature changes more accurately.

[0116] If the deviation growth rate is less than or equal to the deviation rate threshold, it indicates that the heat dissipation device is still in effect and the temperature has not dropped significantly. Then, the operating status of the matching heat dissipation device will continue to be adjusted according to the temperature data of the temperature sensor that currently has an early warning.

[0117] Preferably, the energy management module includes an energy consumption monitoring unit, which is configured with an equipment optimization strategy. The equipment optimization strategy is used to monitor the energy consumption efficiency of the heat dissipation equipment group and evaluate the working performance of the heat dissipation equipment to determine whether to issue an early warning to the heat dissipation equipment and replace the heat dissipation equipment with poor working performance to save energy and increase the service life of the photovoltaic energy storage cabinet;

[0118] See also Figure 4 Preferably, the specific steps of the equipment optimization strategy include:

[0119] Configure the collection cycle. When the temperature sensor triggers an early warning, obtain the operating status of the cooling device that matches the temperature sensor, as well as the power consumption and temperature data of its temperature sensor every other collection cycle. By configuring the collection cycle, ensure that the operating status, energy consumption and temperature data of the cooling device are monitored and recorded in real time when the temperature is too high. Periodic data collection provides sufficient data support for subsequent analysis and optimization, and helps to adjust the working status of the cooling device in a timely manner.

[0120] The energy efficiency of the heat dissipation device is calculated based on the operating status, power consumption, and temperature change of the heat dissipation device, which is used to quantify the relationship between the power consumed by the heat dissipation device and the actual temperature reduction, that is:

[0121] ;

[0122] in, It is a heat dissipation device At the moment Energy efficiency when It is a heat dissipation device At the moment Temperature data at This is the moment when the temperature sensor triggers the warning. It is a heat dissipation device At the moment Temperature data at It is a heat dissipation device At the moment Power consumption, It is a heat dissipation device At the moment By calculating the energy efficiency, the temperature reduction of the cooling device for each unit of power consumed during operation can be determined. This can be used to evaluate the working efficiency of the cooling device and provide a basis for subsequent energy efficiency optimization. If the energy efficiency is too low, it may mean that the operation of the cooling device is not ideal and needs to be adjusted or optimized.

[0123] Configure the efficiency threshold, and calculate the comprehensive energy efficiency of the heat dissipation device when it is adjusted to the standard working state, that is;

[0124] ;

[0125] in, It is a heat dissipation device The overall energy efficiency, It is a heat dissipation device When adjusting to the standard working state, if the cooling device If the comprehensive energy efficiency is less than the efficiency threshold, the cooling device warning is triggered to prompt the operator to check the cooling device or replace it. The calculation of the comprehensive energy efficiency helps evaluate the overall energy efficiency of the cooling device after it is adjusted to the standard working state. If the comprehensive energy efficiency is low, it means that the cooling device has not been able to effectively reduce the temperature or save electricity during the whole process, thus triggering an early warning to indicate that maintenance or replacement of the device may be required.

[0126] Preferably, the user interface module includes:

[0127] The system overview page is used to provide an overall status view of the entire system, helping operation and maintenance personnel to quickly understand the health of the system, including a real-time temperature graph, which is used to display the current temperature of each temperature sensor and the overall temperature status inside the photovoltaic energy storage cabinet. Different colors or icons are used to identify the safety, warning or fault status of the temperature. For example, green is normal, yellow is a warning, and red is a fault; Equipment status: used to display the operating status of the cooling device. For example, whether the fan is running and the speed; the flow rate of the liquid cooling pump, etc.; System energy efficiency, used to display the energy efficiency data of the current cooling device, such as fan speed, liquid cooling pump flow and energy efficiency, to help operation and maintenance personnel judge the working performance of the cooling device.

[0128] The temperature monitoring page is used to display detailed data of the temperature sensor, which is convenient for operation and maintenance personnel to comprehensively monitor the temperature of each key component, including: temperature trend chart, which shows the temperature change trend of each sensor over time through a line chart; temperature alarm and early warning, if the temperature of a sensor exceeds the set threshold, an alarm signal will be issued. The alarm information is displayed on the page, and detailed temperature data, early warning type and device location are provided; temperature analysis data is used to display the temperature change trend after analysis by the central control module, and predict future temperature changes to identify potential risks in advance.

[0129] The cooling device control page is used to allow operation and maintenance personnel to adjust the working status of the cooling device in real time or manually intervene in the working status of the cooling device, including: cooling device status display, which is used to display the working status of each cooling device, including the current fan speed, coolant flow, power consumption, etc.; manual control, which is used to provide manual control options, such as adjusting fan speed, liquid cooling pump flow, etc.

[0130] The energy efficiency monitoring and optimization page is used to monitor the energy consumption performance of cooling equipment and issue alarms for inefficient equipment, including: energy efficiency trend charts, which are used to display the energy efficiency changes of cooling equipment in different time periods through charts to help determine whether there is a problem of energy efficiency degradation; equipment optimization suggestions, which provide working efficiency analysis of cooling equipment based on equipment optimization strategies, identify which equipment may need to be replaced or optimized, and reduce energy waste; energy efficiency alarms, which are used to automatically issue warnings when the energy efficiency of a cooling device is lower than the preset threshold, and prompt operators to check the equipment; historical energy efficiency records, which are used to provide equipment energy efficiency change trends and optimization history, and help operation and maintenance personnel track the long-term performance of cooling equipment.

[0131] The fault alarm and diagnosis page is used to provide fault alarm and fault diagnosis functions to help operation and maintenance personnel locate and solve problems, including: fault log, which is used to display the system's fault records, including alarm type, timestamp, affected equipment and temperature data. Each fault record contains detailed diagnostic information to help quickly locate the problem; fault diagnosis suggestions, which are used to provide possible cause analysis for the fault based on temperature prediction and heat dissipation control strategies, and give repair or adjustment suggestions; fault alarm, if abnormal conditions such as overtemperature and equipment failure are detected, warnings will be issued through visual means, including: flashing red prompts, pop-up windows and alarm sounds, and operation and maintenance personnel can directly view detailed fault information and countermeasures through the page.

[0132] The system settings and parameter adjustment page is used to provide basic system parameter settings and customized adjustments to meet the needs of different application scenarios. It includes temperature threshold settings, which are used by operation and maintenance personnel to adjust various temperature alarm thresholds according to actual needs; energy efficiency optimization parameters, which are used by users to adjust energy efficiency related parameters in equipment optimization strategies according to actual conditions; early warning strategy settings, which are used to set the trigger conditions and notification methods of early warnings; system language and user management, which are used to provide system language settings, user authority management and other functions to facilitate the use of multi-user systems.

[0133] Example 2

[0134] See also Figure 5 This embodiment introduces a method for dynamically balancing the heat dissipation power consumption of a photovoltaic energy storage cabinet, and the specific steps include:

[0135] Step S1: Install temperature sensors inside the photovoltaic energy storage cabinet and on key heat-generating components, build a temperature sensor network, and monitor and collect temperature data of each area in real time;

[0136] Step S2: continuously collecting temperature data and transmitting it to the central control module via wired or wireless means;

[0137] Step S3: After data preprocessing, the temperature data received by the central control module is detected for potential abnormal points, and then the abnormal temperature sensor is identified. A temperature prediction model is constructed for the abnormal temperature sensor to predict the future temperature change trend, and whether to trigger a temperature warning is determined based on the prediction results.

[0138] Step S4: determining the heat dissipation demand of the photovoltaic energy storage cabinet according to the temperature change trend predicted by the temperature sensor, and generating control instructions for the heat dissipation device group;

[0139] Step S5: sending control instructions to the heat dissipation device group through the communication interface, including adjusting the fan speed and adjusting the liquid cooling pump;

[0140] Step S6: monitoring the energy efficiency of the heat dissipation equipment group and determining whether to perform early warning processing on the heat dissipation equipment;

[0141] Step S7: The current temperature data, system status and energy consumption are displayed in real time through the user interface, providing an intuitive monitoring interface; when an abnormal situation is detected, visual and auditory alarm signals are issued, and detailed fault information is provided.

[0142] Preferably, the specific steps of abnormal temperature sensor identification include:

[0143] Configure the potential anomaly threshold, perform preliminary anomaly detection on each temperature sensor corresponding to the temperature data set, and mark the temperature data point of the temperature sensor as a potential anomaly point when it exceeds the potential anomaly threshold. Obtain the timestamp of the potential anomaly point of each temperature sensor;

[0144] Configuring Observation Thresholds , starting from the timestamp of the potential abnormal point, intercept the temperature data of the time period where the observation threshold is located, and calculate the temperature growth rate of the potential abnormal point. The calculation formula is as follows:

[0145] ;

[0146] in, The timestamp is The temperature growth rate of the potential abnormal point, The timestamp is Temperature data, The value of is [ , ], The timestamp is Temperature data, The timestamp is Temperature data, The timestamp is Temperature data, is a non-negative weight coefficient;

[0147] The data search is performed according to the time series starting from the timestamp of the potential abnormal point. When the temperature data is detected to be lower than the temperature data of the potential abnormal point, the temperature data and its timestamp are output to calculate the temperature growth amplitude and temperature growth range of the potential abnormal point. The calculation formula is as follows:

[0148] ;

[0149] ;

[0150] in, The timestamp is The temperature increase, The timestamp is The temperature growth range, The timestamp is Temperature data, is the timestamp of the first temperature data below the potential anomaly point;

[0151] The temperature data of each temperature sensor is quantitatively evaluated for abnormality, and the abnormality evaluation index is constructed by combining the temperature growth rate, temperature growth amplitude and temperature growth range, namely:

[0152] ;

[0153] in, The timestamp is The abnormal evaluation index value of , and It is a non-negative weight coefficient, which is used to adjust the impact of different factors on the comprehensive evaluation index;

[0154] Configure an abnormal threshold. When the abnormal evaluation index value of a potential abnormal point is greater than the abnormal threshold, the temperature sensor where the potential abnormal point is located is marked as an abnormal sensor.

[0155] Preferably, the construction of the temperature prediction model includes:

[0156] The temperature sensors marked as abnormal sensors are fitted with data to build a fitting model. The temperature prediction model is established by combining the historical temperature data of the current temperature sensor, the historical temperature data of the surrounding sensors and the input of the photovoltaic energy storage cabinet. The model formula is as follows:

[0157] ;

[0158] in, It is A temperature sensor at time Temperature data, It is Temperature sensors at historical moments Temperature data, q∈[1,Q], It is around The adjacent temperature sensors are Temperature data, p∈[1,P], The photovoltaic energy storage cabinet is at the moment Input, is the error term, which is used to represent the error of the temperature prediction model. is the number of historical temperature data points used to fit the temperature prediction model, is the number of neighboring temperature sensors used to fit the temperature prediction model, is a constant term, is the regression coefficient associated with the historical temperature data, is the temperature dependence coefficient of the ambient temperature sensor, is the regression coefficient of the photovoltaic energy storage cabinet input.

[0159] Preferably, the specific steps of energy consumption efficiency monitoring include:

[0160] Configure the collection cycle. When the temperature sensor triggers an early warning, obtain the operating status, power consumption and temperature data of the heat dissipation device matching the temperature sensor every other collection cycle.

[0161] According to the operating status, power consumption and temperature change of the heat dissipation equipment, the energy efficiency of the heat dissipation equipment is calculated, that is:

[0162] ;

[0163] in, It is a heat dissipation device At the moment Energy efficiency when It is a heat dissipation device At the moment Temperature data at This is the moment when the temperature sensor triggers the warning. It is a heat dissipation device At the moment Temperature data at It is a heat dissipation device At the moment Power consumption, It is a heat dissipation device At the moment Power consumption

[0164] Configure the efficiency threshold. When the heat dissipation device is adjusted to the standard working state, calculate its comprehensive energy consumption efficiency. If the comprehensive energy consumption efficiency of the heat dissipation device is less than the efficiency threshold, the heat dissipation device warning is triggered.

[0165] Working principle and its effect:

[0166] A method and system for dynamically balancing the heat dissipation power consumption of a photovoltaic energy storage cabinet realizes real-time monitoring and intelligent control of the internal temperature of a photovoltaic energy storage cabinet by integrating a temperature sensor network, a central control module, a heat dissipation device group, an energy management module, and a user interface module. First, the temperature data is collected using a temperature sensor network deployed on key heat-generating components and transmitted to the central control module via wired or wireless means. The central control module preprocesses the received data and detects potential abnormal points. After identifying abnormal temperature sensors, it constructs a temperature prediction model to predict future temperature change trends and determine whether to trigger a temperature warning.

[0167] Based on these analysis results, the central control module generates a dynamic cooling control strategy and sends specific instructions to the cooling equipment group through the communication interface, such as adjusting the fan speed and coolant flow, to achieve intelligent control of the cooling equipment. At the same time, the energy management module monitors the energy efficiency of the cooling equipment group, evaluates its working performance, and issues early warning processing signals when necessary. The user interface module provides an intuitive monitoring interface that displays the current temperature data, system status, and energy consumption in real time, and issues visual and auditory alarm signals when an abnormality is detected, ensuring that operation and maintenance personnel can respond and handle problems in a timely manner.

[0168] By precisely adjusting the operating status of the heat dissipation equipment, it not only improves energy utilization efficiency and reduces unnecessary energy consumption, but also enhances the heat dissipation effect and ensures the stable operation of the photovoltaic energy storage cabinet. In addition, the intelligent management and early warning functions make operation and maintenance more convenient and effectively improve maintenance efficiency.

[0169] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balance configuration system, characterized in that: include: Temperature sensor network, central control module, cooling equipment group, energy management module and user interface module; The temperature sensor network is deployed inside the photovoltaic energy storage cabinet and on key heat-generating components to monitor and collect temperature data of each area in real time; The central control module is used to receive temperature data collected by the temperature sensor network, perform data preprocessing on the temperature data, perform potential abnormal point detection, and then identify abnormal temperature sensors; Build a temperature prediction model for abnormal temperature sensors to predict future temperature change trends, generate dynamic heat dissipation control strategies based on the prediction results, and issue instructions to the heat dissipation equipment group to achieve intelligent control of the heat dissipation equipment group; The energy management module is used to monitor the energy consumption efficiency of the heat dissipation equipment group and determine whether to perform early warning processing on the heat dissipation equipment; The central control module includes a data processing unit, a data prediction unit and an instruction generation unit; The data prediction unit is configured with an intelligent trend analysis strategy, which is used to perform model fitting on the temperature data set after data preprocessing and predict the temperature change trend, and determine whether to trigger a temperature warning based on the prediction result; The instruction generation unit is configured with a dynamic heat dissipation control strategy, which is used to determine the heat dissipation demand of the photovoltaic energy storage cabinet according to the temperature change trend of the temperature sensor and generate control instructions for the heat dissipation device group; The specific steps of the intelligent trend analysis strategy include: Configure the potential anomaly threshold, perform preliminary anomaly detection on each temperature sensor corresponding to the temperature data set, and mark the temperature data point of the temperature sensor as a potential anomaly point when it exceeds the potential anomaly threshold. Obtain the timestamp of the potential anomaly point of each temperature sensor; Configuring Observation Thresholds , starting from the timestamp of the potential abnormal point, intercept the temperature data of the time period where the observation threshold is located, and calculate the temperature growth rate of the potential abnormal point; The data search is performed according to the time series starting from the timestamp of the potential abnormal point. When the temperature data is detected to be lower than the temperature data of the potential abnormal point, the temperature data and its timestamp are output to calculate the temperature growth amplitude and temperature growth range of the potential abnormal point. The calculation formula is as follows: ； ； in, The timestamp is The temperature increase, The timestamp is The temperature growth range, The timestamp is Temperature data, is the timestamp of the first temperature data below the potential anomaly point; Perform an abnormal quantitative evaluation on the temperature data of each temperature sensor, and construct an abnormal evaluation index by combining the temperature growth rate, temperature growth amplitude and temperature growth range; Configure an abnormal threshold. When the abnormal evaluation index value of a potential abnormal point is greater than the abnormal threshold, the temperature sensor where the potential abnormal point is located is marked as an abnormal sensor. Configure an abnormal threshold. When the abnormal evaluation index value of a potential abnormal point is greater than the abnormal threshold, the temperature sensor where the potential abnormal point is located is marked as an abnormal sensor. Perform data fitting on the temperature sensors marked as abnormal sensors, build a fitting model, and combine the historical temperature data of the current temperature sensor, the historical temperature data of the surrounding sensors, and the input of the photovoltaic energy storage cabinet to establish a temperature prediction model; Configure the prediction threshold and temperature threshold, predict the temperature data within the prediction threshold time range according to the fitted temperature prediction model, and determine whether the temperature data of the temperature sensor within the prediction threshold exceeds the temperature threshold based on the prediction result. If it exceeds the set temperature threshold, generate warning information and issue a warning.

2. A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balancing configuration system as claimed in claim 1, characterized in that: The calculation formula for the temperature growth rate of the potential abnormal point is as follows: ； in, The timestamp is The temperature growth rate of the potential abnormal point, The timestamp is Temperature data, The value of is [ , ], The timestamp is Temperature data, The timestamp is Temperature data, The timestamp is Temperature data, is a non-negative weight coefficient.

3. A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balancing configuration system as described in claim 2, characterized in that: The calculation formula of the abnormal evaluation index value is as follows: ； in, The timestamp is The abnormal evaluation index value of , and is a non-negative weight coefficient.

4. A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balancing configuration system as described in claim 3, characterized in that: The model formula of the temperature prediction model is as follows: ； in, It is A temperature sensor at time Temperature data, It is A temperature sensor at time Temperature data, q∈[1,Q], It is around The adjacent temperature sensors are Temperature data, p∈[1,P], The photovoltaic energy storage cabinet is at the moment Input, is the error term, which is used to represent the error of the temperature prediction model. is the number of historical temperature data points used to fit the temperature prediction model, is the number of neighboring temperature sensors used to fit the temperature prediction model, is a constant term, is the regression coefficient associated with the historical temperature data, is the temperature dependence coefficient of the ambient temperature sensor, is the regression coefficient of the photovoltaic energy storage cabinet input.

5. A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balancing configuration system as claimed in claim 1, characterized in that: The specific steps of the dynamic heat dissipation control strategy include: Configure the distance threshold to evaluate the relative position relationship between the temperature sensor and the heat sink. For each pair of temperature sensor and heat sink, calculate the distance between them. If the distance from the heat sink to the temperature sensor is less than or equal to the distance threshold, the heat sink is considered to match the current temperature sensor. If the same heat sink matches multiple temperature sensors, the temperature sensor is selected based on the nearest principle. The operating status of the heat dissipation device that matches the temperature sensor with the warning is obtained, and the operating status of the matching heat dissipation device is adjusted according to the temperature data of the temperature sensor with the warning, that is: ； ； in, It is a heat dissipation device At the moment The fan speed at It is a heat dissipation device At the moment Coolant flow rate at and Heat dissipation equipment The maximum adjustment range of fan speed and coolant flow, It is a heat dissipation device At the moment Temperature data at is the maximum allowable temperature, is the standard temperature during normal operation. It is a heat dissipation device At the moment The fan speed at It is a heat dissipation device At the moment Coolant flow rate at .

6. A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balancing configuration system as described in claim 5, characterized in that: The specific steps of the dynamic heat dissipation control strategy also include: Monitor the temperature data of the temperature sensor in real time, calculate the temperature deviation from the prediction result of the temperature prediction model, and calculate the deviation growth rate based on the temperature deviation; Configure the deviation speed threshold. If the deviation growth rate is greater than the deviation speed threshold, adjust the operating status of the cooling device to reduce the workload, that is: ； ； in, It is an adjusted cooling device At the moment The fan speed at It is an adjusted cooling device At the moment Coolant flow rate at It's time The deviation growth rate when It is a heat dissipation device Set the fan speed during standard operation. It is a heat dissipation device The coolant flow rate during standard operation is set. and are the non-negative weights for fan speed and coolant flow adjustment, is the maximum value function; If the deviation growth rate is less than or equal to the deviation rate threshold, the operating state of the matching heat dissipation device continues to be adjusted according to the temperature data of the temperature sensor that currently has a warning.

7. A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balance configuration system as claimed in claim 1, characterized in that: The energy management module includes an energy consumption monitoring unit, in which a device optimization strategy is configured. The device optimization strategy monitors the energy consumption efficiency of the heat dissipation device group and evaluates the working performance of the heat dissipation device to determine whether to issue an early warning to the heat dissipation device.

8. A photovoltaic energy storage cabinet heat dissipation power consumption dynamic balance configuration system as claimed in claim 7, characterized in that: The specific steps of the equipment optimization strategy include: Configure the collection cycle. When the temperature sensor triggers an early warning, obtain the operating status, power consumption and temperature data of the heat dissipation device matching the temperature sensor every other collection cycle. According to the operating status, power consumption and temperature change of the heat dissipation equipment, the energy efficiency of the heat dissipation equipment is calculated, that is: ； in, It is a heat dissipation device At the moment Energy efficiency when It is a heat dissipation device At the moment Temperature data at This is the moment when the temperature sensor triggers the warning. It is a heat dissipation device At the moment Temperature data at It is a heat dissipation device At the moment When power consumption, It is a heat dissipation device At the moment Power consumption Configure the efficiency threshold. When the heat dissipation device is adjusted to the standard working state, calculate its comprehensive energy consumption efficiency. If the comprehensive energy consumption efficiency of the heat dissipation device is less than the efficiency threshold, the heat dissipation device warning is triggered.

9. A method for dynamically balancing heat dissipation and power consumption of a photovoltaic energy storage cabinet, which is implemented based on a system for dynamically balancing heat dissipation and power consumption of a photovoltaic energy storage cabinet according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step S1: Install temperature sensors inside the photovoltaic energy storage cabinet and on key heat-generating components, build a temperature sensor network, and monitor and collect temperature data of each area in real time; Step S2: continuously collecting temperature data and transmitting it to the central control module via wired or wireless means; Step S3: After preprocessing the temperature data received by the central control module, potential abnormal point detection is performed to identify abnormal temperature sensors, and a temperature prediction model is built for the abnormal temperature sensors to predict future temperature change trends. Based on the prediction results, it is determined whether to trigger a temperature warning. Step S4: determining the heat dissipation demand of the photovoltaic energy storage cabinet according to the temperature change trend predicted by the temperature sensor, and generating control instructions for the heat dissipation device group; Step S5: sending control instructions to the heat dissipation device group through the communication interface, including adjusting the fan speed and adjusting the liquid cooling pump; Step S6: monitoring the energy efficiency of the heat dissipation equipment group and determining whether to perform early warning processing on the heat dissipation equipment; Step S7: Display the current temperature data, system status and energy consumption in real time through the user interface; when an abnormal situation is detected, issue visual and auditory alarm signals and provide fault information.

Images