Heat dissipation control method and system for network control cabinet

Abstract

The invention provides a heat dissipation control method and system for a network control cabinet, and belongs to the field of heat dissipation control, and the method comprises the steps: building a correlation model of the load and temperature of the network control cabinet according to the historical load of the network control cabinet and the corresponding historical temperature data, obtaining the current load data of the network control cabinet, inputting the load data into the correlation model to obtain a future temperature change trend of the network control cabinet; determining a heat dissipation control instruction according to the temperature change trend and a dynamic threshold value of the network control cabinet; and controlling heat dissipation equipment of the network control cabinet to dissipate heat of the network control cabinet according to the heat dissipation control instruction. According to the heat dissipation control method and system for the network control cabinet, the temperature trend of the network control cabinet can be predicted in advance according to the historical load data and the temperature data, countermeasures are accurately taken according to the temperature trend, the heat dissipation state of the network control cabinet is controlled in real time, and the stability of the network control cabinet is improved.

Description

Technical Field

[0001] The present application belongs to the field of heat dissipation control technology, and more specifically, relates to a heat dissipation control method and system for a network control cabinet. Background Art

[0002] With the continuous improvement of the level of factory intelligence, the stability of the network control cabinet, as the basic unit in the existing network physical architecture, is a key factor in ensuring the actual implementation of the industrial network. The installation environment of the network control cabinet is mainly in the production workshop. During the production process, a large amount of heat energy is required, which causes the temperature of the entire workshop to rise. The basic network equipment built inside the network control cabinet will also generate a lot of heat energy during long-term operation. The existing heat dissipation method cannot adjust the heat dissipation strategy according to the working status of the network control cabinet in real time, and the heat dissipation efficiency is low. The stability of the network control cabinet is easily affected by excessive temperature. Summary of the Invention

[0003] The purpose of this application is to provide a network control cabinet heat dissipation control method and system, so as to predict the temperature trend of the network control cabinet in advance based on historical load data and temperature data, make accurate response measures according to the temperature trend, control the heat dissipation status of the network control cabinet in real time, and improve the stability of the network control cabinet.

[0004] A first aspect of an embodiment of the present application provides a method for controlling heat dissipation in a network control cabinet, comprising: A correlation model between the network control cabinet load and temperature is constructed based on the historical load and corresponding historical temperature data of the network control cabinet. The current load data of the network control cabinet is obtained, and the load data is input into the correlation model to obtain the future temperature change trend of the network control cabinet. Determine heat dissipation control instructions based on temperature change trends and dynamic thresholds of the network control cabinet; The heat dissipation device of the network control cabinet is controlled according to the heat dissipation control instruction to dissipate heat for the network control cabinet.

[0005] A second aspect of an embodiment of the present application provides a network control cabinet heat dissipation control system, comprising: The temperature change acquisition module is used to build a correlation model between the network control cabinet load and temperature based on the historical load and corresponding historical temperature data of the network control cabinet, obtain the current load data of the network control cabinet, input the load data into the correlation model, and obtain the future temperature change trend of the network control cabinet; The heat dissipation instruction acquisition module is used to determine the heat dissipation control instruction according to the temperature change trend and the dynamic threshold of the network control cabinet; The heat dissipation control module is used to control the heat dissipation device of the network control cabinet to dissipate heat for the network control cabinet according to the heat dissipation control instruction.

[0006] According to a third aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned network control cabinet heat dissipation control method are implemented.

[0007] In a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned network control cabinet heat dissipation control method are implemented.

[0008] The beneficial effects of the network control cabinet heat dissipation control method and system provided by the embodiments of the present application are: the embodiments of the present application can accurately capture the temperature change pattern under different loads through the correlation model of load and temperature, so that the predicted trend is more in line with reality and the risk of overheating is avoided; the embodiments of the present application can reduce the heat dissipation intensity in advance according to the predicted temperature drop trend, and can also predict the temperature rise trend according to the load change rate, control and enhance the heat dissipation intensity in advance, dynamically adjust the heat dissipation control instructions, avoid resource waste, and save energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] Figure 1 A flow chart of a method for controlling heat dissipation in a network control cabinet according to an embodiment of the present application; Figure 2 A schematic diagram of the heat dissipation process of a network control cabinet provided in one embodiment of the present application; Figure 3 This is a structural block diagram of a network control cabinet heat dissipation control system provided in one embodiment of the present application; Figure 4 A schematic block diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0011] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0012] In order to make the purpose, technical solutions and advantages of this application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for controlling heat dissipation in a network control cabinet according to an embodiment of the present application. The method may include: S101: constructing a correlation model between the load and temperature of the network control cabinet based on the historical load and corresponding historical temperature data of the network control cabinet, obtaining the current load data of the network control cabinet, inputting the load data into the correlation model, and obtaining the future temperature change trend of the network control cabinet.

[0014] In this embodiment, the historical load data of the network control cabinet is decomposed into three load components: base load, periodic load, and burst load. Base load is the long-term average of the historical load data, periodic load is the peak load (for example, the daily peak period between 9:00 AM and 7:00 PM), and burst load is the instantaneous traffic peak. Based on these three load components, the temperature response delay and response sensitivity are calculated. Based on the load and temperature characteristics, a load-temperature correlation model is constructed, such as a long short-term memory (LSTM) model with a temporal attention mechanism.

[0015] A causal inference algorithm is used to filter out the load factors that affect temperature from historical data. The load factors are input into an LSTM model with a temporal attention mechanism. The model automatically focuses on the time periods that have a greater impact on the temperature and outputs the temperature change trend curve in the future time period.

[0016] This embodiment also includes dynamic verification and adaptive updating of the temperature trend curve. At preset intervals, the actual temperature of the control cabinet is compared with the predicted temperature to determine the temperature deviation. If the deviation is greater than 3°C for a preset number of consecutive times, the model's temporary correction function is triggered to adjust the predicted temperature. The preset interval can be 5 minutes, and the preset number of consecutive times can be 3.

[0017] For example, a causal inference algorithm revealed that the central processing unit (CPU) load of the main switch in the control cabinet accounts for 70%, the power supply output power accounts for 25%, and the backup equipment load accounts for 5%. This indicates that the main switch CPU load and power supply output power are the core factors affecting the temperature, while the impact of the backup equipment load is negligible. By inputting the time-varying characteristics of the main switch CPU load and power supply output power into the load-temperature correlation model, the temperature is predicted to rise from 36°C to 41°C over the next 20 minutes.

[0018] S102: Determine a heat dissipation control instruction according to a temperature change trend and a dynamic threshold of the network control cabinet.

[0019] In this embodiment, a preset basic threshold is set based on the hardware parameters of the network control cabinet. The preset basic threshold may be 40°C. A correction value is determined based on the health coefficient of the network control cabinet, the load fluctuation coefficient, and the ambient humidity. A dynamic threshold is determined based on the correction value and the preset basic threshold. The temperature change trend is quantified in multiple dimensions to determine parameters of the temperature change trend. These parameters include the slope of the temperature change trend, the trend persistence, and the predicted extreme value. The predicted extreme values ​​corresponding to different confidence values ​​are determined based on the slope of the temperature change trend and the trend persistence. The heat dissipation control instruction is determined based on the predicted extreme value and the dynamic threshold.

[0020] S103: Control the heat dissipation device of the network control cabinet according to the heat dissipation control instruction to dissipate heat for the network control cabinet.

[0021] In this embodiment, the heat dissipation control instructions specify the devices that require heat dissipation, such as the reverse-blade fan, semiconductor cooling plate, and water cooling head. The heat dissipation control instructions also determine the operating parameters of each heat dissipation device, such as the fan speed percentage, the power of the semiconductor cooling plate, and the water cooling flow rate. An infrared thermal imaging scanner monitors the temperature distribution thermogram of the network control cabinet in real time, monitors temperature changes in real time, and compares the temperature trend before executing the heat dissipation control instructions with the cooling effect after executing the heat dissipation control instructions. If the temperature drop does not reach the expected value within the preset time, the heat dissipation control instructions are strengthened to increase the speed of the reverse-blade fan and the cooling power of the semiconductor cooling plate.

[0022] From the above, it can be concluded that the embodiment of the present application quantifies the mapping relationship between load and temperature through the correlation model constructed by historical load data and historical temperature data, which can predict future temperature change trends in advance, so that heat dissipation control is transformed from passive response to active prevention; a step-by-step heat dissipation strategy is specified according to the temperature change trend, and the heat dissipation strategy is adjusted in real time according to the workload and temperature of the network control cabinet, which can effectively match the heat dissipation requirements and reduce the ineffective loss of equipment; this embodiment not only ensures the stable operation of the network control cabinet, but also achieves energy saving and consumption reduction and improves operation and maintenance efficiency.

[0023] In one embodiment of the present application, a three-dimensional dynamic threshold model is constructed based on the health coefficient, load fluctuation coefficient and ambient humidity of the network control cabinet to determine the dynamic threshold of the network control cabinet; Quantify temperature trends in multiple dimensions, determine parameters of temperature trends, and determine risk levels based on these parameters and dynamic thresholds. Parameters include the slope of the temperature trend, trend persistence, and predicted extreme values. Determine thermal control instructions based on risk level.

[0024] In this embodiment, a preset basic threshold for the network control cabinet is determined based on the hardware devices in the network control cabinet. The health coefficient of the network control cabinet ranges from 0 to 1, with 1 indicating the optimal health of the network control cabinet. The health coefficient of the network control cabinet is determined based on the operating time and the number of historical failures. The load fluctuation coefficient of the network control cabinet ranges from 0 to 1, with 1 indicating the maximum load fluctuation of the network control cabinet. The load fluctuation coefficient is determined based on the standard deviation and average load of the load over the past hour. The ambient humidity ranges from 0 to 1, with 1 indicating the highest humidity and lower heat dissipation efficiency. The ambient humidity of the network control cabinet is determined based on a linear mapping of temperature and humidity. A three-dimensional dynamic threshold model is constructed based on the health coefficient, load fluctuation coefficient, and ambient humidity to determine the dynamic threshold of the network control cabinet. This model includes: determining a corresponding correction value based on the health coefficient, load fluctuation coefficient, and ambient humidity to determine the temperature correction value. The temperature correction value is the sum of the health correction value, the load fluctuation correction value, and the ambient correction value. The dynamic threshold is the sum of the preset basic threshold and the temperature correction value.

[0025] Temperature trends are quantified across multiple dimensions to determine slope, trend persistence, and predicted extremes. A positive slope indicates warming, while a negative slope indicates cooling. Based on temperature trend parameters and dynamic thresholds, the risk level is divided into four ascending levels: Level 1, Level 2, Level 3, and Level 4.

[0026] In this embodiment, if the difference between the predicted extreme value and the dynamic threshold is greater than or equal to the first preset temperature value, the system is determined to be at the first risk level, meaning that the current temperature of the network control cabinet is far below the risk line for the second risk level. At this point, even short-term fluctuations will not reach the dynamic threshold, and the speed of the reverse-leaf fan is controlled to 30%. If the difference between the predicted extreme value and the dynamic threshold is greater than or equal to the second preset temperature value and less than or equal to the first predicted temperature value, the system is determined to be at the second risk level. At this point, the temperature is gradually rising but not approaching the dynamic threshold range. The speed of the reverse-leaf fan is controlled to 60%, and a medium-intensity cooling mode is activated. If the difference between the predicted extreme value and the dynamic threshold is less than or equal to the second predicted temperature value, the system is determined to be at the third risk level. At this point, the temperature is gradually rising and approaching the dynamic threshold with a clear upward trend. Continued temperature rise may exceed the dynamic threshold, and the reverse-leaf fan and semiconductor cooling plate are controlled to activate the enhanced cooling mode. If the predicted extreme value exceeds the third preset temperature value of the dynamic threshold, the system is determined to be at the fourth risk level, approaching the critical value of the network control cabinet's tolerance temperature. The speed of the reverse-leaf fan is controlled to 100%, and the highest level of cooling mode is activated.

[0027] For example, the first risk level is low risk, where the temperature is stable and there is no risk of exceeding the dynamic threshold. At this time, the positive-leaf fan can be controlled to operate normally, and the reverse-leaf fan speed can be controlled to 30% to maintain air circulation in the network control cabinet and avoid local heat accumulation; the semiconductor refrigeration plate and the water-cooling head can be controlled to be shut down. The second risk level is medium risk, where the temperature rises slowly but does not approach the dynamic threshold. If the second risk level is reached, the positive-leaf fan can operate normally, and the reverse-leaf fan speed can be controlled to 60% to speed up heat dissipation; the power of the semiconductor refrigeration plate is controlled to 30%, and the 1 / 2 refrigeration unit is started to assist in absorbing the heat transferred by the reverse-leaf fan. After absorbing the heat, the heat is transferred to the water-cooling head through the heating surface of the semiconductor refrigeration plate, and the heat is transferred to the outside of the network control cabinet through the water-cooling head and the circulating water pump. The third risk level is the medium-high risk level. The temperature is close to the dynamic threshold and has an obvious upward trend. At this time, the positive-blade fan operates normally, and the speed of the reverse-blade fan is controlled to 100% to maximize the air circulation and transfer heat to the semiconductor refrigeration plate; the power of the semiconductor refrigeration plate is controlled to 100%, and all refrigeration units are started. The heat transferred by the reverse-blade fan is absorbed by the cooling surface, and the heat generated by the semiconductor self-refrigeration plate is transferred to the water-cooled head through the heating surface. The circulating water pump cools the water-cooled head.

[0028] In one embodiment of the present application, the temperature change trend is quantified in multiple dimensions, the parameters of the temperature change trend are determined, and the risk level is determined based on the parameters and the dynamic threshold, including: The slope of the temperature change trend is determined by weighting each period of the segmented sliding window; The direction of the slope is verified by trend consistency. If the direction of the slope is consistent within a continuous preset period, the trend persistence is determined based on the direction of the slope. Based on trend persistence, the forecast extreme value is determined according to the multiple confidence levels of the long short-term memory network model; Determine the risk level based on predicted extreme values ​​and dynamic thresholds.

[0029] In this embodiment, the segmented sliding window is divided into several consecutive segmented sliding windows, each containing n data points (for example, n is 5, indicating a 5-minute window). The windows overlap by m data points to ensure continuity of the data trend. Weights are assigned to different time periods within each window, with the sum of the weights equal to 1. For each window, a linear equation representing the temperature over time is fitted using weighted least squares to determine the slope of each window. In this embodiment, the slope of the current temperature trend is determined by taking the average of the slopes of the three most recent consecutive windows to reduce the slope error caused by a single window.

[0030] The trend consistency check method is used to determine the trend persistence. The number of continuous verification cycles is set, that is, the slope direction of the continuous sliding window is verified, and the direction of the slope of each window is recorded. A positive slope indicates heating, a negative slope indicates cooling, and a slope of zero indicates stability. If the slope direction is consistent within the continuous preset period, the trend is determined to be persistent. The persistence value is the number of continuous sliding windows. If the direction of the slope alternates within the continuous preset period, the persistence is zero. In this embodiment, the consistent slope direction means that the slope is either positive or negative, that is, the slope direction within the continuous preset period is heating or cooling.

[0031] The multiple confidence levels in this embodiment include a first confidence value, a second confidence value, and a third confidence value, wherein the first confidence value is 95%, the second confidence value is 80%, and the third confidence value is 60%. Taking historical temperature data, the current slope, and trend persistence as input, the long-short-term memory network model outputs a temperature prediction curve for the future time period and the prediction values ​​corresponding to different confidence levels. If the trend persistence is ≥3, it indicates that the current trend is stable, and the prediction value corresponding to the first confidence value is used as the prediction extreme value; if 1≤trend persistence≤2, it indicates that the current trend is weak, and the prediction value corresponding to the second confidence value is used as the prediction extreme value; if the trend persistence is zero, the prediction value corresponding to the third confidence value is used as the prediction extreme value. The risk level is determined based on the prediction extreme value and the dynamic threshold.

[0032] In one embodiment of the present application, determining the risk level based on the predicted extreme value and the dynamic threshold includes: Determine the risk level based on the difference between the predicted extreme value and the dynamic threshold; If the difference between the dynamic threshold and the predicted extreme value is greater than or equal to the first preset temperature value, it is determined to be the first risk level; If the difference between the dynamic threshold and the predicted extreme value is greater than the second preset temperature value and less than the first preset temperature value, it is determined to be the second risk level; If the difference between the dynamic threshold and the predicted extreme value is less than or equal to the second preset temperature value, it is determined to be the third risk level; If the difference between the predicted extreme value and the dynamic threshold is greater than the third preset temperature value, it is determined to be the fourth risk level; the risks of the first risk level, the second risk level, the third risk level and the fourth risk level increase in sequence.

[0033] In this embodiment, the difference between the dynamic threshold and the predicted extreme value serves as the core condition for determining the risk level, while the slope and trend persistence serve as auxiliary conditions for determining the risk level. Specifically, if the core condition is that the difference between the dynamic threshold and the predicted extreme value is greater than or equal to a first preset temperature value, and the auxiliary conditions are that the slope is less than or equal to zero, and the trend persistence is greater than or equal to two cycles, then the risk level is determined to be the first risk level. If the core condition is that the difference between the dynamic threshold and the predicted extreme value is greater than a second preset temperature value and less than the first preset temperature value, and the auxiliary conditions are that the slope is in the range of 0-0.3°C / min, and the trend persistence is less than or equal to two cycles, then the risk level is determined to be the second risk level. If the core condition is that the difference between the dynamic threshold and the predicted extreme value is less than or equal to the second preset temperature value, and the auxiliary conditions are that the slope is in the range of 0.3-0.6°C / min, and the trend persistence is greater than or equal to two cycles, then the risk level is determined to be the third risk level. If the core condition is that the difference between the predicted extreme value and the dynamic threshold is greater than the third preset temperature value, and the auxiliary conditions are that the slope is greater than 0.6°C / min, and the trend persistence is greater than or equal to three cycles, then the risk level is determined to be the fourth risk level. This embodiment accurately divides risk levels based on the quantitative relationship between the predicted extreme value and the dynamic threshold, combined with the trend characteristics of temperature changes.

[0034] For example, if the first preset temperature value is set to 8°C, the second preset temperature value is set to 5°C, and the third preset temperature value is set to 3°C, and the dynamic threshold value of a network control cabinet is set to 40°C, the risk level is determined based on the predicted extreme value, slope, and trend persistence. If the predicted extreme value is 30°C, the slope is -0.2°C / min, and the trend persistence is 3 (indicating three consecutive cycles of temperature decrease), then the difference between the dynamic threshold value and the predicted extreme value is 10°C, which is greater than the first preset temperature value, the slope is less than zero, and the trend persistence is greater than 2. Therefore, the risk level of this network control cabinet is Level 1.

[0035] In one embodiment of the present application, a three-dimensional dynamic threshold model is constructed based on the health coefficient, load fluctuation coefficient, and ambient humidity of the network control cabinet to determine the dynamic threshold of the network control cabinet, including: Set the basic threshold of the network control cabinet; Based on the basic threshold, the dynamic threshold is determined according to the health coefficient of the network control cabinet, the load fluctuation coefficient and the weight coefficient corresponding to the ambient humidity.

[0036] In this embodiment, the preset basic threshold of the network control cabinet is set to 40°C, and the health coefficient H = 1-(a1×0.1)-(a2×0.2), where a1 is the value of the operating years (for example, if the operating years are two years, a1 is 2; if the operating years are five years, a1 is 5), and a2 is the number of serious failures; the load fluctuation coefficient F = b1 / b2, where b1 is the load standard deviation in the past hour, and b2 is the load average in the past hour; the ambient humidity M = c / 90%, where c is the actual humidity. The health coefficient H, load fluctuation coefficient F, and ambient humidity M are normalized and converted into dimensionless parameters. Weights are assigned based on the degree of impact of each parameter on temperature. In this embodiment, the health factor is weighted at 0.4, the load fluctuation factor is weighted at 0.3, and the ambient humidity is weighted at 0.3. A correction value is determined based on each parameter and its corresponding weight: correction value P = (1-H) × d1 × 0.4 + F × d2 × 0.3 + M × d3 × 0.3, where d1 is the health factor's impact, d2 is the load fluctuation factor's impact, and d3 is the ambient humidity factor's impact. The units of d1, d2, and d3 are °C (for example, d1 = 5°C means that the temperature threshold is corrected by 5°C for every unit change in health). A dynamic threshold is determined based on a preset base threshold and the correction value. The dynamic threshold is the sum of the preset base threshold and the correction value. In this embodiment, the dynamic threshold can be adjusted in real time based on device status, load fluctuation, and environmental changes, ensuring device safety while avoiding energy waste caused by excessive heat dissipation.

[0037] In one embodiment of the present application, after determining the dynamic threshold based on the basic threshold and according to the health coefficient of the network control cabinet, the load fluctuation coefficient, and the weight coefficient corresponding to the ambient humidity, the method further includes: Scan the network control cabinet with an infrared thermal imaging scanner to generate a temperature distribution thermogram; Determine the actual temperature of the network control cabinet based on the temperature distribution thermal map; Determine the deviation between the actual temperature of the network control cabinet and the dynamic threshold; The health coefficient of the network control cabinet, the load fluctuation coefficient, and the weights corresponding to the ambient humidity are adjusted according to the deviation, and the dynamic threshold is calibrated according to the adjusted weights.

[0038] In this embodiment, the infrared thermal imaging scanner is set at a distance of 1-1.5 meters from the network control cabinet, ensuring that the lens is facing the front of the cabinet of the network control cabinet; the infrared thermal imaging scanner is started, the preset acquisition interval is set to 10 seconds, and the acquisition is performed three times in succession. The temperature distribution thermodynamic map is generated based on the average results of the three scans. According to the temperature distribution thermodynamic map, the temperature values ​​of the core heating areas are screened out. The core heating areas include the main heating area, the heat dissipation key area, and the average temperature area on the surface of the cabinet. Weights are set for the temperatures of the three areas. For example, the main heating area is 60%, the heat dissipation key area is 30%, and the average temperature area is 10%. The actual temperature of the network control cabinet is determined based on each area and the corresponding weight of each area. The temperature deviation is determined based on the actual temperature and the dynamic threshold, and the weights corresponding to the health coefficient, load fluctuation coefficient, and ambient humidity are adjusted based on the temperature deviation, thereby dynamically calibrating the dynamic threshold.

[0039] In this embodiment, the actual temperature obtained through infrared thermal imaging can accurately reflect the actual heat dissipation status of the cabinet. After adjusting the weight in combination with the deviation, the dynamic threshold can be more in line with the actual operation risk of the equipment, avoiding insufficient heat dissipation or excessive energy consumption caused by unreasonable threshold setting.

[0040] For example, if the temperature deviation is ≤-3°C, it is determined that the dynamic threshold may be too high, the weights of the health coefficient and ambient humidity are reduced, and the weight of the load fluctuation coefficient is increased; if the temperature deviation is between -3 and 3°C, it is determined that the dynamic threshold is stable and no weight adjustment is required; if the temperature deviation is ≥+3°C, it is determined that the dynamic threshold may be too low, the weights of the health coefficient and ambient humidity are increased, and the weight of the load fluctuation coefficient is reduced.

[0041] In one embodiment of the present application, controlling a heat dissipation device of a network control cabinet to dissipate heat from the network control cabinet according to a heat dissipation control instruction includes: If the heat dissipation device fails, the emergency heat dissipation mode of the network control cabinet will be triggered, the compression refrigerator will be started to dissipate heat for the network control cabinet, and an emergency signal will be sent to the master control device.

[0042] In this embodiment, if any of the following situations occurs, it is determined that the heat dissipation device is faulty: The speed of the positive blade fan and the reverse blade fan is less than 30% of the rated value for 10 seconds; The power of the semiconductor refrigeration chip is zero and there is no current output, which is determined to be a power outage or a damage to the semiconductor refrigeration chip; The water cooling circulation flow rate is less than 50% of the rated value for 15 seconds, or a water leakage signal is detected.

[0043] If the heat dissipation device fails, the power supply to the faulty heat dissipation device will be cut off, triggering the emergency heat dissipation mode, sending a start signal to the compression refrigerator, and using the compression refrigerator to dissipate heat for the network control cabinet; during the heat dissipation process, an emergency signal will be sent to the master control device via Ethernet or wireless network. The emergency signal includes the type of faulty device, the time when the fault occurred, the actual temperature in the current cabinet, and the start status of the emergency mode.

[0044] refer to Figure 2 , a schematic diagram of the heat dissipation process of a network control cabinet according to one embodiment of the present application, wherein a straight-blade fan 21 is fixed inside the bottom vent of the network control cabinet 20, with its outlet facing upward within the cabinet. This ensures upward airflow when the fan is activated, driving heat from the bottom to the top. A reverse-blade fan 22 is fixed outside the top vent of the network control cabinet 20, with its air inlet connected to the top of the cabinet and its outlet connected to the cooling surface of the semiconductor cooling plate 23 via an air duct.

[0045] The heat inside the network control cabinet 20 is transported to the top of the network control cabinet 20 by the positive blade fan 21. The future temperature change trend of the network control cabinet 20 is determined according to the correlation model between the load and temperature of the network control cabinet 20. The dynamic threshold of the network control cabinet 20 is determined. According to the temperature change trend and the dynamic threshold, the current risk level of the network control cabinet 20 is determined to be the second risk level. At this time, the positive blade fan 21 is controlled to operate normally, and the speed of the reverse blade fan 22 is controlled to 60% to speed up the removal of heat from the top of the network control cabinet 20. The heat is transported to the semiconductor cooling plate 23 by the reverse blade fan 22. The cooling plate 23 is based on the Peltier effect. When direct current passes through a galvanic couple formed by two different semiconductor materials in series, heat is absorbed and released at both ends of the galvanic couple respectively. The heat transported by the reverse-blade fan 22 is absorbed by the cooling surface of the semiconductor cooling plate 23, and the heat released by the semiconductor cooling plate 23 is transported to the water cooling head 24. The water cooling head 24 is connected to the circulating water pump 25. The cold water 201 is transported to the water cooling head 24 through the circulating water pump 25 to cool the water cooling head 24. The hot water 202 generated in the cooling process of the water cooling head 24 is transported to the circulating water pump 25, and the hot water 202 is transported to the water reservoir through the circulating water pump 25.

[0046] Corresponding to the network control cabinet heat dissipation control method of the above embodiment, Figure 3 This is a structural block diagram of a network control cabinet heat dissipation control system provided by an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 3 The network control cabinet heat dissipation control system 30 includes: a temperature change acquisition module 31 , a heat dissipation instruction control module 32 and a heat dissipation control module 33 .

[0047] The temperature change acquisition module 31 is used to build a correlation model between the network control cabinet load and temperature based on the historical load and corresponding historical temperature data of the network control cabinet, obtain the current load data of the network control cabinet, input the load data into the correlation model, and obtain the future temperature change trend of the network control cabinet; The heat dissipation instruction acquisition module 32 is used to determine the heat dissipation control instruction according to the temperature change trend and the dynamic threshold of the network control cabinet; The heat dissipation control module 33 is used to control the heat dissipation device of the network control cabinet to dissipate heat for the network control cabinet according to the heat dissipation control instruction.

[0048] In one embodiment of the present application, the heat dissipation instruction acquisition module 32 is specifically configured to construct a three-dimensional dynamic threshold model based on the health coefficient, load fluctuation coefficient, and ambient humidity of the network control cabinet to determine the dynamic threshold of the network control cabinet; Quantify temperature trends in multiple dimensions, determine parameters of temperature trends, and determine risk levels based on these parameters and dynamic thresholds. Parameters include the slope of the temperature trend, trend persistence, and predicted extreme values. Determine thermal control instructions based on risk level.

[0049] In one embodiment of the present application, the heat dissipation instruction acquisition module 32 is further configured to determine the slope of the temperature change trend by weighting each time period of the segmented sliding window; The direction of the slope is verified by trend consistency. If the direction of the slope is consistent within a continuous preset period, the trend persistence is determined based on the direction of the slope. Based on the slope and trend persistence, the predicted extreme value is determined according to the multiple confidence levels of the long short-term memory network model; Determine the risk level based on predicted extreme values ​​and dynamic thresholds.

[0050] In one embodiment of the present application, the heat dissipation instruction acquisition module 32 is further configured to determine the risk level based on the difference between the predicted extreme value and the dynamic threshold; If the difference between the dynamic threshold and the predicted extreme value is greater than or equal to the first preset temperature value, it is determined to be the first risk level; If the difference between the dynamic threshold and the predicted extreme value is greater than the second preset temperature value and less than the first preset temperature value, it is determined to be the second risk level; If the difference between the dynamic threshold and the predicted extreme value is less than or equal to the second preset temperature value, it is determined to be the third risk level; If the difference between the predicted extreme value and the dynamic threshold is greater than the third preset temperature value, it is determined to be the fourth risk level; the risks of the first risk level, the second risk level, the third risk level and the fourth risk level increase in sequence.

[0051] In one embodiment of the present application, the heat dissipation instruction acquisition module 32 is further used to set a basic threshold value of the network control cabinet; Based on the basic threshold, the dynamic threshold is determined according to the health coefficient of the network control cabinet, the load fluctuation coefficient and the weight coefficient corresponding to the ambient humidity.

[0052] In one embodiment of the present application, the network control cabinet heat dissipation control system 30 further includes a dynamic threshold calibration module. A dynamic threshold calibration module is used to determine the dynamic threshold based on the basic threshold and the weight coefficient corresponding to the health coefficient of the network control cabinet, the load fluctuation coefficient, and the ambient humidity, and then scan the network control cabinet with an infrared thermal imaging scanner to generate a temperature distribution thermogram; Determine the actual temperature of the network control cabinet based on the temperature distribution thermal map; Determine the deviation between the actual temperature of the network control cabinet and the dynamic threshold; The health coefficient of the network control cabinet, the load fluctuation coefficient, and the weights corresponding to the ambient humidity are adjusted according to the deviation, and the dynamic threshold is calibrated according to the adjusted weights.

[0053] In one embodiment of the present application, the heat dissipation control module 33 is further used to trigger the emergency heat dissipation mode of the network control cabinet when the heat dissipation device fails, start the compression refrigerator to dissipate heat for the network control cabinet, and send an emergency signal to the master control device.

[0054] See also Figure 4 , Figure 4 This is a schematic block diagram of an electronic device provided in one embodiment of the present application. Figure 4 The electronic device 400 in the embodiment shown may include: one or more processors 401, one or more input devices 402, one or more output devices 403, and one or more memories 404. The processors 401, input devices 402, output devices 403, and memories 404 communicate with each other via a communication bus 405. The memory 404 is used to store computer programs, which include program instructions. The processor 401 is used to execute the program instructions stored in the memory 404. The processor 401 is configured to call the program instructions to execute the functions of the modules / units in the above-mentioned system embodiments, such as Figure 3 The functions of the temperature change acquisition module 31, the heat dissipation instruction acquisition module 32 and the heat dissipation control module 33 are shown.

[0055] It should be understood that in the embodiment of the present application, the processor 401 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0056] The input device 402 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 403 may include a display (LCD, etc.), a speaker, etc.

[0057] The memory 404 may include a read-only memory and a random access memory, and provides instructions and data to the processor 401. A portion of the memory 404 may also include a non-volatile random access memory. For example, the memory 404 may also store information such as load data and temperature change trends of the network control cabinet.

[0058] In a specific implementation, the processor 401, input device 402, and output device 403 described in the embodiment of the present application can execute the implementation method described in the network control cabinet heat dissipation control method provided in the embodiment of the present application, and can also execute the implementation method of the electronic device described in the embodiment of the present application, which will not be repeated here.

[0059] In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, all or part of the process of the method in the above embodiment is implemented. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above method embodiments are implemented. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or system capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0060] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned embodiments, such as the electronic device's hard drive or memory. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or is about to be output.

[0061] Those skilled in the art will appreciate that the modules / units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0062] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0063] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules, units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or modules / units, or can be electrical, mechanical or other forms of connection.

[0064] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units may be selected based on actual needs to achieve the objectives of the embodiments of the present application.

[0065] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing unit, or each module may exist physically separately, or two or more modules may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0066] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for controlling heat dissipation of a network control cabinet, characterized in that: include: Building a correlation model between the load and temperature of the network control cabinet based on the historical load and corresponding historical temperature data of the network control cabinet, obtaining the current load data of the network control cabinet, inputting the load data into the correlation model, and obtaining the future temperature change trend of the network control cabinet; Determining a heat dissipation control instruction based on the temperature change trend and the dynamic threshold of the network control cabinet; The heat dissipation device of the network control cabinet is controlled according to the heat dissipation control instruction to dissipate heat for the network control cabinet.

2. The heat dissipation control method of the network control cabinet according to claim 1, characterized in that: The determining of the heat dissipation control instruction according to the temperature change trend and the dynamic threshold of the network control cabinet includes: Constructing a three-dimensional dynamic threshold model based on the health coefficient, load fluctuation coefficient and ambient humidity of the network control cabinet to determine the dynamic threshold of the network control cabinet; quantifying the temperature change trend in multiple dimensions, determining parameters of the temperature change trend, and determining a risk level based on the parameters and the dynamic threshold, wherein the parameters include the slope of the temperature change trend, the persistence of the trend, and the predicted extreme value; A heat dissipation control instruction is determined according to the risk level.

3. The heat dissipation control method of the network control cabinet according to claim 2, characterized in that: The multi-dimensional quantification of the temperature change trend, determining parameters of the temperature change trend, and determining the risk level according to the parameters and the dynamic threshold include: Determining the slope of the temperature change trend by weighting each time period of the segmented sliding window; The direction of the slope is verified by trend consistency, and if the direction of the slope is consistent within a continuous preset period, the trend persistence is determined based on the direction of the slope; Determining a predicted extreme value based on the slope and the trend persistence according to multiple confidence levels of a long short-term memory network model; A risk level is determined based on the predicted extreme value and the dynamic threshold.

4. The heat dissipation control method of the network control cabinet according to claim 3, characterized in that: Determining the risk level according to the predicted extreme value and the dynamic threshold includes: determining a risk level according to a difference between the predicted extreme value and the dynamic threshold; If the difference between the dynamic threshold and the predicted extreme value is greater than or equal to a first preset temperature value, it is determined to be a first risk level; If the difference between the dynamic threshold and the predicted extreme value is greater than the second preset temperature value and less than the first preset temperature value, it is determined to be a second risk level; If the difference between the dynamic threshold and the predicted extreme value is less than or equal to the second preset temperature value, it is determined to be a third risk level; If the difference between the predicted extreme value and the dynamic threshold is greater than the third preset temperature value, it is determined to be the fourth risk level; the risks of the first risk level, the second risk level, the third risk level and the fourth risk level increase in sequence.

5. The heat dissipation control method of a network control cabinet according to claim 2, characterized in that: The three-dimensional dynamic threshold model is constructed based on the health coefficient, load fluctuation coefficient and ambient humidity of the network control cabinet to determine the dynamic threshold of the network control cabinet, including: Set the basic threshold of the network control cabinet; Based on the basic threshold, a dynamic threshold is determined according to a health coefficient of the network control cabinet, a load fluctuation coefficient, and a weight coefficient corresponding to the ambient humidity.

6. The heat dissipation control method of a network control cabinet according to claim 5, characterized in that: After determining the dynamic threshold based on the basic threshold and according to the health coefficient of the network control cabinet, the load fluctuation coefficient, and the weight coefficient corresponding to the ambient humidity, the method further includes: Scan the network control cabinet with an infrared thermal imaging scanner to generate a temperature distribution thermogram; determining the actual temperature of the network control cabinet according to the temperature distribution thermodynamic map; Determining a deviation between the actual temperature of the network control cabinet and the dynamic threshold; The health coefficient of the network control cabinet, the load fluctuation coefficient, and the weights corresponding to the ambient humidity are adjusted according to the deviation, and the dynamic threshold is calibrated according to the adjusted weights.

7. The heat dissipation control method of a network control cabinet according to claim 1, characterized in that: The step of controlling the heat dissipation device of the network control cabinet to dissipate heat for the network control cabinet according to the heat dissipation control instruction includes: If the heat dissipation device fails, the emergency heat dissipation mode of the network control cabinet is triggered, the compression refrigerator is started to dissipate heat for the network control cabinet, and an emergency signal is sent to the master control device.

8. A network control cabinet heat dissipation control system, characterized in that: include: A temperature change acquisition module is used to construct a correlation model between the load and temperature of the network control cabinet based on the historical load and corresponding historical temperature data of the network control cabinet, obtain the current load data of the network control cabinet, input the load data into the correlation model, and obtain the future temperature change trend of the network control cabinet; A heat dissipation instruction acquisition module, configured to determine a heat dissipation control instruction based on the temperature change trend and the dynamic threshold of the network control cabinet; The heat dissipation control module is used to control the heat dissipation device of the network control cabinet to dissipate heat for the network control cabinet according to the heat dissipation control instruction.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images