Efficient machine room approaching temperature control method

Abstract

The invention relates to the field of machine room temperature control, in particular to an efficient machine room approaching temperature control method, and the method comprises the steps: combining historical data prediction with real-time sensor data, and adaptively adjusting the state of a refrigeration system; the cabinet layout and the airflow path are dynamically optimized by using a thermal imaging technology; the air flow design is optimized through computational fluid dynamics, and an air door and a fan are intelligently controlled; heat recovery and renewable energy utilization are implemented, and the energy efficiency is improved; establishing a multi-stage redundant refrigeration system, and predicting and preventing faults; remote monitoring and automatic operation and maintenance are achieved by means of the Internet of Things and AI, accurate control over the temperature of the machine room is ensured, energy consumption is reduced, and operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of temperature control in a computer room, and in particular to a method for efficiently controlling the temperature of a computer room. Background Art

[0002] In modern data centers and computer rooms, cooling systems are a key component to ensure stable operation of equipment. With the rapid development of information technology, the scale of data centers and computer rooms continues to expand, and the equipment density and heat load have increased significantly, which has put forward higher requirements for the temperature control of computer rooms.

[0003] However, due to the lack of effective prediction and adaptive control mechanisms, the temperature of the computer room is easily affected by changes in the external environment and the operating status of internal equipment, resulting in large temperature fluctuations and control accuracy that is difficult to meet the operating requirements of high-density equipment. Summary of the invention

[0004] In order to realize intelligent, efficient and energy-saving temperature control of a computer room, the present application provides an efficient temperature control method for a computer room.

[0005] In a first aspect, the present application provides an efficient method for controlling the temperature of a computer room, comprising the following steps: S1: Predict the temperature change trend in the computer room based on historical data, combine it with real-time sensor data, adaptively adjust the prediction model, and adjust the working status of the cooling system in advance based on the prediction results; S2: Use thermal imaging technology to monitor the heat distribution of equipment in the room in real time, identify high heat density areas, dynamically adjust the cabinet layout and equipment configuration, disperse high heat density equipment, and optimize the airflow path; S3: Use computational fluid dynamics simulation to optimize the airflow design in the computer room, introduce intelligent dampers and adjustable speed fans, dynamically adjust the damper opening and fan speed according to real-time temperature and airflow requirements, and monitor the airflow status in real time through a sensor network; S4: Use a heat recovery system to recover the heat energy discharged from the computer room for other purposes, implement hot and cold aisle isolation, and use the heat energy of the hot aisle for energy recovery. Combined with renewable energy such as solar energy or geothermal energy, it can provide part or all of the energy needs of the computer room. S5: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, and predict potential failures by analyzing equipment operation data to perform maintenance in advance; S6: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time, implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms.

[0006] Optionally, predicting the temperature change trend in the computer room according to historical data, combining real-time sensor data, adaptively adjusting the prediction model, and adjusting the working state of the refrigeration system in advance according to the prediction result, includes the following steps: S11: Use deep neural networks to build prediction models; S12: Integrates multiple sensor data, including temperature, humidity, airflow speed, and device power consumption, for real-time data fusion; S13: dynamically adjusting the temperature control threshold according to the prediction result, and dynamically adjusting the temperature control threshold according to the prediction result to reduce temperature fluctuation; S14: Based on the prediction model and real-time data, intelligently decide the operation mode of the refrigeration system and automatically adjust the operating parameters of the refrigeration equipment.

[0007] Optionally, the real-time monitoring of the heat distribution of the equipment in the computer room by thermal imaging technology, identifying the high heat density area, dynamically adjusting the cabinet layout and equipment configuration, dispersing the high heat density equipment, and optimizing the airflow path includes the following steps: S21: Use machine vision and thermal imaging technology to intelligently identify the heat source distribution of equipment in the computer room and provide data support for heat source management; S22: Dynamically classify heat sources according to their intensity and distribution; S23: Based on heat source classification, intelligently adjust equipment layout, optimize airflow paths, and reduce mutual influence between heat sources; S24: Use heat pipes or heat exchangers to remove heat from high heat density areas and optimize the matching of heat sources and cooling systems.

[0008] Optionally, the method uses computational fluid dynamics simulation to optimize the airflow design in the computer room, introduces intelligent dampers and adjustable-speed fans, dynamically adjusts the damper opening and fan speed according to real-time temperature and airflow requirements, and monitors the airflow status in real time through a sensor network, including the following steps: S31: Optimize the airflow design in the computer room using computational fluid dynamics simulation; S32: Deploys intelligent dampers and adjustable speed fans to dynamically adjust according to real-time airflow requirements; S33: Real-time monitoring of temperature, humidity and air flow speed; S34: Combine the monitored temperature, humidity and airflow speed data and feed them back to the intelligent control system to automatically adjust the airflow management strategy.

[0009] Optionally, the heat recovery system is used to recover the heat energy discharged from the computer room for other purposes, implement cold and hot aisle isolation, and use the heat energy of the hot aisle for energy recovery, and combine with renewable energy such as solar energy or geothermal energy to provide part or all of the energy needs of the computer room, including the following steps: S41: Recover the heat energy discharged from the machine room for other purposes; S42: Combine renewable energy sources such as solar energy and geothermal energy to provide part or all of the energy needs of the computer room; S43: Establish an energy intelligent dispatching system to intelligently dispatch energy use based on real-time energy demand and the availability of renewable energy; S44: Optimize energy management through data analysis and machine learning.

[0010] Optionally, the establishment of a multi-level redundant refrigeration system, including a backup refrigeration unit and a backup power supply, predicting potential failures by analyzing equipment operation data, and performing maintenance in advance, includes the following steps: S51: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, to ensure stable operation of the system; S52: Use deep learning and big data analysis to predict equipment failures and perform maintenance in advance; S53: Implement regular system health checks; S54: Establish a rapid response mechanism to immediately initiate the intelligent recovery process once a fault is detected.

[0011] Optionally, the establishment of an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time, implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms includes the following steps: S61: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time; S62: Implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms; S63: Introducing virtual reality (VR) and augmented reality (AR) technologies to provide remote diagnosis and maintenance guidance for operation and maintenance personnel; S64: Combines big data analysis and AI algorithms to provide intelligent support for operation and maintenance decisions.

[0012] In a second aspect, the present application provides an efficient computer room temperature control system, comprising: The data acquisition and preprocessing module is used to collect real-time data from sensors in the computer room, including temperature, humidity and airflow parameters, and integrate historical data for data cleaning and preprocessing; Intelligent prediction and decision-making module, based on machine learning or deep learning algorithms, builds prediction models, analyzes historical data and real-time data, predicts the temperature change trend of the computer room, and intelligently generates cooling strategies based on the prediction results, including the start and stop of cooling equipment and parameter adjustment; The refrigeration system control module dynamically adjusts the operating status of the refrigeration system according to the strategy generated by the intelligent prediction and decision-making module, including controlling the start and stop of the refrigeration equipment, cooling capacity, wind speed, etc., to achieve precise temperature control; The system monitoring and optimization module monitors the performance of the refrigeration system in real time, including key indicators of temperature control accuracy and energy consumption, and continuously optimizes the prediction model and refrigeration strategy through a feedback mechanism.

[0013] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a high-efficiency temperature control method for a computer room as described in any one of the above items are implemented.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a high-efficiency computer room approach temperature control method as described in any one of the above items are implemented.

[0015] In summary, this application includes the following beneficial technical effects: 1. By adaptively adjusting the prediction model and adjusting the working status of the refrigeration system in advance, combined with thermal imaging technology and airflow optimization design, it can effectively respond to changes in the operating status of equipment in the computer room and the external environment, achieve precise temperature control, reduce temperature fluctuations, and provide a stable working environment for high-density equipment; 2. Using heat recovery systems and renewable energy, such as solar energy or geothermal energy, not only reduces the energy consumption of the computer room, but also realizes the recycling of energy, reduces operating costs, and reduces carbon emissions, which is in line with the development trend of green data centers; 3. Establish a multi-level redundant refrigeration system and an intelligent operation and maintenance platform based on the Internet of Things, which can monitor equipment status in real time, predict potential failures, implement remote control and automated operation and maintenance, significantly improve the system reliability and operation and maintenance efficiency, reduce downtime caused by equipment failures, and ensure the continuous and stable operation of the computer room. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of an efficient method for controlling the temperature of a computer room in an embodiment of the present application.

[0017] Figure 2 It is a flowchart of the sub-steps of step S1 in the embodiment of the present application.

[0018] Figure 3 It is a flowchart of the sub-steps of step S2 in the embodiment of the present application.

[0019] Figure 4 It is a flowchart of the sub-steps of step S3 in the embodiment of the present application.

[0020] Figure 5 It is a flowchart of the sub-steps of step S4 in the embodiment of the present application.

[0021] Figure 6 It is a flowchart of the sub-steps of step S5 in the embodiment of the present application.

[0022] Figure 7 It is a flowchart of the sub-steps of step S6 in the embodiment of the present application. DETAILED DESCRIPTION

[0023] The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] Reference Figure 1 The present application embodiment discloses an efficient temperature control method for a computer room, comprising the following steps: S1: Predict the temperature change trend in the computer room based on historical data, combine it with real-time sensor data, adaptively adjust the prediction model, and adjust the working status of the refrigeration system in advance based on the prediction results.

[0025] Reference Figure 2 , step S1 correspondingly includes the following sub-steps: S11: Use deep neural networks to build prediction models; S12: Integrates multiple sensor data, including temperature, humidity, airflow speed, and device power consumption, for real-time data fusion; S13: dynamically adjusting the temperature control threshold according to the prediction result, and dynamically adjusting the temperature control threshold according to the prediction result to reduce temperature fluctuation; S14: Based on the prediction model and real-time data, intelligently decide the operation mode of the refrigeration system and automatically adjust the operating parameters of the refrigeration equipment.

[0026] Correspondingly, for further refinement of the efficient temperature control method for computer rooms, the following is a specific example that details how to build a prediction model through a deep neural network, integrate multiple sensor data, and how to dynamically adjust the temperature control threshold and cooling system operation mode based on the prediction results.

[0027] S11: Use deep neural networks to build prediction models.

[0028] Example: Long short-term memory network (LSTM) is used as the core of the prediction model. LSTM is a special recurrent neural network (RNN) that can process time series data and capture long-term dependencies. Assume that there are multiple temperature sensors in the computer room, which collect data every 10 minutes, and the historical data set contains temperature records for the past year. The input of the LSTM model is the temperature sequence of the past 24 hours, and the output is the temperature forecast value for the next hour. When training the model, the mean square error (MSE) is used as the loss function, and the weights are adjusted through the back propagation algorithm to minimize the prediction error.

[0029] S12: Integrate data from multiple sensors for real-time data fusion.

[0030] Example: In addition to temperature sensors, the computer room is also equipped with humidity sensors, air flow velocity sensors, and equipment power consumption monitors. The real-time data fusion module receives real-time data from these sensors and converts multi-source data into a unified format for use in the prediction model through data preprocessing (such as missing value filling, outlier detection) and feature engineering (such as calculating average temperature and humidity change rate). For example, the calculation formula for humidity change rate is: [ \text{Humidity change rate} = \frac{\text{Current humidity} - \text{Previous humidity}}{\text{Time interval}} ] S13: Dynamically adjust the temperature control threshold according to the prediction result.

[0031] Example: Based on the prediction results of the LSTM model, if the predicted temperature exceeds the currently set temperature control threshold (for example, 25°C), the system will automatically adjust the threshold, for example, to 26°C, to reduce the overwork of the cooling system. If the predicted temperature is lower than the threshold, the threshold will be reduced accordingly, for example, to 24°C, to keep the room temperature within the ideal range. This dynamic adjustment mechanism can effectively reduce temperature fluctuations and improve the accuracy of temperature control.

[0032] S14: Intelligently decide the operation mode of the refrigeration system based on the prediction model and real-time data.

[0033] Example: Combining the output of the prediction model with real-time sensor data, the intelligent decision-making module can automatically adjust the operating parameters of the refrigeration equipment. For example, if the temperature is predicted to rise in the next hour, the system will increase the cooling capacity in advance by increasing the fan speed or starting the backup refrigeration unit. The specific algorithm can use fuzzy logic control to dynamically adjust the operating parameters of the refrigeration equipment based on the difference between the predicted temperature and the current temperature, as well as the temperature change rate. For example, if the difference between the predicted temperature and the current temperature is greater than 2°C, and the temperature change rate is greater than 0.5°C / hour, the system will automatically increase the fan speed to 80% of the maximum value.

[0034] Replay Figure 1 , after step S1, the following steps are included: S2: Use thermal imaging technology to monitor the heat distribution of equipment in the computer room in real time, identify high heat density areas, dynamically adjust the cabinet layout and equipment configuration, disperse high heat density equipment, and optimize the airflow path.

[0035] Reference Figure 3 , step S2 correspondingly includes the following sub-steps: S21: Use machine vision and thermal imaging technology to intelligently identify the heat source distribution of equipment in the computer room and provide data support for heat source management; S22: Dynamically classify heat sources according to their intensity and distribution; S23: Based on heat source classification, intelligently adjust equipment layout, optimize airflow paths, and reduce mutual influence between heat sources; S24: Use heat pipes or heat exchangers to remove heat from high heat density areas and optimize the matching of heat sources and cooling systems.

[0036] Correspondingly, for the detailed steps of heat source management in the efficient temperature control method of the computer room, the following is a specific example, which details how to use machine vision and thermal imaging technology to intelligently identify the distribution of heat sources, dynamically classify heat sources, intelligently adjust equipment layout, and optimize the matching of heat sources and cooling systems.

[0037] S21: Use machine vision and thermal imaging technology to intelligently identify the heat source distribution of equipment in the computer room.

[0038] Example: Install a thermal imaging camera in the machine room to capture the thermal distribution images of the equipment in real time. Use image processing algorithms such as edge detection and region segmentation to identify areas with high heat density. For example, use the Canny edge detection algorithm to identify the edge of the equipment, and then use connected region analysis to determine the specific location and range of the heat source. Assuming that the thermal imaging camera captures an image every 5 minutes, the system compares several consecutive frames of images to identify the dynamic changes of the heat source.

[0039] S22: Dynamically classify heat sources based on their intensity and distribution.

[0040] Example: Based on thermal imaging data, the system classifies heat sources into three levels: low, medium, and high. For example, if the temperature of the heat source is more than 5°C higher than the average temperature of the room, it is classified as "high"; between 3°C and 5°C is "medium"; and below 3°C is "low". This classification helps with subsequent equipment layout optimization and airflow path design.

[0041] S23: Based on heat source classification, intelligently adjust equipment layout and optimize airflow path.

[0042] Example: Based on the classification of heat sources, the system disperses high heat density equipment to avoid heat source concentration and reduce the heat island effect. For example, if there are multiple high heat density servers in the computer room, the system will recommend distributing them to different cabinets to optimize the airflow path. At the same time, through computational fluid dynamics (CFD) simulation, the airflow distribution under different layouts is analyzed to select the best layout solution. For example, CFD software is used to simulate the airflow velocity and temperature distribution under different equipment layouts, and the layout solution with the most uniform airflow distribution and the smallest temperature fluctuation is selected.

[0043] S24: Use heat pipes or heat exchangers to remove heat from high heat density areas and optimize the matching of heat sources and cooling systems.

[0044] Example: For areas with high heat density, the system will recommend installing heat pipes or heat exchangers to improve heat transfer efficiency. For example, if the heat density of a server cabinet is particularly high, a heat pipe can be installed inside the cabinet to quickly export the heat to the cooling system in the computer room. The working principle of the heat pipe is to use the internal liquid evaporation and condensation cycle to efficiently transfer heat. At the same time, the system will intelligently adjust the operating parameters of the cooling system, such as fan speed and coolant flow, according to the classification and distribution of the heat source, to achieve the best match between the heat source and the cooling system, improve cooling efficiency, and reduce energy consumption. Replay Figure 1 , after step S2, the following steps are also included: S3: Use computational fluid dynamics simulation to optimize the airflow design in the computer room, introduce intelligent dampers and adjustable-speed fans, dynamically adjust the damper opening and fan speed according to real-time temperature and airflow requirements, and monitor the airflow status in real time through a sensor network.

[0045] Reference Figure 4 , step S3 correspondingly includes the following sub-steps.

[0046] S31: Optimize the airflow design in the computer room using computational fluid dynamics simulation; S32: Deploys intelligent dampers and adjustable speed fans to dynamically adjust according to real-time airflow requirements; S33: Real-time monitoring of temperature, humidity and air flow speed; S34: Combine the monitored temperature, humidity and airflow speed data and feed them back to the intelligent control system to automatically adjust the airflow management strategy.

[0047] Correspondingly, for the detailed steps of airflow management in the efficient temperature control method of the computer room, the following is a specific example, which details how to use computational fluid dynamics (CFD) simulation to optimize the airflow design in the computer room, deploy smart dampers and adjustable speed fans, monitor environmental parameters in real time, and automatically adjust the airflow management strategy.

[0048] S31: Use computational fluid dynamics simulation to optimize the airflow design in the computer room.

[0049] Example: Use CFD software to simulate the airflow in the computer room and analyze the airflow distribution, temperature and humidity changes under different layouts. For example, by simulating different cabinet layouts, fan positions and damper openings, evaluate their impact on airflow paths, temperature uniformity and humidity control. CFD simulation can predict airflow velocity, pressure distribution and temperature field, helping designers optimize the layout of the computer room to ensure that the airflow effectively covers all equipment and avoids local overheating or overhumidification.

[0050] S32: Deploys intelligent dampers and adjustable speed fans to dynamically adjust based on real-time airflow requirements.

[0051] Example: Install smart dampers and adjustable-speed fans in the machine room, and monitor the airflow status in real time through the sensor network. Smart dampers can automatically adjust the opening according to the airflow demand, while adjustable-speed fans can dynamically adjust the speed according to the real-time airflow demand. For example, if the airflow speed in a certain area is lower than the preset value, the intelligent control system will automatically increase the opening of the damper in that area and increase the fan speed to increase the airflow supply and ensure uniform airflow distribution.

[0052] S33: Real-time monitoring of temperature, humidity and air flow rate.

[0053] Example: Deploy temperature, humidity, and airflow velocity sensors in the computer room to monitor environmental parameters in real time. Sensor data is transmitted to the intelligent operation and maintenance platform through IoT technology to achieve remote monitoring. For example, the temperature sensor collects data every 5 minutes, the humidity sensor collects data every 10 minutes, and the airflow velocity sensor collects data every 1 minute to ensure that the computer room environment status is grasped in real time.

[0054] S34: Combine the monitored temperature, humidity and airflow speed data and feed them back to the intelligent control system to automatically adjust the airflow management strategy.

[0055] Example: The intelligent control system receives real-time data from sensors and automatically adjusts the airflow management strategy based on CFD simulation results. For example, if the temperature in a certain area is monitored to rise, the system will automatically increase the fan speed in that area and adjust the damper opening to increase cooling airflow. If the humidity exceeds the preset value, the system will reduce the airflow speed in that area to reduce the spread of moisture. Through this closed-loop control mechanism, the intelligent control system can respond to environmental changes in real time and automatically adjust the airflow management strategy to ensure a stable computer room environment and improve energy efficiency.

[0056] Replay Figure 1 , after step S3, the following steps are also included.

[0057] S4: Use a heat recovery system to recover the heat energy discharged from the computer room for other purposes, implement hot and cold aisle isolation, and use the heat energy of the hot aisle for energy recovery. Combined with renewable energy such as solar energy or geothermal energy, it can provide part or all of the energy needs of the computer room.

[0058] Reference Figure 5 , step S4 correspondingly includes the following sub-steps.

[0059] S41: Recover the heat energy discharged from the machine room for other purposes; S42: Combine renewable energy sources such as solar energy and geothermal energy to provide part or all of the energy needs of the computer room; S43: Establish an energy intelligent dispatching system to intelligently dispatch energy use based on real-time energy demand and the availability of renewable energy; S44: Optimize energy management through data analysis and machine learning.

[0060] Correspondingly, for the detailed steps of energy management in the efficient temperature control method of the computer room, the following is a specific example, which details how to recycle the heat energy discharged from the computer room, combine it with renewable energy, establish an intelligent scheduling system, and optimize energy management through data analysis and machine learning.

[0061] S41: Recover the heat energy discharged from the machine room for other purposes.

[0062] Example: The cooling system of the computer room usually generates a lot of waste heat. By installing a heat recovery system, this part of the heat energy can be recovered and used for heating domestic water, heating or preheating the air intake, etc. For example, using a heat exchanger to transfer the waste heat from the cooling system to the domestic water system not only reduces the energy consumption of the computer room, but also reduces the energy cost of heating domestic water. The heat recovery efficiency can be calculated using the thermal efficiency formula of the heat exchanger: [\text{Heat recovery efficiency} = \frac{\text{Recovered heat}}{\text{Total heat discharged}} \times 100%] S42: Combine renewable energy sources such as solar energy and geothermal energy to provide part or all of the energy needs of the computer room.

[0063] Example: Install solar photovoltaic panels on the top of the computer room to use solar energy to provide electricity for the computer room. At the same time, consider the use of geothermal energy and provide cooling or heating for the computer room through the geothermal heat pump system. For example, the electricity generated by solar photovoltaic panels can be used first for the daily operation of the computer room, and the excess electricity can be stored in the battery pack or fed back to the power grid. The geothermal heat pump system can be used as a cooling source in summer and as a heat source in winter, providing a stable energy supply and reducing dependence on traditional energy.

[0064] S43: Establish an energy intelligent dispatching system to intelligently dispatch energy use based on real-time energy demand and the availability of renewable energy.

[0065] Example: By establishing an energy intelligent dispatching system, the energy demand of the computer room and the output of renewable energy are monitored in real time. For example, the system can predict the solar power generation in the next few hours, and intelligently dispatch energy use in combination with the energy demand of the computer room. If the solar power generation is predicted to be sufficient, the system will give priority to solar power while reducing the use of traditional energy. If the renewable energy supply is insufficient, the system will automatically switch to backup energy to ensure the stable operation of the computer room.

[0066] S44: Optimize energy management through data analysis and machine learning.

[0067] Example: Collect energy consumption data, renewable energy output data, and environmental parameter data from the computer room, analyze energy usage patterns through machine learning algorithms, predict energy demand, and optimize energy management strategies. For example, use time series prediction models (such as ARIMA or LSTM) to predict energy demand in the next few days, combine the predicted output of renewable energy, and plan energy scheduling in advance. Through continuous learning and optimization, the intelligent scheduling system can continuously improve energy efficiency and reduce energy costs.

[0068] Replay Figure 1 , after step S4, the following steps are also included.

[0069] S5: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, predict potential failures by analyzing equipment operation data, and perform maintenance in advance.

[0070] Reference Figure 6 , step S5 correspondingly includes the following sub-steps.

[0071] S51: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, to ensure stable operation of the system; S52: Use deep learning and big data analysis to predict equipment failures and perform maintenance in advance; S53: Implement regular system health checks; S54: Establish a rapid response mechanism to immediately initiate the intelligent recovery process once a fault is detected.

[0072] Correspondingly, for the detailed steps of system stability and fault prevention in the efficient temperature control method of the computer room, the following is a specific example, which details how to establish a multi-level redundant cooling system, use deep learning and big data analysis to predict equipment failures, implement regular system health checks, and establish a rapid response mechanism to ensure the stable operation of the computer room system and rapid recovery from faults.

[0073] S51: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, to ensure stable operation of the system.

[0074] Example: Install multiple cooling units in the computer room, with at least one as a backup to ensure that it can be started immediately when the main cooling unit fails to maintain the cooling needs of the computer room. At the same time, equip a backup power system, such as a diesel generator or an uninterruptible power supply (UPS), to cope with power grid failures. For example, when the main power is interrupted, the backup power system can automatically start within a few seconds to provide power to the cooling system to ensure that the temperature and humidity control of the computer room is not affected.

[0075] S52: Use deep learning and big data analysis to predict equipment failures and perform maintenance in advance.

[0076] Example: Collect the operating data of the equipment in the computer room, including parameters such as temperature, humidity, air flow speed, current, voltage, etc., analyze the operating status of the equipment through deep learning algorithms, and predict potential failures. For example, use convolutional neural networks (CNN) to analyze the vibration signals of the equipment, identify abnormal patterns, and predict bearing or fan failures. By performing maintenance in advance, system downtime caused by sudden equipment failures can be avoided, improving the stability and reliability of the computer room.

[0077] S53: Perform regular system health checks.

[0078] Example: Establish a regular system health check mechanism, including physical inspection and performance testing of equipment. For example, perform a monthly pressure test on the refrigeration system to check for refrigerant leaks; perform a quarterly load test on the power system to evaluate the backup power supply capacity. Through regular inspections, potential problems can be discovered and resolved in a timely manner to ensure that the system is in optimal condition.

[0079] S54: Establish a rapid response mechanism to immediately initiate the intelligent recovery process once a fault is detected.

[0080] Example: Establish a fault detection and response system to immediately start the intelligent recovery process once a device failure is detected. For example, if a refrigeration unit failure is detected, the system will automatically switch to the backup refrigeration unit and notify maintenance personnel to troubleshoot and repair the fault. Through the intelligent recovery process, the system can be quickly restored to operation, reducing the impact of the fault on the computer room. At the same time, the system records the fault information for subsequent fault analysis and prevention.

[0081] Replay Figure 1 , after step S5, the following steps are also included: S6: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time, implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms.

[0082] Reference Figure 7 , step S6 correspondingly includes the following sub-steps.

[0083] S61: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time; S62: Implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms; S63: Introducing virtual reality (VR) and augmented reality (AR) technologies to provide remote diagnosis and maintenance guidance for operation and maintenance personnel; S64: Combines big data analysis and AI algorithms to provide intelligent support for operation and maintenance decisions.

[0084] Correspondingly, for the detailed steps of intelligent operation and maintenance in the efficient temperature control method of the computer room, the following is a specific example, which details how to establish an intelligent operation and maintenance platform based on the Internet of Things, implement remote control and automated operation and maintenance, introduce virtual reality (VR) and augmented reality (AR) technologies, and combine big data analysis and AI algorithms to provide intelligent support for operation and maintenance decisions.

[0085] S61: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time.

[0086] Example: IoT sensors are deployed in the computer room to collect equipment operation data and environmental parameters, such as temperature, humidity, air flow speed, current, voltage, etc. These data are transmitted to the intelligent operation and maintenance platform in real time through IoT technology to achieve remote monitoring. For example, the platform can display the real-time status of each device, including operating time, load, fault alarm and other information, and provide real-time charts of environmental parameters to help operation and maintenance personnel fully understand the operation status of the computer room.

[0087] S62: Implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms.

[0088] Example: The intelligent operation and maintenance platform has a remote control function. The operation and maintenance personnel can remotely adjust the equipment parameters through the platform, such as fan speed, damper opening, temperature setting of the refrigeration unit, etc. At the same time, the platform integrates AI algorithms, which can automatically adjust equipment parameters according to real-time monitoring data and optimize the operating efficiency of the computer room. For example, the AI ​​algorithm can analyze the load and environmental parameters of the equipment and automatically adjust the operating mode of the refrigeration system to achieve the best energy efficiency ratio.

[0089] S63: Introducing virtual reality (VR) and augmented reality (AR) technologies to provide remote diagnosis and maintenance guidance for operation and maintenance personnel.

[0090] Example: Through VR and AR technology, maintenance personnel can diagnose and maintain equipment at remote locations. For example, using AR glasses, maintenance personnel can see the real-time status and fault information of the equipment, and obtain maintenance guidance, such as the steps to replace faulty parts, safe operating procedures, etc. Through VR technology, maintenance personnel can perform virtual equipment inspections and fault simulations to improve maintenance efficiency and safety.

[0091] S64: Combines big data analysis and AI algorithms to provide intelligent support for operation and maintenance decisions.

[0092] Example: The intelligent operation and maintenance platform collects a large amount of data, and provides intelligent support for operation and maintenance decisions through big data analysis and AI algorithms. For example, by analyzing the operation data of the equipment, the failure trend of the equipment is predicted, and maintenance is carried out in advance to avoid system downtime caused by sudden equipment failure. At the same time, AI algorithms can analyze the energy consumption of the computer room, optimize energy management strategies, and reduce operating costs.

[0093] This embodiment also provides a high-efficiency computer room temperature control system, including: The data acquisition and preprocessing module is used to collect real-time data from sensors in the computer room, including temperature, humidity and airflow parameters, and integrate historical data for data cleaning and preprocessing; Intelligent prediction and decision-making module, based on machine learning or deep learning algorithms, builds prediction models, analyzes historical data and real-time data, predicts the temperature change trend of the computer room, and intelligently generates cooling strategies based on the prediction results, including the start and stop of cooling equipment and parameter adjustment; The refrigeration system control module dynamically adjusts the operating status of the refrigeration system according to the strategy generated by the intelligent prediction and decision-making module, including controlling the start and stop of the refrigeration equipment, cooling capacity, wind speed, etc., to achieve precise temperature control; The system monitoring and optimization module monitors the performance of the refrigeration system in real time, including key indicators of temperature control accuracy and energy consumption, and continuously optimizes the prediction model and refrigeration strategy through a feedback mechanism.

[0094] This embodiment also provides an electronic device. The electronic device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an efficient method for approaching temperature control in a computer room is implemented: S1: Predict the temperature change trend in the computer room based on historical data, combine it with real-time sensor data, adaptively adjust the prediction model, and adjust the working status of the cooling system in advance based on the prediction results; S2: Use thermal imaging technology to monitor the heat distribution of equipment in the room in real time, identify high heat density areas, dynamically adjust the cabinet layout and equipment configuration, disperse high heat density equipment, and optimize the airflow path; S3: Use computational fluid dynamics simulation to optimize the airflow design in the computer room, introduce intelligent dampers and adjustable speed fans, dynamically adjust the damper opening and fan speed according to real-time temperature and airflow requirements, and monitor the airflow status in real time through a sensor network; S4: Use a heat recovery system to recover the heat energy discharged from the computer room for other purposes, implement hot and cold aisle isolation, and use the heat energy of the hot aisle for energy recovery. Combined with renewable energy such as solar energy or geothermal energy, it can provide part or all of the energy needs of the computer room. S5: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, and predict potential failures by analyzing equipment operation data to perform maintenance in advance; S6: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time, implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms.

[0095] When the computer program is executed by a processor, any one of the efficient computer room approach temperature control methods in the above method embodiments can be implemented.

[0096] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S1: Predict the temperature change trend in the computer room based on historical data, combine it with real-time sensor data, adaptively adjust the prediction model, and adjust the working status of the cooling system in advance based on the prediction results; S2: Use thermal imaging technology to monitor the heat distribution of equipment in the room in real time, identify high heat density areas, dynamically adjust the cabinet layout and equipment configuration, disperse high heat density equipment, and optimize the airflow path; S3: Use computational fluid dynamics simulation to optimize the airflow design in the computer room, introduce intelligent dampers and adjustable speed fans, dynamically adjust the damper opening and fan speed according to real-time temperature and airflow requirements, and monitor the airflow status in real time through a sensor network; S4: Use a heat recovery system to recover the heat energy discharged from the computer room for other purposes, implement hot and cold aisle isolation, and use the heat energy of the hot aisle for energy recovery. Combined with renewable energy such as solar energy or geothermal energy, it can provide part or all of the energy needs of the computer room. S5: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, and predict potential failures by analyzing equipment operation data to perform maintenance in advance; S6: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time, implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms.

[0097] When the computer program is executed by a processor, any one of the efficient computer room approach temperature control methods in the above method embodiments can be implemented.

[0098] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0099] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0100] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application is described in detail in the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An efficient temperature control method for a computer room, characterized in that: The following steps are involved: S1: Predict the temperature change trend in the computer room based on historical data, combine it with real-time sensor data, adaptively adjust the prediction model, and adjust the working status of the cooling system in advance based on the prediction results; S2: Use thermal imaging technology to monitor the heat distribution of equipment in the room in real time, identify high heat density areas, dynamically adjust the cabinet layout and equipment configuration, disperse high heat density equipment, and optimize the airflow path; S3: Use computational fluid dynamics simulation to optimize the airflow design in the computer room, introduce intelligent dampers and adjustable speed fans, dynamically adjust the damper opening and fan speed according to real-time temperature and airflow requirements, and monitor the airflow status in real time through a sensor network; S4: Use a heat recovery system to recover the heat energy discharged from the computer room for other purposes, implement hot and cold aisle isolation, and use the heat energy of the hot aisle for energy recovery. Combined with renewable energy such as solar energy or geothermal energy, it can provide part or all of the energy needs of the computer room. S5: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, and predict potential failures by analyzing equipment operation data to perform maintenance in advance; S6: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time, implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms.

2. According to claim 1, a high-efficiency computer room approach temperature control method is characterized in that: The method of predicting the temperature change trend in the computer room based on historical data, combining real-time sensor data, adaptively adjusting the prediction model, and adjusting the working state of the refrigeration system in advance based on the prediction results includes the following steps: S11: Use deep neural networks to build prediction models; S12: Integrates multiple sensor data, including temperature, humidity, airflow speed, and device power consumption, for real-time data fusion; S13: dynamically adjusting the temperature control threshold according to the prediction result, and dynamically adjusting the temperature control threshold according to the prediction result to reduce temperature fluctuation; S14: Based on the prediction model and real-time data, intelligently decide the operation mode of the refrigeration system and automatically adjust the operating parameters of the refrigeration equipment.

3. The high-efficiency temperature control method for a computer room according to claim 1, characterized in that: The method of using thermal imaging technology to monitor the heat distribution of equipment in the computer room in real time, identify high heat density areas, dynamically adjust the cabinet layout and equipment configuration, disperse the high heat density equipment, and optimize the airflow path includes the following steps: S21: Use machine vision and thermal imaging technology to intelligently identify the heat source distribution of equipment in the computer room and provide data support for heat source management; S22: Dynamically classify heat sources according to their intensity and distribution; S23: Based on heat source classification, intelligently adjust equipment layout, optimize airflow paths, and reduce mutual influence between heat sources; S24: Use heat pipes or heat exchangers to remove heat from high heat density areas and optimize the matching of heat sources and cooling systems.

4. The high-efficiency temperature control method for a computer room according to claim 1, characterized in that: The method uses computational fluid dynamics simulation to optimize the airflow design in the computer room, introduces intelligent dampers and adjustable speed fans, dynamically adjusts the damper opening and fan speed according to real-time temperature and airflow requirements, and monitors the airflow status in real time through a sensor network, including the following steps: S31: Optimize the airflow design in the computer room using computational fluid dynamics simulation; S32: Deploys intelligent dampers and adjustable speed fans to dynamically adjust according to real-time airflow requirements; S33: Real-time monitoring of temperature, humidity and air flow speed; S34: Combine the monitored temperature, humidity and airflow speed data and feed them back to the intelligent control system to automatically adjust the airflow management strategy.

5. The high-efficiency temperature control method for a computer room according to claim 1, characterized in that: The heat recovery system is used to recover the heat energy discharged from the computer room for other purposes, implement the isolation of hot and cold channels, and use the heat energy of the hot channel for energy recovery, and combine with renewable energy such as solar energy or geothermal energy to provide part or all of the energy needs of the computer room, including the following steps: S41: Recover the heat energy discharged from the machine room for other purposes; S42: Combine renewable energy sources such as solar energy and geothermal energy to provide part or all of the energy needs of the computer room; S43: Establish an energy intelligent dispatching system to intelligently dispatch energy use based on real-time energy demand and the availability of renewable energy; S44: Optimize energy management through data analysis and machine learning.

6. The high-efficiency temperature control method for a computer room according to claim 1, characterized in that: The establishment of a multi-level redundant refrigeration system, including a backup refrigeration unit and a backup power supply, predicting potential failures by analyzing equipment operation data and performing maintenance in advance, includes the following steps: S51: Establish a multi-level redundant refrigeration system, including backup refrigeration units and backup power supplies, to ensure stable operation of the system; S52: Use deep learning and big data analysis to predict equipment failures and perform maintenance in advance; S53: Implement regular system health checks; S54: Establish a rapid response mechanism to immediately initiate the intelligent recovery process once a fault is detected.

7. The high-efficiency temperature control method for a computer room according to claim 1, characterized in that: The establishment of an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time, implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms includes the following steps: S61: Establish an intelligent operation and maintenance platform based on the Internet of Things to monitor the operating status and environmental parameters of all equipment in the computer room in real time; S62: Implement remote control and automated operation and maintenance, and automatically adjust equipment parameters through AI algorithms; S63: Introducing virtual reality (VR) and augmented reality (AR) technologies to provide remote diagnosis and maintenance guidance for operation and maintenance personnel; S64: Combines big data analysis and AI algorithms to provide intelligent support for operation and maintenance decisions.

8. An efficient computer room approach temperature control system, characterized in that: include: The data acquisition and preprocessing module is used to collect real-time data from sensors in the computer room, including temperature, humidity and airflow parameters, and integrate historical data for data cleaning and preprocessing; Intelligent prediction and decision-making module, based on machine learning or deep learning algorithms, builds prediction models, analyzes historical data and real-time data, predicts the temperature change trend of the computer room, and intelligently generates cooling strategies based on the prediction results, including the start and stop of cooling equipment and parameter adjustment; The refrigeration system control module dynamically adjusts the operating status of the refrigeration system according to the strategy generated by the intelligent prediction and decision-making module, including controlling the start and stop of the refrigeration equipment, cooling capacity, wind speed, etc., to achieve precise temperature control; The system monitoring and optimization module monitors the performance of the refrigeration system in real time, including key indicators of temperature control accuracy and energy consumption, and continuously optimizes the prediction model and refrigeration strategy through a feedback mechanism.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of a high-efficiency computer room approach temperature control method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the high-efficiency computer room approach temperature control method as described in any one of claims 1 to 7 are implemented.

Images