Control method, system and equipment of data center air conditioner and medium

Abstract

The invention relates to a data center air conditioner control method, system and device and a medium. The method comprises the steps that internal environment data, device operation state data, standby energy state data and external climate data of a data center are obtained; comprehensively analyzing the environmental data, the equipment state data and the external climate data of the data center through a multiple data fusion algorithm, and inputting the data into a pre-trained temperature model for comparative analysis to obtain a temperature prediction result; acquiring the equipment priority of the data center, and dynamically generating a temperature adjustment scheme in combination with the temperature prediction result and the standby energy state data; and according to the temperature adjusting scheme, the operation mode and parameters of the data center air-conditioning system are adjusted. The method has the effect of improving the operation efficiency of the data center.

Description

Technical Field

[0001] The present application relates to the technical field of Internet information, and in particular to a control method, system, device and medium for air conditioning in a data center. Background Art

[0002] As the scale of data centers continues to expand, their energy consumption issues are becoming increasingly prominent. As one of the main energy-consuming devices in data centers, the operating efficiency of the air-conditioning system directly affects the energy consumption level and operating costs of the entire data center. Current data center air-conditioning control technology generally relies on a fixed threshold control method, that is, the air-conditioning equipment is started and stopped according to a preset temperature or humidity range. However, this method lacks the ability to perceive the dynamic changes in the load of equipment inside the data center, and is difficult to adapt to complex environmental fluctuations, which often leads to energy waste or inaccurate temperature control.

[0003] On the other hand, modern data centers usually introduce backup energy to cope with sudden power outages, but the existing technology has low efficiency in scheduling the use of backup energy and fails to achieve linkage optimization with the air conditioning system. In addition, external climate conditions also have a certain impact on the heat load inside the data center, and the existing air conditioning system is difficult to effectively integrate external climate data for comprehensive control.

[0004] The above-mentioned existing technical solutions have the following defects: the backup energy cannot be effectively combined with the operation scheduling of the air-conditioning system, and the energy utilization efficiency is low. Especially in the case of emergency power outage or energy shortage, resources cannot be allocated efficiently, so there is room for improvement. Summary of the invention

[0005] In order to improve the operating efficiency of a data center, the present application provides a control method, system, device and medium for air conditioning in a data center.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A control method for a data center air conditioner, the control method for a data center air conditioner comprising: Acquire the internal environment data, equipment operation status data, backup energy status data and external climate data of the data center; conduct a comprehensive analysis of the environment data, equipment status data and external climate data of the data center through a multiple data fusion algorithm, and input them into a pre-trained temperature model for comparison and analysis to obtain a temperature prediction result; Obtaining the equipment priority of the data center, combining the temperature prediction result and the backup energy status data, and dynamically generating a temperature adjustment plan; According to the temperature adjustment scheme, the operating mode and parameters of the data center air conditioning system are adjusted.

[0007] By adopting the above technical solutions, by obtaining the environmental data inside the data center, the operating status of the equipment, the status of the backup energy and the external climate data, it is possible to monitor and obtain key data sources in real time, which helps to provide rich and accurate information for the air-conditioning control system, and support more accurate temperature adjustment decisions and system optimization; by using multiple data fusion algorithms, comprehensive analysis of multiple data sources, including environmental data, equipment status and external climate data, it is possible to more accurately capture the impact of different factors on temperature control, which helps to improve the accuracy of temperature prediction and avoid the defect that a single data source cannot fully reflect environmental changes; these analysis results are input into the pre-trained temperature prediction model, and by comparing historical data and real-time Data can generate more reliable temperature predictions and provide a scientific basis for temperature control in advance; by obtaining equipment priority and combining temperature prediction results with backup energy status data, it can comprehensively consider the equipment load and energy utilization, which helps to dynamically generate the most optimized temperature adjustment plan, ensuring that energy is reasonably allocated while meeting temperature control needs, and maximizing resource utilization efficiency; by adjusting the operating mode and parameters of the air-conditioning system in real time according to the generated temperature adjustment plan, it helps to accurately control the environment inside the data center, ensure that environmental parameters such as temperature and humidity are maintained within the optimal range, avoid overheating or overcooling of equipment due to improper temperature control, reduce the occurrence of failures, and improve system stability.

[0008] In one example, the present application may be further configured as follows: the acquisition of the internal environment data, the equipment operation status data and the external climate data of the data center includes: Acquire the internal environmental data of the data center in real time through environmental sensors, wherein the internal environmental data includes temperature, humidity, air flow rate, heat load and equipment heat generation; Obtain the real-time power consumption, heat generation, operating load, equipment status and working time of each equipment in the data center through the equipment monitoring system; The external climate data is obtained, wherein the external climate data includes outdoor temperature and humidity, wind speed, and solar radiation intensity.

[0009] By adopting the above technical solutions, the internal environmental data of the data center can be fully acquired through environmental sensors, so that the environmental status of the data center can be grasped in real time, ensuring the accuracy and timeliness of the environmental data; the equipment monitoring system can be used to monitor each device in the data center in real time, and obtain data such as power consumption, heat generation, operating load, equipment status and working hours of key equipment, which helps to accurately grasp the operating status of the equipment, discover potential problems in time, and provide the necessary adjustment basis for the air-conditioning system; by collecting external climate data, it helps to comprehensively consider the impact of external climate conditions on the air-conditioning system of the data center and adjust the cooling strategy of the air-conditioning system.

[0010] In one example, the present application may be further configured as follows: before the environmental data of the data center, the equipment status data and the external climate data are comprehensively analyzed by the multiple data fusion algorithm and input into a pre-trained temperature model for comparison and analysis to obtain a temperature prediction result, the control method of a data center air conditioner further includes: Collecting historical environmental data, historical equipment status data, and external climate historical data of the data center, and forming a historical data set through data preprocessing; Based on the historical data set, a temperature prediction model is constructed and trained using a hybrid architecture of long short-term memory network and convolutional neural network; During the temperature prediction model training process, a genetic algorithm is used to perform hyperparameter optimization to obtain the pre-trained temperature model.

[0011] By adopting the above technical solutions, by collecting historical environmental data, equipment status data and external climate historical data, and organizing them into historical data sets through data preprocessing, it is helpful to establish a detailed historical data foundation, so that the temperature prediction model can be trained based on past environmental, equipment and climate changes, thereby providing a predictive basis for future temperature regulation; by combining the hybrid architecture of long short-term memory network and convolutional neural network, building and training the temperature prediction model based on historical data sets, it helps the model to effectively capture the temporal characteristics and spatial patterns in the data, thereby extracting valuable features from complex time series and multi-dimensional data, and accurately predicting future temperature change trends; by introducing genetic algorithms for hyperparameter optimization during the model training process, it helps to automatically adjust the model's hyperparameters, thereby improving the accuracy and performance of the temperature prediction model.

[0012] In one example, the present application may be further configured as follows: the environmental data of the data center, the equipment status data and the external climate data are comprehensively analyzed by a multiple data fusion algorithm, and input into a pre-trained temperature model for comparison and analysis, and the temperature prediction result obtained includes: Using a weighted fusion algorithm to perform weighted processing on the environmental data, the equipment status data and the external climate data to generate weighted data; Based on the weighted data, the correlation between various data sources is modeled using a Bayesian network to obtain a comprehensive analysis result; The comprehensive analysis result is input into the pre-trained temperature model, and the temperature prediction result is generated through multi-level nonlinear mapping.

[0013] By adopting the above technical solution, weighted processing of environmental data, equipment status data and external climate data is performed through a weighted fusion algorithm, which helps to assign different weights to different data sources according to their importance, thereby highlighting the data that has a greater impact on temperature prediction and improving the accuracy of data fusion; by using a Bayesian network to model the weighted data, it helps to capture and quantify the causal relationship and uncertainty between various data sources, thereby forming a comprehensive analysis framework based on probabilistic reasoning; by inputting the comprehensive analysis results into a pre-trained temperature model and processing them through multi-level nonlinear mapping, it helps to make more accurate temperature predictions for complex and nonlinear data. Multi-level nonlinear mapping can deeply explore the nonlinear relationship in the data and handle the complex interactions between different dimensions, thereby generating more accurate and detailed temperature prediction results.

[0014] In one example, the present application may be further configured as follows: the obtaining of the equipment priority of the data center, combining the temperature prediction result and the backup energy status data, and dynamically generating a temperature adjustment plan includes: Based on the equipment priority and the temperature prediction result, a comprehensive evaluation of the equipment working mode is performed through a multi-objective optimization algorithm to generate an evaluation result; Based on the evaluation result and in combination with the backup energy state data, the allocation plan of the backup energy is adjusted through a dynamic programming algorithm to generate the temperature adjustment plan.

[0015] By adopting the above technical solution and comprehensively evaluating the equipment priority and temperature prediction results through a multi-objective optimization algorithm, it is helpful to optimize the equipment's working mode and operation scheduling while meeting the needs of different equipment and the air-conditioning temperature regulation goals, thereby achieving efficient allocation and use of resources; adjusting the allocation plan of backup energy through a dynamic programming algorithm, combining the evaluation results with the backup energy status data, helps to flexibly adjust the allocation of backup energy in different time periods and different environmental conditions, optimize energy utilization efficiency, and ensure that the energy resources required for temperature regulation of the air-conditioning system are guaranteed.

[0016] In one example, the present application may be further configured as follows: the control method of a data center air conditioner further includes: monitoring the internal temperature, humidity and equipment status in real time during the operation of the air conditioning system, and adjusting the air conditioning operation mode through a feedback control mechanism; When the temperature adjustment of the air-conditioning system exceeds the preset safety range, a temperature alarm signal is generated and sent to the data center administrator through the cloud platform, enabling backup control measures or directly starting the protection mode of the air-conditioning system.

[0017] By adopting the above technical solution, real-time monitoring of internal temperature, humidity and equipment status can help obtain real-time data during the operation of the air-conditioning system, ensure timely understanding of changes in the environment and equipment, and dynamically adjust the operation mode of the air-conditioning through a feedback control mechanism based on these real-time data. The operation of the air-conditioning system can be automatically optimized according to changing environmental conditions, thereby maintaining a stable working environment, reducing energy consumption and improving system efficiency; by monitoring the temperature regulation of the air-conditioning system, it helps to immediately generate an alarm signal when the temperature is abnormal or exceeds the preset safety range, ensuring that relevant personnel can receive the alarm and respond in time, and sending the alarm signal to the data center administrator through the cloud platform can achieve remote real-time monitoring and response, so that the administrator can obtain alarm information and take countermeasures anywhere.

[0018] The second object of the invention is achieved by the following technical solutions: A control system for a data center air conditioner, the control system for a data center air conditioner comprising: A data acquisition module is used to acquire the internal environment data, equipment operation status data, backup energy status data and external climate data of the data center; A prediction module is used to comprehensively analyze the environmental data of the data center, the equipment status data and the external climate data through a multiple data fusion algorithm, and input them into a pre-trained temperature model for comparison and analysis to obtain a temperature prediction result; An adjustment scheme acquisition module is used to acquire the equipment priority of the data center, and dynamically generate a temperature adjustment scheme in combination with the temperature prediction result and the backup energy status data; The adjustment module is used to adjust the operation mode and parameters of the data center air conditioning system according to the temperature adjustment plan.

[0019] By adopting the above technical solutions, by obtaining the environmental data inside the data center, the operating status of the equipment, the status of the backup energy and the external climate data, it is possible to monitor and obtain key data sources in real time, which helps to provide rich and accurate information for the air-conditioning control system, and support more accurate temperature adjustment decisions and system optimization; by using multiple data fusion algorithms, comprehensive analysis of multiple data sources, including environmental data, equipment status and external climate data, it is possible to more accurately capture the impact of different factors on temperature control, which helps to improve the accuracy of temperature prediction and avoid the defect that a single data source cannot fully reflect environmental changes; these analysis results are input into the pre-trained temperature prediction model, and by comparing historical data and real-time Data can generate more reliable temperature predictions and provide a scientific basis for temperature control in advance; by obtaining equipment priority and combining temperature prediction results with backup energy status data, it can comprehensively consider the equipment load and energy utilization, which helps to dynamically generate the most optimized temperature adjustment plan, ensuring that energy is reasonably allocated while meeting temperature control needs, and maximizing resource utilization efficiency; by adjusting the operating mode and parameters of the air-conditioning system in real time according to the generated temperature adjustment plan, it helps to accurately control the environment inside the data center, ensure that environmental parameters such as temperature and humidity are maintained within the optimal range, avoid overheating or overcooling of equipment due to improper temperature control, reduce the occurrence of failures, and improve system stability.

[0020] The third objective of the present application is achieved through the following technical solutions: A computer device includes 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 the above-mentioned data center air conditioning control method are implemented.

[0021] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the control method of a data center air conditioner are implemented.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. By acquiring the environmental data inside the data center, the operating status of the equipment, the status of the backup energy, and the external climate data, it is possible to monitor and obtain key data sources in real time, which helps to provide rich and accurate information for the air conditioning control system, and supports more accurate temperature adjustment decisions and system optimization; by using multiple data fusion algorithms, comprehensive analysis of multiple data sources, including environmental data, equipment status, and external climate data, it is possible to more accurately capture the impact of different factors on temperature control, which helps to improve the accuracy of temperature prediction and avoid the defect that a single data source cannot fully reflect environmental changes; these analysis results are input into the pre-trained temperature prediction model, and by comparing historical data and real-time data, a more reliable temperature prediction can be generated, providing a scientific basis for temperature control in advance; 2. By obtaining the equipment priority and combining the temperature prediction results with the status data of the backup energy, the equipment load and energy utilization can be comprehensively considered, which helps to dynamically generate the most optimized temperature adjustment plan to ensure that energy is reasonably allocated while meeting the temperature control requirements and maximize resource utilization efficiency; by adjusting the operating mode and parameters of the air-conditioning system in real time according to the generated temperature adjustment plan, it helps to accurately control the environment inside the data center, ensure that environmental parameters such as temperature and humidity are maintained within the optimal range, avoid overheating or overcooling of equipment due to improper temperature control, reduce the occurrence of failures, and improve system stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a control method of a data center air conditioner in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S10 in a method for controlling a data center air conditioner in one embodiment of the present application; Figure 3 This is another implementation flow chart of step S20 in a method for controlling a data center air conditioner in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S20 in a method for controlling a data center air conditioner in one embodiment of the present application; Figure 5 This is a flowchart for implementing step S30 in a method for controlling a data center air conditioner in one embodiment of the present application; Figure 6 This is a flow chart of an implementation of a method for controlling a data center air conditioner in one embodiment of the present application; Figure 7 This is a principle block diagram of a control system for a data center air conditioner in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a control method for a data center air conditioner, which specifically includes the following steps: S10: Acquire the internal environment data, equipment operation status data, backup energy status data and external climate data of the data center.

[0026] Specifically, by arranging environmental sensors inside the data center, such as temperature sensors, humidity sensors, air flow rate sensors and heat load sensors, the temperature, humidity, air flow rate, heat load and equipment heat generation data inside the data center are collected in real time. The sensors transmit the real-time data to the data acquisition module through the network interface for processing; at the same time, the real-time power consumption, heat generation, operating load, equipment status and working hours of various equipment are obtained through the equipment monitoring system, and these data are transmitted to the centralized data processing platform through the equipment port of the monitoring system; for external climate data, meteorological monitoring equipment is used or the cooperative meteorological service interface is used to obtain outdoor temperature, humidity, wind speed and solar radiation intensity data, and these data are transmitted to the integrated system of the data center through regular or real-time updates for subsequent processing and analysis.

[0027] S20: Through multiple data fusion algorithms, the environmental data, equipment status data and external climate data of the data center are comprehensively analyzed and input into the pre-trained temperature model for comparison and analysis to obtain the temperature prediction results.

[0028] Specifically, the collected environmental data, equipment status data and external climate data are first preprocessed and standardized to ensure data format consistency; then, a weighted fusion algorithm is used to weight the data from different sources, where environmental data, equipment status data and climate data are assigned different weights according to their importance. For example, the weights of environmental data and equipment status data may be higher because they directly affect the temperature changes inside the data center, while the impact of external climate data is more indirect and the weight may be lower; then, a multiple data fusion algorithm is used to comprehensively analyze the weighted data to capture the intrinsic relationship between various types of data, and the data is input into a pre-trained temperature prediction model. The predicted temperature change results are obtained through comparative analysis, which can provide a basis for subsequent air-conditioning adjustments.

[0029] S30: Obtain the equipment priority of the data center, combine the temperature prediction results and the backup energy status data, and dynamically generate a temperature adjustment plan.

[0030] Specifically, first, the equipment groups are divided according to the importance and priority of different equipment in the data center. The equipment priority can be evaluated by the equipment's power consumption, operating status, and the magnitude of its impact on the overall temperature of the data center. For example, critical equipment that is sensitive to temperature may be given a higher priority, and vice versa. Based on the temperature prediction results and combined with backup energy status data, such as the operating status of backup generators or other energy facilities, a temperature adjustment plan is generated through a multi-objective optimization algorithm. The optimization goal is to ensure the normal operation of the equipment and save energy as much as possible, while ensuring that the indoor temperature is within the set range. This plan will be dynamically adjusted to adapt to changes in actual operating conditions.

[0031] S40: According to the temperature adjustment plan, adjust the operation mode and parameters of the data center air conditioning system.

[0032] Specifically, according to the generated temperature adjustment plan, the operating mode of the air-conditioning system may include heating, cooling or maintaining the current state. The target temperature is adjusted by adjusting the air-conditioning operating frequency, wind speed, temperature control strategy and other parameters. For example, if the temperature prediction results show that the indoor temperature will rise to the set upper limit, the indoor temperature is lowered by increasing the air-conditioning cooling power. In addition, other parameters of the air-conditioning operation, such as humidity control and air flow rate, are adjusted to further improve the adjustment efficiency.

[0033] By adopting the above technical solutions, by obtaining the environmental data inside the data center, the operating status of the equipment, the status of the backup energy and the external climate data, it is possible to monitor and obtain key data sources in real time, which helps to provide rich and accurate information for the air-conditioning control system, and support more accurate temperature adjustment decisions and system optimization; by using multiple data fusion algorithms, comprehensive analysis of multiple data sources, including environmental data, equipment status and external climate data, it is possible to more accurately capture the impact of different factors on temperature control, which helps to improve the accuracy of temperature prediction and avoid the defect that a single data source cannot fully reflect environmental changes; these analysis results are input into the pre-trained temperature prediction model, and by comparing historical data and real-time Data can generate more reliable temperature predictions and provide a scientific basis for temperature control in advance; by obtaining equipment priority and combining temperature prediction results with backup energy status data, it can comprehensively consider the equipment load and energy utilization, which helps to dynamically generate the most optimized temperature adjustment plan, ensuring that energy is reasonably allocated while meeting temperature control needs, and maximizing resource utilization efficiency; by adjusting the operating mode and parameters of the air-conditioning system in real time according to the generated temperature adjustment plan, it helps to accurately control the environment inside the data center, ensure that environmental parameters such as temperature and humidity are maintained within the optimal range, avoid overheating or overcooling of equipment due to improper temperature control, reduce the occurrence of failures, and improve system stability.

[0034] In one embodiment, if Figure 2 As shown, in step S10, the internal environment data, equipment operation status data and external climate data of the data center are obtained, specifically including: S11: The internal environment data of the data center is obtained in real time through environmental sensors. The internal environment data includes temperature, humidity, air flow rate, heat load and equipment heat generation.

[0035] Specifically, environmental sensors are arranged at multiple locations in the data center, especially near heat source equipment. The sensors obtain temperature, humidity, air flow rate, heat load and equipment heat generation data in real time. These sensors can use integrated temperature and humidity sensors, wind speed sensors, heat load sensors, etc., and send the measured data to the data acquisition module through a wireless or wired network. The data acquisition module will pre-process the collected data and transmit it to the data analysis module for subsequent data analysis and temperature adjustment solution generation.

[0036] S12: The real-time power consumption, heat generation, operating load, equipment status and working time of each equipment in the data center are obtained through the equipment monitoring system.

[0037] Specifically, the equipment monitoring system monitors the power consumption, heat generation, operating load, equipment status and working hours of each device in real time through power meters, thermal sensors and load monitoring devices installed on the data center equipment. The acquired data is transmitted to the central data platform through the device communication interface. These data can help determine the load and heat conditions of the equipment, and then analyze the source of temperature changes inside the data center.

[0038] S13: Acquire external climate data, which includes outdoor temperature and humidity, wind speed, and solar radiation intensity.

[0039] Specifically, monitoring is carried out using meteorological stations set up in the surrounding areas of the data center. The meteorological stations include temperature and humidity sensors, wind speed sensors, radiation intensity sensors, etc., which record outdoor temperature and humidity, wind speed, solar radiation intensity and other data in real time. These data help to evaluate the impact of external climate on the internal temperature of the data center and provide important input information for the temperature prediction model.

[0040] In one embodiment, if Figure 3 As shown, before step S20, that is, before the environmental data, equipment status data and external climate data of the data center are comprehensively analyzed by a multiple data fusion algorithm and input into a pre-trained temperature model for comparison and analysis to obtain a temperature prediction result, the control method of the data center air conditioner includes: S201: Collect historical environmental data, historical equipment status data and external climate historical data of the data center, and form a historical data set through data preprocessing.

[0041] Specifically, historical environmental data, equipment status data, and external climate data of the data center are collected through sensors in the data center. These data records may cover different time periods, such as data from the past few months or years. Through data preprocessing steps, including removing abnormal data, filling in missing data, and standardizing data formats, a historical data set that can be used for training is finally formed for the training of the temperature prediction model.

[0042] S202: Based on the historical data set, a temperature prediction model is constructed and trained using a hybrid architecture of long short-term memory network and convolutional neural network; Specifically, when processing historical data sets, a long short-term memory network is used to capture long-term dependencies in time series data, and a convolutional neural network is used to extract spatial features, such as using the formula: Slide on the input data to extract features, and by combining the two, build a hybrid architecture temperature prediction model that can handle the temporal and spatial nature of environmental data, optimize temperature prediction results, and improve the accuracy and robustness of the model. The training process uses batch processing technology to make training more efficient, and uses historical data sets to optimize the model so that it can provide accurate temperature predictions in actual operation.

[0043] S203: During the temperature prediction model training process, a genetic algorithm is used to perform hyperparameter optimization to obtain a pre-trained temperature model.

[0044] Specifically, the genetic algorithm is used to optimize the hyperparameters of the temperature prediction model during the training process, such as the number of neural network layers, learning rate, activation function type, etc. Through the selection, crossover, mutation and other operations of the genetic algorithm, the optimal hyperparameter combination is gradually searched to achieve the optimal prediction accuracy of the model; the optimization process is completed through multiple iterations, and the results of each generation of optimization will be compared with the previous generation, and finally a pre-trained temperature prediction model is obtained, which can adapt to different data inputs and generate accurate temperature prediction results.

[0045] In one embodiment, if Figure 4 As shown, in step S20, the environmental data, equipment status data and external climate data of the data center are comprehensively analyzed through a multiple data fusion algorithm, and input into a pre-trained temperature model for comparison and analysis to obtain a temperature prediction result, which specifically includes: S21: A weighted fusion algorithm is used to perform weighted processing on environmental data, equipment status data, and external climate data to generate weighted data.

[0046] Specifically, the data from different sources are weighted through the weighted fusion algorithm. In practical applications, environmental data may include information such as temperature, humidity, and air flow rate inside the data center. Equipment status data may involve parameters such as power consumption, heat generation, and operating load of each device. External climate data may include external temperature, humidity, wind speed and other meteorological data. The importance of each type of data to air-conditioning control may be different in different situations. For example, indoor temperature is more critical in air-conditioning control, while the impact of external climate data is smaller. Therefore, different weights are assigned to different data sources through the weighted fusion algorithm to generate weighted data.

[0047] S22: Based on the weighted data, the Bayesian network is used to model the relationship between various data sources to obtain comprehensive analysis results.

[0048] Specifically, after generating weighted data, the Bayesian network is used to model the association between various data sources. The Bayesian network establishes the causal relationship between different data sources by constructing a probability model, such as the correlation between temperature and humidity, the relationship between equipment power consumption and heat generation, etc., to obtain a comprehensive analysis result. The Bayesian network can model the interdependence of different factors based on conditional probability, so that when new environmental data is input, it can accurately infer potential influencing factors and conduct a comprehensive analysis.

[0049] S23: The comprehensive analysis results are input into a pre-trained temperature model, and a temperature prediction result is generated through multi-level nonlinear mapping.

[0050] Specifically, the comprehensive analysis results are input into a pre-trained temperature model, and multi-level nonlinear mapping is performed to generate temperature prediction results. Multi-level nonlinear mapping can handle complex data relationships and fully consider the nonlinear effects of various factors. The temperature model processes the input data through multi-level nonlinear mapping to predict future temperature changes. For example, the "memory" mechanism in the LSTM network helps the model capture long-term dependencies in time series data, while CNN can extract the spatial features of the input data, ultimately achieving high-precision temperature prediction effects. In this way, accurate temperature predictions can be given under the combined effect of multiple factors to help the air-conditioning system make appropriate adjustments.

[0051] In one embodiment, if Figure 5 As shown, in step S30, the equipment priority of the data center is obtained, and a temperature adjustment plan is dynamically generated in combination with the temperature prediction result and the backup energy status data, which specifically includes: S31: Based on the equipment priority and temperature prediction results, a comprehensive evaluation of the equipment working mode is performed through a multi-objective optimization algorithm to generate an evaluation result.

[0052] Specifically, after obtaining the equipment priority of the data center, combined with the temperature prediction results and the backup energy status data, a comprehensive evaluation of the equipment working mode is performed through a multi-objective optimization algorithm. Specifically, the equipment priority is determined based on the importance of the equipment, the operating load, and the operating status. Devices with higher priorities are usually critical devices or devices that are running at high loads. For example, core servers and data storage devices usually have higher priorities, while auxiliary devices such as non-core network devices may have lower priorities. Through a multi-objective optimization algorithm, these factors are comprehensively evaluated to obtain an evaluation result, where the objective function can include factors such as equipment operating priority, power consumption minimization, and temperature stability, and ultimately an optimized equipment working mode is generated.

[0053] S32: Based on the evaluation results and in combination with the backup energy status data, the backup energy allocation plan is adjusted through a dynamic programming algorithm to generate a temperature adjustment plan.

[0054] Specifically, based on the evaluation results and combined with the backup energy status data, that is, according to the remaining status of the backup energy in the data center (such as UPS batteries, diesel generators, etc.), it is evaluated whether the backup energy is sufficient to cope with emergencies, and the backup energy allocation plan is adjusted through the dynamic programming algorithm. The core idea of ​​the dynamic programming algorithm is to decompose the problem into a series of sub-problems and make the best decision on each sub-problem to achieve the global optimum. The dynamic programming algorithm adjusts the energy source used by each device (such as the main power grid or backup battery) according to the evaluation results and the real-time status of the backup energy to achieve the optimal execution of the temperature adjustment plan, ensure that the temperature of the data center is maintained within the most suitable range, and reasonably use the backup energy to avoid energy waste.

[0055] In one embodiment, if Figure 6 As shown, the control method of a data center air conditioner includes: S51: During the operation of the air conditioning system, the internal temperature, humidity and equipment status are monitored in real time, and the air conditioning operation mode is adjusted through a feedback control mechanism.

[0056] Specifically, the temperature and humidity of each area in the data center are monitored in real time through temperature and humidity sensors, and the equipment status is tracked in real time through the equipment monitoring system. Data is collected every 5 seconds and uploaded to the cloud for processing in real time. The air-conditioning operation mode is adjusted through the PID control algorithm based on the real-time monitored temperature and humidity data. The PID control automatically adjusts the cooling intensity, wind speed and other parameters according to the deviation between the current temperature and the target temperature to ensure that the temperature is controlled within the predetermined range.

[0057] S52: When the temperature adjustment of the air-conditioning system exceeds the preset safety range, a temperature alarm signal is generated and sent to the data center administrator through the cloud platform, enabling backup control measures or directly starting the protection mode of the air-conditioning system.

[0058] Specifically, temperature data is monitored in real time through the cloud platform. If the monitored temperature exceeds the preset safety range, such as exceeding 30°C or below 18°C, the temperature alarm mechanism will be automatically triggered. When the temperature exceeds the limit, the system generates an alarm signal and sends the alarm to the data center administrator through the cloud platform. The administrator can view the alarm information in real time through a mobile terminal or PC. After the alarm signal is triggered, the protection mode is automatically enabled. The protection mode will prevent excessive heating by limiting cooling power consumption or enabling the backup cooling system to ensure safe operation of the equipment.

[0059] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0060] In one embodiment, a control system for a data center air conditioner is provided, and the control system for a data center air conditioner corresponds one-to-one to a control method for a data center air conditioner in the above embodiment. Figure 7 As shown, the control system of the data center air conditioner includes a data acquisition module, a prediction module, an adjustment scheme acquisition module and an adjustment module. The detailed description of each functional module is as follows: A data acquisition module is used to acquire the internal environment data, equipment operation status data, backup energy status data and external climate data of the data center; The prediction module is used to comprehensively analyze the environmental data, equipment status data and external climate data of the data center through multiple data fusion algorithms, and input them into the pre-trained temperature model for comparison and analysis to obtain the temperature prediction results; the adjustment plan acquisition module is used to obtain the equipment priority of the data center, combine the temperature prediction results and the backup energy status data, and dynamically generate the temperature adjustment plan; The adjustment module is used to adjust the operation mode and parameters of the data center air conditioning system according to the temperature adjustment plan.

[0061] Optionally, the control system of the data center air conditioner further includes: The training set acquisition module is used to collect the historical environmental data, historical equipment status data and external climate historical data of the data center, and form a historical data set through data preprocessing; Model training module, which is used to build and train temperature prediction models based on historical data sets using a hybrid architecture of long short-term memory networks and convolutional neural networks; The parameter optimization module is used to optimize the hyperparameters by using a genetic algorithm during the temperature prediction model training process to obtain a pre-trained temperature model.

[0062] Feedback adjustment module, used to monitor the internal temperature, humidity and equipment status in real time during the operation of the air conditioning system, and adjust the air conditioning operation mode through the feedback control mechanism; The protection module is used to generate a temperature alarm signal and send it to the data center administrator through the cloud platform when the temperature adjustment of the air-conditioning system exceeds the preset safety range, enabling backup control measures or directly starting the protection mode of the air-conditioning system.

[0063] Optionally, the data acquisition module includes: The environmental monitoring submodule is used to obtain real-time data on the internal environment of the data center through environmental sensors. The internal environmental data includes temperature, humidity, air flow rate, heat load, and equipment heat generation. The equipment monitoring submodule is used to obtain the real-time power consumption, heat generation, operating load, equipment status and working time of each device in the data center through the equipment monitoring system; The external monitoring submodule is used to obtain external climate data, which includes outdoor temperature and humidity, wind speed and solar radiation intensity.

[0064] Optionally, the prediction module includes: The data fusion submodule is used to perform weighted processing on environmental data, equipment status data and external climate data using a weighted fusion algorithm to generate weighted data; The association analysis submodule is used to model the association relationship between various data sources based on weighted data using the Bayesian network to obtain comprehensive analysis results; The comparison analysis submodule is used to input the comprehensive analysis results into the pre-trained temperature model and generate temperature prediction results through multi-level nonlinear mapping.

[0065] Optionally, the module for obtaining an adjustment plan includes: The evaluation submodule is used to conduct a comprehensive evaluation of the device working mode based on the device priority and temperature prediction results through a multi-objective optimization algorithm to generate an evaluation result; The adjustment allocation submodule is used to adjust the allocation plan of the backup energy based on the evaluation results and in combination with the backup energy status data through a dynamic programming algorithm to generate a temperature adjustment plan.

[0066] For the specific definition of a control system for a data center air conditioner, please refer to the definition of a control method for a data center air conditioner in the above text, which will not be repeated here. Each module in the control system of the above-mentioned data center air conditioner can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0067] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer 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 computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a control method for a data center air conditioner is implemented.

[0068] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain the internal environment data, equipment operation status data, backup energy status data and external climate data of the data center; conduct a comprehensive analysis of the data center's environment data, equipment status data and external climate data through multiple data fusion algorithms, and input them into the pre-trained temperature model for comparison and analysis to obtain temperature prediction results; Obtain the equipment priority of the data center, combine the temperature prediction results and backup energy status data, and dynamically generate a temperature adjustment plan; Adjust the operating mode and parameters of the data center air conditioning system according to the temperature adjustment plan.

[0069] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain the internal environment data, equipment operation status data, backup energy status data and external climate data of the data center; conduct a comprehensive analysis of the data center's environment data, equipment status data and external climate data through multiple data fusion algorithms, and input them into the pre-trained temperature model for comparison and analysis to obtain temperature prediction results; Obtain the equipment priority of the data center, combine the temperature prediction results and backup energy status data, and dynamically generate a temperature adjustment plan; Adjust the operating mode and parameters of the data center air conditioning system according to the temperature adjustment plan.

[0070] 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 can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can 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).

[0071] 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.

[0072] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such 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 all be included in the protection scope of the present application.

Claims

1. A method for controlling air conditioning in a data center, characterized in that: The control method of a data center air conditioner comprises: Obtain data center internal environment data, equipment operation status data, backup energy status data, and external climate data; Through a multiple data fusion algorithm, the environmental data of the data center, the equipment status data and the external climate data are comprehensively analyzed, and input into a pre-trained temperature model for comparison and analysis to obtain a temperature prediction result; Obtaining the equipment priority of the data center, combining the temperature prediction result and the backup energy status data, and dynamically generating a temperature adjustment plan; According to the temperature adjustment scheme, the operating mode and parameters of the data center air conditioning system are adjusted.

2. A data center air conditioning control method according to claim 1, characterized in that: The acquisition of the internal environment data, equipment operation status data and external climate data of the data center includes: Acquire the internal environmental data of the data center in real time through environmental sensors, wherein the internal environmental data includes temperature, humidity, air flow rate, heat load and equipment heat generation; Obtain the real-time power consumption, heat generation, operating load, equipment status and working time of each equipment in the data center through the equipment monitoring system; The external climate data is obtained, wherein the external climate data includes outdoor temperature and humidity, wind speed, and solar radiation intensity.

3. A data center air conditioning control method according to claim 1, characterized in that: Before comprehensively analyzing the environmental data of the data center, the equipment status data, and the external climate data through the multiple data fusion algorithm and inputting them into a pre-trained temperature model for comparison and analysis to obtain a temperature prediction result, the control method for a data center air conditioner further includes: Collecting historical environmental data, historical equipment status data, and external climate historical data of the data center, and forming a historical data set through data preprocessing; Based on the historical data set, a temperature prediction model is constructed and trained using a hybrid architecture of long short-term memory network and convolutional neural network; During the temperature prediction model training process, a genetic algorithm is used to perform hyperparameter optimization to obtain the pre-trained temperature model.

4. A data center air conditioning control method according to claim 1, characterized in that: The environmental data of the data center, the equipment status data and the external climate data are comprehensively analyzed through the multiple data fusion algorithm, and input into the pre-trained temperature model for comparison and analysis, and the temperature prediction results obtained include: Using a weighted fusion algorithm to perform weighted processing on the environmental data, the equipment status data and the external climate data to generate weighted data; Based on the weighted data, the correlation between various data sources is modeled using a Bayesian network to obtain a comprehensive analysis result; The comprehensive analysis result is input into the pre-trained temperature model, and the temperature prediction result is generated through multi-level nonlinear mapping.

5. A data center air conditioning control method according to claim 1, characterized in that: The obtaining of the equipment priority of the data center and combining the temperature prediction result and the backup energy status data to dynamically generate a temperature adjustment plan includes: Based on the equipment priority and the temperature prediction result, a comprehensive evaluation of the equipment working mode is performed through a multi-objective optimization algorithm to generate an evaluation result; Based on the evaluation result and in combination with the backup energy state data, the allocation plan of the backup energy is adjusted through a dynamic programming algorithm to generate the temperature adjustment plan.

6. A data center air conditioning control method according to claim 1, characterized in that: The control method of a data center air conditioner also includes: real-time monitoring of internal temperature, humidity and equipment status during operation of the air conditioning system, and adjusting the air conditioning operation mode through a feedback control mechanism; When the temperature adjustment of the air-conditioning system exceeds the preset safety range, a temperature alarm signal is generated and sent to the data center administrator through the cloud platform, enabling backup control measures or directly starting the protection mode of the air-conditioning system.

7. A control system for data center air conditioning, characterized in that: The control system of a data center air conditioner comprises: A data acquisition module is used to acquire the internal environment data, equipment operation status data, backup energy status data and external climate data of the data center; A prediction module is used to comprehensively analyze the environmental data of the data center, the equipment status data and the external climate data through a multiple data fusion algorithm, and input them into a pre-trained temperature model for comparison and analysis to obtain a temperature prediction result; An adjustment scheme acquisition module is used to acquire the equipment priority of the data center, and dynamically generate a temperature adjustment scheme in combination with the temperature prediction result and the backup energy status data; The adjustment module is used to adjust the operation mode and parameters of the data center air conditioning system according to the temperature adjustment plan.

8. A data center air conditioning control system according to claim 7, characterized in that: The control system of the data center air conditioner also includes: A training set acquisition module is used to collect historical environmental data, historical equipment status data and external climate historical data of the data center, and form a historical data set through data preprocessing; A model training module is used to construct and train a temperature prediction model based on the historical data set by using a hybrid architecture of a long short-term memory network and a convolutional neural network; The parameter optimization module is used to use a genetic algorithm to perform hyperparameter optimization during the temperature prediction model training process to obtain the pre-trained temperature model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for controlling the data center air conditioner as described in any one of claims 1 to 6 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 a method for controlling a data center air conditioner as described in any one of claims 1 to 6 are implemented.

Images