A data center cooling control method using hot aisles and related apparatus

Abstract

This invention discloses a data center cooling control method and related apparatus utilizing hot aisles, relating to the field of data processing technology. The method includes: constructing a digital twin model of the data center to analyze its heat generation; determining airflow organization simulation data based on the digital twin model to perform airflow organization impact analysis; performing heat dissipation energy consumption control analysis based on the airflow organization impact analysis data; constructing a cooling strategy based on heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data, combined with hot and cold aisle load operation analysis; performing cooling simulation of the data center based on the cooling strategy; optimizing the cooling strategy based on the simulation results to obtain an optimized cooling strategy; and constructing an adaptive control system to control the hot and cold aisles for data center cooling based on the optimized cooling strategy and the adaptive control system. This invention enables data center cooling to achieve more ideal results.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data center cooling control method and related apparatus utilizing hot aisles. Background Technology

[0002] With the rapid development of the internet and computer technology, the various services provided based on the internet have also increased significantly. As the carrier of these internet services, data centers are facing ever-changing and growing construction demands. Data centers generate a large amount of heat during operation. Improper cooling management can lead to overheating, degraded equipment performance, and shortened lifespan, thus affecting the stability and security of the data center. Therefore, data center cooling management is crucial. Heat generation analysis is a vital step in data center cooling management. Currently, heat generation analysis is typically achieved through data comparison by relevant personnel. However, this method relies heavily on the professional expertise of these personnel, making it difficult to guarantee the accuracy of the analysis. Furthermore, most current data center cooling strategies lack consideration for heat dissipation and energy consumption control, resulting in a failure to achieve energy-saving control in data center cooling processes. How to achieve adaptive control and adjustment of the data center cooling process is also a problem that enterprises need to consider. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art. This invention provides a data center cooling control method and related device that utilizes hot aisles, which can effectively regulate the cooling process of the data center and achieve a more ideal cooling effect.

[0004] To address the aforementioned technical problems, this invention provides a data center cooling control method utilizing hot aisles, the method comprising: Construct a digital twin model of the data center and analyze the heat generation of the data center based on the digital twin model; Based on the digital twin model, the airflow organization simulation data of the data center is determined, and the airflow organization impact analysis is carried out based on the airflow organization simulation data to obtain airflow organization impact analysis data. Based on the airflow organization influence analysis data, heat dissipation energy consumption control analysis is performed to obtain heat dissipation energy consumption control analysis data; A cooling strategy is constructed based on the heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data, combined with the cold and hot aisle load operation analysis. Based on the cooling strategy, a cooling simulation of the data center is performed to obtain the cooling simulation results. Based on the cooling simulation results, the cooling strategy is optimized to obtain an optimized cooling strategy. An adaptive control system is constructed, and based on the optimized cooling strategy, the adaptive control system controls the hot aisle and cold aisle for data center cooling.

[0005] Optionally, the step of constructing a digital twin model of the data center and analyzing the heat generation of the data center based on the digital twin model includes: A 3D model of the data center is constructed based on the building data and equipment parameters of the data center; A mapping analysis is performed between the 3D model and the object entities in the data center to obtain the offset value of the mapping point. Based on the offset value of the mapping point, the 3D model is corrected to obtain the corrected 3D model. Analyze the equipment loss in the data center, and construct a digital twin model based on the equipment loss and the corrected 3D model; The heat source distribution is simulated based on a digital twin model to obtain the corresponding temperature field. Based on the corresponding temperature field and the evaporation point temperature analysis, the heat generation of the data center is analyzed using a heat generation analysis model.

[0006] Optionally, the step of determining the airflow organization simulation data of the data center based on the digital twin model, and performing airflow organization impact analysis based on the airflow organization simulation data to obtain airflow organization impact analysis data includes: The airflow organization simulation is performed based on the digital twin model to obtain airflow organization simulation data, and the airflow organization simulation data is evaluated to obtain airflow organization evaluation data. Based on the airflow organization evaluation data, an airflow organization impact analysis was conducted to obtain airflow organization impact analysis data.

[0007] Optionally, the step of performing heat dissipation energy consumption control analysis based on airflow organization influence analysis data to obtain heat dissipation energy consumption control analysis data includes: A cooling energy consumption control model is constructed based on the power of the cooling system in the hot and cold aisles and the airflow velocity in the data center, using airflow organization influence analysis data. A constraint function is constructed based on the total energy consumption target, and heat dissipation energy consumption control analysis is performed by combining the constraint function and the cooling energy consumption control model with the particle swarm algorithm to obtain heat dissipation energy consumption control analysis data.

[0008] Optionally, the step of constructing a cooling strategy based on the heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data, combined with hot and cold aisle load operation analysis, includes: A load operation analysis model was constructed based on historical hot and cold aisle temperature difference data. Temperature prediction data for hot and cold channels is obtained based on data from analysis of heat generation, airflow organization, and heat dissipation energy consumption control. Based on the load operation analysis model, the load operation status of the hot and cold aisles is analyzed using temperature prediction data to obtain load operation status data. The control parameters of the hot and cold aisles are determined based on the analysis data of heat generation, airflow organization, heat dissipation energy consumption control, and load operation status. Set thermal safety parameters, and construct a cooling strategy using Bayesian optimizer data based on control parameters, thermal safety parameters, and heat dissipation energy consumption control analysis data.

[0009] Optionally, the step of performing a cooling simulation of the data center based on the cooling strategy, obtaining cooling simulation results, and optimizing the cooling strategy based on the cooling simulation results to obtain an optimized cooling strategy includes: The cooling strategy is input into the simulation software to simulate the cooling of the data center and obtain the cooling simulation results. Feedback data is extracted based on the cooling simulation results, and the cooling strategy is optimized based on the feedback data to obtain an optimized cooling strategy.

[0010] Optionally, the construction of an adaptive control system, and the control of hot and cold aisles for data center cooling based on the optimized cooling strategy, includes: Establish an object model for the data center, and build an internal model controller based on the object model; A state error system is constructed using a fractional-order complex network system based on an object model; The parameters of a conventional PID controller are tuned based on the equivalent model generated by the object model to obtain the parameter-tuned conventional PID controller. An adaptive control system is constructed based on an internal model controller, a state error system, and a conventional PID controller with tuned parameters. In the process of cooling the data center by controlling the hot aisle and cold aisle based on the optimized cooling strategy, the deviation value between the real-time temperature of the data center and the preset target temperature is detected, and the adjustment parameters are generated by the adaptive control system based on the deviation value. The operating parameters of the hot aisle and cold aisle are adjusted in real time based on the adjustment parameters.

[0011] In addition, the present invention also provides a data center cooling control device utilizing hot aisles, the device comprising: Heat generation analysis module: used to construct a digital twin model of the data center and analyze the heat generation of the data center based on the digital twin model; Airflow organization impact analysis module: used to determine the airflow organization simulation data of the data center based on the digital twin model, and to perform airflow organization impact analysis based on the airflow organization simulation data to obtain airflow organization impact analysis data; The heat dissipation energy consumption control and analysis module is used to perform heat dissipation energy consumption control analysis based on airflow organization influence analysis data, and obtain heat dissipation energy consumption control and analysis data. Cooling strategy module: used to construct a cooling strategy based on the heat generation, airflow organization impact analysis data and heat dissipation energy consumption control analysis data, combined with the hot and cold aisle load operation analysis; Strategy optimization module: used to perform cooling simulation of the data center based on the cooling strategy, obtain cooling simulation results, and optimize the cooling strategy based on the cooling simulation results to obtain an optimized cooling strategy; Cooling module: Used to build an adaptive control system, and based on the optimized cooling strategy, combine the adaptive control system to control the hot aisle and cold aisle for data center cooling.

[0012] In addition, the present invention also provides an electronic device, which includes a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory to cause the electronic device to execute the above-described data center cooling control method utilizing hot aisles.

[0013] In addition, the present invention provides a computer-readable storage medium that stores computer instructions that, when executed on an electronic device, cause the electronic device to perform the above-described data center cooling control method utilizing hot aisles.

[0014] In this embodiment of the invention, constructing a digital twin model of the data center to analyze its heat generation effectively improves the accuracy and efficiency of heat generation analysis. Based on the digital twin model, simulated airflow organization data is determined, and airflow organization impact analysis is performed based on this data. Heat dissipation energy consumption control analysis is then conducted based on this airflow organization impact analysis data, making the heat dissipation energy consumption control analysis more refined and improving its reliability. A cooling strategy is constructed based on heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data, combined with hot and cold aisle load operation analysis. This strategy effectively cools the data center while also considering energy-saving control of the hot and cold aisles and their refrigeration system, effectively conserving energy. Cooling simulation of the data center is performed based on the cooling strategy, and the simulation results are used to optimize the cooling strategy, resulting in an optimized cooling strategy that better reflects the actual conditions of the data center. An adaptive control system is constructed, and based on the optimized cooling strategy, the adaptive control system controls the hot and cold aisles for data center cooling. This effectively regulates the cooling process and avoids significant deviations between the actual and expected cooling effects. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic flowchart of a data center cooling control method utilizing hot aisles in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structural composition of a data center cooling control device utilizing a hot aisle in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structural composition of the electronic device in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1

[0019] Please see Figure 1 , Figure 1 This is a flowchart illustrating a data center cooling control method utilizing hot aisles according to an embodiment of the present invention. The method includes: S11: Construct a digital twin model of the data center and analyze the heat generation of the data center based on the digital twin model; In the specific implementation of this invention, the construction of a digital twin model of the data center and the analysis of the heat generation of the data center based on the digital twin model include: constructing a three-dimensional model of the data center based on the building data and equipment parameters of the data center; performing mapping analysis on the three-dimensional model and the object entities of the data center to obtain the mapping point offset value, and correcting the three-dimensional model based on the mapping point offset value to obtain a corrected three-dimensional model; analyzing the equipment loss of the data center, and constructing a digital twin model based on the equipment loss and the corrected three-dimensional model; performing heat source distribution simulation based on the digital twin model to obtain the corresponding temperature field, and analyzing the heat generation of the data center using a heat generation analysis model based on the corresponding temperature field combined with the escaping point temperature analysis.

[0020] Specifically, a 3D model of the data center is constructed based on its architectural data and equipment parameters. The architectural data includes the data center's structure, equipment layout, and configuration, while the equipment parameters include the dimensions, structure, operating status, and temperature of each piece of equipment. This data is then input into 3D model generation software to obtain the 3D model. A mapping analysis is performed between the 3D model and the data center's object entities. Point cloud data of each target object in the data center, including its equipment, is collected. Discrete point removal is performed on the point cloud data. This is done by calculating the Euclidean distance between the point cloud data and the 3D model of the data center. Points with a distance exceeding a threshold are discarded as discrete points, resulting in standardized point cloud data. The coordinates of the target object entities are then obtained from the standardized point cloud. The offset values ​​are calculated based on the mapping points between the target object entities and their corresponding points in the 3D model of the data center. These mapping points are the spatial points corresponding to the target object entities in the 3D model of the data center, thus obtaining the mapping point offset values. The 3D model is then corrected based on these offset values, adjusting the coordinates of the corresponding spatial points in the data center to obtain a corrected 3D model. This process analyzes equipment wear and tear in data centers, acquiring operational data for each device. A device degradation analysis model, which can be a deep convolutional neural network model, is then constructed. Based on this model, the degradation status of the equipment is analyzed using the operational data, and the corresponding equipment wear is determined. Operational data includes the number of equipment repairs and the type of repair failure. A digital twin model is then built based on the equipment wear and a corrected 3D model. This model is input into the object software of the digital twin, allowing interaction between the relevant data from the 3D model and the digital twin object in the object software, thus forming the digital twin model. Finally, a heat source distribution simulation is performed based on the digital twin model. Each device twin model in the digital twin model is used as a heat source, and fluid dynamics simulation analysis is conducted based on the distribution of the heat sources. This fluid dynamics simulation analysis can be used for heat conduction and transfer simulation analysis to obtain the corresponding temperature field.Based on the corresponding temperature field and escaping point temperature analysis, a heat generation analysis model is used to analyze the heat generation of the data center. Escape points refer to key locations within the data center where airflow occurs, such as areas with significant server temperature changes or the location of exhaust fans. Equipment power data within the data center is acquired, and heat generation waveform data is analyzed based on this data. The heat generation waveform data represents the heat change data during the equipment's heat generation process. A heat generation prediction model is constructed based on this waveform data. This model is a convergent model obtained by inputting the heat generation waveform data as a sample dataset into a deep neural network for training. The heat generation prediction model is used to analyze the heat generated at the escaping points. Based on the heat generated and a preset heat transfer coefficient, the heat dissipation is analyzed. The heat dissipation is the heat generated by the equipment after heat generation. Heat dissipation from contact with the surrounding environment, such as heat dissipation from equipment upon contact with air, is addressed using an exponential smoothing algorithm to smooth the generated and dissipated heat, thus obtaining the generated and dissipated heat at the next moment. The exponential smoothing algorithm is a data analysis algorithm used for short-term prediction. Based on the generated and dissipated heat and the heat generated at the next moment, as well as the dissipated heat and the heat dissipated heat at the next moment, the temperature change data at the dissipation point is analyzed. The corresponding temperature field and the temperature change data at the dissipation point are then input into the heat generation analysis model for heat generation analysis. The heat generation analysis model can employ a deep learning model to obtain the heat generation of the data center. The resulting heat generation of the data center is closer to the actual situation and can more comprehensively reflect the internal temperature conditions of the data center.

[0021] S12: Determine the airflow organization simulation data of the data center based on the digital twin model, and conduct airflow organization impact analysis based on the airflow organization simulation data to obtain airflow organization impact analysis data; In the specific implementation of this invention, the step of determining the airflow organization simulation data of the data center based on the digital twin model, and performing airflow organization impact analysis based on the airflow organization simulation data to obtain airflow organization impact analysis data includes: performing airflow organization simulation based on the digital twin model to obtain airflow organization simulation data, evaluating the airflow organization simulation data to obtain airflow organization evaluation data; and performing airflow organization impact analysis based on the airflow organization evaluation data to obtain airflow organization impact analysis data.

[0022] Specifically, airflow organization simulation is performed based on a digital twin model. This simulation is conducted in software with fluid dynamics simulation tools to obtain airflow organization simulation data, including wind speed distribution, gas flow, temperature field distribution and changes. The simulation data is then evaluated using indices such as the inlet / outlet air temperature difference, heating index, and thermal mixing index. The heating index characterizes the degree of mixing between the supplied air and hot air before it enters the cold aisle. The thermal mixing index characterizes the worst airflow mixing conditions in the data center racks. The average temperature difference between the rack inlet and outlet air is used to assess the likelihood of local hot spots. The airflow organization evaluation index values ​​are obtained based on the analysis of the simulation data. A heating index closer to 0 indicates less mixing of hot and cold air, resulting in higher air supply efficiency. A smaller thermal mixing index indicates less mixing of hot and cold air, leading to a more stable thermal environment in the data center. A smaller inlet / outlet air temperature difference indicates a higher airflow organization evaluation. This process yields the airflow organization evaluation data. Based on airflow organization evaluation data, an airflow organization impact analysis is conducted. This involves analyzing the factors affecting airflow organization using the airflow organization evaluation data, and matching the evaluation index values ​​in the airflow organization evaluation data with the corresponding factors affecting airflow organization. The factors affecting airflow organization include the degree of closure of hot and cold channels, wind speed, wind direction, and supply air temperature. The matching data of the airflow organization evaluation data and the corresponding factors affecting airflow organization are then used to generate airflow organization impact analysis data.

[0023] S13: Perform heat dissipation energy consumption control analysis based on airflow organization influence analysis data to obtain heat dissipation energy consumption control analysis data; In the specific implementation of this invention, the step of performing heat dissipation energy consumption control analysis based on airflow organization influence analysis data to obtain heat dissipation energy consumption control analysis data includes: constructing a cooling energy consumption control model based on the power of the cooling system in the hot and cold aisles and the airflow velocity of the data center using airflow organization influence analysis data; constructing a constraint function based on the total energy consumption target; and performing heat dissipation energy consumption control analysis based on the constraint function and the cooling energy consumption control model combined with particle swarm optimization algorithm to obtain heat dissipation energy consumption control analysis data.

[0024] Specifically, a cooling energy consumption control model is constructed based on the power of the cooling system in the hot and cold aisles and the air velocity of the data center using airflow organization influence analysis data. According to the power of the cooling system in the hot and cold aisles, the energy consumption corresponding to the power of the cooling system is determined. The air velocity data of the data center, as well as the total power and energy consumption of the cooling system, are obtained under different set temperatures and set wind speeds of the cooling system. The above data, combined with airflow organization influence analysis data and different heat generation values ​​of the data center, are used as training data. An extreme learning machine model is selected as the initial cooling energy consumption control model. The extreme learning machine model is trained using the training data, and the trained extreme learning machine model is the cooling energy consumption control model. A constraint function is constructed based on the total energy consumption target, and a total energy consumption target threshold is set. The constraint function is then set according to the total energy consumption target threshold, indicating that the total energy consumption of the cooling system cannot exceed the total energy consumption target threshold. Based on the constraint function and the cooling energy consumption control model, a particle swarm optimization algorithm is used to analyze the heat dissipation energy consumption control. Using the particle swarm optimization algorithm, the operating parameters of the cooling system are analyzed under the constraint function using the cooling energy consumption control model. This yields the set temperature and set fan speed of the cooling system with the lowest total power under different heat generation conditions in the data center, thus obtaining the heat dissipation energy consumption control analysis data.

[0025] S14: Based on the heat generation, airflow organization influence analysis data and heat dissipation energy consumption control analysis data, combined with the cold and hot aisle load operation analysis, a cooling strategy is constructed; In the specific implementation of this invention, the step of constructing a cooling strategy based on the heat generation, airflow organization influence analysis data, and heat dissipation energy consumption control analysis data combined with the cold and hot aisle load operation analysis includes: constructing a load operation analysis model based on historical cold and hot aisle temperature difference data; predicting the temperature of the cold and hot aisles based on the heat generation, airflow organization influence analysis data, and heat dissipation energy consumption control analysis data to obtain temperature prediction data; analyzing the load operation status of the cold and hot aisles using the temperature prediction data based on the load operation analysis model to obtain load operation status data; determining the control parameters of the cold and hot aisles based on the heat generation, airflow organization influence analysis data, heat dissipation energy consumption control analysis data, and load operation status data; setting thermal safety parameters; and constructing a cooling strategy based on the control parameters, thermal safety parameters, and heat dissipation energy consumption control analysis data using Bayesian optimizer data.

[0026] Specifically, a load operation analysis model is constructed based on historical cold and hot aisle temperature difference data. This historical data is used as the dataset for model training, resulting in the load operation analysis model. Temperature prediction for the cold and hot aisles is performed based on heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data. The operating parameters of the refrigeration system in the cold and hot aisles, such as operating wind speed, power, and cooling temperature, are determined from these data. The temperature prediction model then uses these parameters to predict the temperature of the cold and hot aisles during operation, obtaining predicted temperatures for both the cold and hot aisles, thus acquiring the temperature prediction data. Finally, the load operation analysis model is used to analyze the load operation status of the cold and hot aisles. The temperature difference between the predicted cold and hot aisle temperatures is calculated, and the load operation analysis model is used to analyze the load operation status of the air conditioning system in the cold aisle and the heat dissipation equipment in the hot aisle. The heat dissipation equipment can be exhaust fans, thus obtaining the load operation status data. The control parameters for the cold and hot aisles are determined based on the analysis data of heat generation, airflow organization, heat dissipation energy consumption control, and load operation status. Specifically, the operating parameters of the air conditioners in the cold aisle and the operating parameters of the heat dissipation equipment in the hot aisle are determined using an operating parameter sequence analysis model based on the analysis data of heat generation, airflow organization, heat dissipation energy consumption control, and load operation status. For example, the cooling temperature of the air conditioners in the cold aisle and the fan speed of the heat dissipation equipment in the hot aisle. Thermal safety parameters are set, with the thermal safety temperature target being the temperature safety threshold. A cooling strategy is constructed using Bayesian optimizer data based on control parameters, thermal safety parameters, and heat dissipation energy consumption control analysis data. The Bayesian optimizer includes a kernel function based on Gaussian regression and a data acquisition function. The data acquisition function employs a confidence interval upper bound algorithm. The Bayesian optimizer, combined with the thermal safety parameters and heat dissipation energy consumption control analysis data, performs error optimization on the control parameters. Since the analysis model may contain certain modeling errors when determining control parameters, it is trained using relevant datasets to reduce generalization error. However, generalization error is an average measure, so the control parameters derived from the analysis model may still have significant errors. Therefore, the Bayesian optimizer recognizes this error and performs error optimization on the control parameters to find better control parameters under temperature and energy consumption constraints. A cooling strategy is then constructed using the error-optimized control parameters, resulting in a more reliable cooling strategy.

[0027] S15: Perform cooling simulation of the data center based on the cooling strategy, obtain cooling simulation results, and optimize the cooling strategy based on the cooling simulation results to obtain an optimized cooling strategy; In the specific implementation of this invention, the step of performing a cooling simulation of the data center based on the cooling strategy, obtaining cooling simulation results, and optimizing the cooling strategy based on the cooling simulation results to obtain an optimized cooling strategy includes: inputting the cooling strategy into simulation software to perform a cooling simulation of the data center and obtaining cooling simulation results; extracting feedback data based on the cooling simulation results and optimizing the cooling strategy based on the feedback data to obtain an optimized cooling strategy.

[0028] Specifically, the cooling strategy is input into simulation software to simulate data center cooling and obtain simulation results. Feedback data is extracted based on the simulation results, and the cooling effect of the data center is determined according to the simulation results. The cooling effect is then analyzed to compare the cooling effect with the expected effect, obtaining feedback data. Based on the feedback data, the cooling strategy is optimized, that is, the equipment control parameters in the hot and cold aisles of the cooling strategy are adjusted according to the feedback data to obtain an optimized cooling strategy.

[0029] S16: Construct an adaptive control system, and based on the optimized cooling strategy, combine the adaptive control system to control the hot aisle and cold aisle for data center cooling.

[0030] In the specific implementation of this invention, the construction of an adaptive control system and the control of hot and cold aisles for data center cooling based on the optimized cooling strategy include: establishing an object model of the data center; constructing an internal model controller based on the object model; constructing a state error system using a fractional-order complex network system based on the object model; tuning the parameters of a conventional PID controller based on the equivalent model generated by the object model to obtain a parameter-tuned conventional PID controller; constructing an adaptive control system based on the internal model controller, the state error system, and the parameter-tuned conventional PID controller; during the cooling process of the data center by controlling the hot and cold aisles based on the optimized cooling strategy, detecting the deviation between the real-time temperature of the data center and the preset target temperature, generating adjustment parameters based on the deviation values ​​using the adaptive control system, and adjusting the operating parameters of the hot and cold aisles in real time based on the adjustment parameters.

[0031] Specifically, an object model of the data center is established. The object model is an abstraction of the data center entity, with the data center as the controlled object. By abstracting the controlled object and its corresponding functions at a preset level, a corresponding object model is formed. An internal model controller is built based on the object model. The object model is divided into more simplified units through the preset level. Each unit has a set of corresponding basis functions. The solution vector is calculated based on the basis functions. By interpolating the solution vector and the basis functions in all units geometrically, the relative order of the object model can be obtained. Based on the relative order, an internal model controller is built using a low-pass filter function. The low-pass filter function ensures the stability and robustness of the internal model controller. Furthermore, the addition of the low-pass filter function makes its parameters adjustable parameters. The internal model controller can connect the controlled object in parallel to the corresponding loop, making the output result closer to the ideal output value. A state error system is constructed based on an object model using a fractional-order complex network system. A differential equation corresponding to the object model is established, and fractional-order derivatives are used to obtain fractional-order values. These fractional-order derivatives are in the Caputo sense. A fractional-order complex network system is constructed using the corresponding differential equations. The fractional-order complex network system, through the fractional derivatives, gains infinite memory and genetic properties, making it more consistent with real-world networks. Furthermore, the fractional derivatives increase the degrees of freedom, making the network system more practical in real-world applications. Considering the existence of uncertainties and unpredictable nonlinear states, aperiodic orbits and equivalent perturbations corresponding to the nonlinear states are introduced to construct state equations. Based on these state equations, a state error system is constructed between the object model and the fractional-order complex network system.The parameters of a conventional proportional-integral-differential (PID) controller are tuned based on an equivalent model generated from an object model. The conventional PID controller is constructed using proportional, integral, and derivative coefficients obtained from a database. By fitting the object model, low-order equivalent system parameters are obtained using frequency domain analysis, highlighting characteristics within the main frequency bands. The equivalent model is obtained by fitting the model using these low-order equivalent system parameters. The equivalent model is then divided into simplified units based on a predefined hierarchy. Each unit has a corresponding set of basis functions. Solution vectors are calculated based on the basis functions, and the two derivatives at zero complex variables are calculated from the solution vectors to obtain the first... The first and second derivatives are used to calculate the external disturbance parameters through a preset filtering function. The target complex variable is obtained based on the first and second derivatives. A first-order inertial transfer function is constructed based on the target complex variable and the external disturbance parameters. The definite integral of the first-order inertial transfer function is calculated based on the parameter decomposition theorem, reducing it to two simple integrals, thereby obtaining the target parameters. The conventional PID controller is then tuned using the target parameters, that is, the control unit parameters, such as the proportional coefficient and integral coefficient of the controller, are changed by the target parameters to make the controller output results more accurately. Thus, the conventional PID controller after parameter tuning is obtained. An adaptive control system is constructed based on an internal model controller, a state error system, and a conventional PID controller with tuned parameters. An extended state observer is introduced, which treats uncertainties or disturbances in the system as one of the system's states, establishes a new state space, and observes this new state space. The extended state observer observes the equivalent disturbance of the system through the state error system, obtaining an extended state vector. Extended state feedback compensation is obtained using a preset bandwidth parameter based on the extended state feedback compensation. The conventional PID controller with tuned parameters is then adjusted based on the extended state feedback compensation, that is, the parameters of the conventional PID controller are optimized. The adjustment of the PID controller by the extended state feedback is mainly reflected in optimizing the parameters of the PID controller by estimating the internal state and external disturbances of the system, thereby improving the robustness and control accuracy of the system. Finally, the internal model controller and the optimized conventional PID controller are fused, that is, the control parameters of the two are fused to form an adaptive control system. In the process of cooling the data center by controlling the hot aisle and cold aisle based on the optimized cooling strategy, the deviation value between the real-time temperature of the data center and the preset target temperature is detected, and the adjustment parameters are generated by the adaptive control system based on the deviation value. The operating parameters of the hot aisle and cold aisle are adjusted in real time based on the adjustment parameters, that is, the control parameters of the heat dissipation equipment in the hot aisle and the control parameters of the air conditioning system in the cold aisle are adjusted to achieve better cooling effect.

[0032] In this embodiment of the invention, constructing a digital twin model of the data center to analyze its heat generation effectively improves the accuracy and efficiency of heat generation analysis. Based on the digital twin model, simulated airflow organization data is determined, and airflow organization impact analysis is performed based on this data. Heat dissipation energy consumption control analysis is then conducted based on this airflow organization impact analysis data, making the heat dissipation energy consumption control analysis more refined and improving its reliability. A cooling strategy is constructed based on heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data, combined with hot and cold aisle load operation analysis. This strategy effectively cools the data center while also considering energy-saving control of the hot and cold aisles and their refrigeration system, effectively conserving energy. Cooling simulation of the data center is performed based on the cooling strategy, and the simulation results are used to optimize the cooling strategy, resulting in an optimized cooling strategy that better reflects the actual conditions of the data center. An adaptive control system is constructed, and based on the optimized cooling strategy, the adaptive control system controls the hot and cold aisles for data center cooling. This effectively regulates the cooling process and avoids significant deviations between the actual and expected cooling effects.

[0033] Example 2

[0034] Please see Figure 2 , Figure 2 This is a schematic diagram of the structural composition of a data center cooling control device utilizing hot aisles according to an embodiment of the present invention. The device includes: Heat generation analysis module 21: used to construct a digital twin model of the data center and analyze the heat generation of the data center based on the digital twin model; Airflow organization impact analysis module 22: used to determine the airflow organization simulation data of the data center based on the digital twin model, and to perform airflow organization impact analysis based on the airflow organization simulation data to obtain airflow organization impact analysis data; Heat dissipation energy consumption control analysis module 23: used to perform heat dissipation energy consumption control analysis based on airflow organization influence analysis data, and obtain heat dissipation energy consumption control analysis data; Cooling strategy module 24: used to construct a cooling strategy based on the heat generation, airflow organization influence analysis data and heat dissipation energy consumption control analysis data, combined with the cold and hot aisle load operation analysis; Strategy optimization module 25: used to perform cooling simulation of the data center based on the cooling strategy, obtain cooling simulation results, and optimize the cooling strategy based on the cooling simulation results to obtain an optimized cooling strategy; Cooling module 26: Used to build an adaptive control system and, based on the optimized cooling strategy, combine the adaptive control system to control the hot aisle and cold aisle for data center cooling.

[0035] In the specific implementation of this invention, the specific implementation of the device item can be referred to the implementation of the method item above, and will not be repeated here.

[0036] In this embodiment of the invention, constructing a digital twin model of the data center to analyze its heat generation effectively improves the accuracy and efficiency of heat generation analysis. Based on the digital twin model, simulated airflow organization data is determined, and airflow organization impact analysis is performed based on this data. Heat dissipation energy consumption control analysis is then conducted based on this airflow organization impact analysis data, making the heat dissipation energy consumption control analysis more refined and improving its reliability. A cooling strategy is constructed based on heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data, combined with hot and cold aisle load operation analysis. This strategy effectively cools the data center while also considering energy-saving control of the hot and cold aisles and their refrigeration system, effectively conserving energy. Cooling simulation of the data center is performed based on the cooling strategy, and the simulation results are used to optimize the cooling strategy, resulting in an optimized cooling strategy that better reflects the actual conditions of the data center. An adaptive control system is constructed, and based on the optimized cooling strategy, the adaptive control system controls the hot and cold aisles for data center cooling. This effectively regulates the cooling process and avoids significant deviations between the actual and expected cooling effects.

[0037] This invention provides a computer-readable storage medium storing a computer program. When executed by a processor, this program implements the data center cooling control method utilizing hot aisles as described in any of the above embodiments. The computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. In other words, the storage device includes any medium that stores or transmits information in a readable form by a device (e.g., a computer, a mobile phone), and can be a read-only memory, a disk, or an optical disk, etc.

[0038] Example 3

[0039] Please see Figure 3 , Figure 3This is a schematic diagram of the structural composition of the electronic device in an embodiment of the present invention.

[0040] This invention also provides an electronic device, such as... Figure 3 As shown, the electronic device includes a memory 31, a processor 33, and a computer program 32 stored in the memory 31 and executable on the processor 33. Those skilled in the art will understand that... Figure 3 The illustrated electronic device does not constitute a limitation on all devices and may include more or fewer components than illustrated, or combine certain components. Memory 31 can be used to store computer program 32 and various functional modules. Processor 33 runs the computer program 32 stored in memory 31, thereby performing various functional applications and data processing of the device. Memory can be internal memory or external memory, or both. Internal memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or random access memory. External memory may include hard disks, floppy disks, ZIP disks, USB flash drives, magnetic tapes, etc. Processor 33 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, a single-chip microcomputer, or a processor 33, or any conventional processor, etc. The processors and memories disclosed in this invention include, but are not limited to, these types of processors and memories. The processors and memories disclosed in this invention are merely examples and not intended to be limiting.

[0041] As one embodiment, the electronic device includes: one or more processors 33, a memory 31, and one or more computer programs 32, wherein the one or more computer programs 32 are stored in the memory 31 and configured to be executed by the one or more processors 33, and the one or more computer programs 32 are configured to perform the data center cooling control method utilizing hot aisles in any of the above embodiments. For specific implementation details, please refer to the above embodiments, which will not be repeated here.

[0042] In this embodiment of the invention, constructing a digital twin model of the data center to analyze its heat generation effectively improves the accuracy and efficiency of heat generation analysis. Based on the digital twin model, simulated airflow organization data is determined, and airflow organization impact analysis is performed based on this data. Heat dissipation energy consumption control analysis is then conducted based on this airflow organization impact analysis data, making the heat dissipation energy consumption control analysis more refined and improving its reliability. A cooling strategy is constructed based on heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data, combined with hot and cold aisle load operation analysis. This strategy effectively cools the data center while also considering energy-saving control of the hot and cold aisles and their refrigeration system, effectively conserving energy. Cooling simulation of the data center is performed based on the cooling strategy, and the simulation results are used to optimize the cooling strategy, resulting in an optimized cooling strategy that better reflects the actual conditions of the data center. An adaptive control system is constructed, and based on the optimized cooling strategy, the adaptive control system controls the hot and cold aisles for data center cooling. This effectively regulates the cooling process and avoids significant deviations between the actual and expected cooling effects.

[0043] Furthermore, the above provides a detailed description of a data center cooling control method and related apparatus utilizing hot aisles provided by the embodiments of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A data center cooling control method utilizing hot aisles, characterized in that, The method includes: Construct a digital twin model of the data center and analyze the heat generation of the data center based on the digital twin model; Based on the digital twin model, the airflow organization simulation data of the data center is determined, and the airflow organization impact analysis is carried out based on the airflow organization simulation data to obtain airflow organization impact analysis data. Based on the airflow organization influence analysis data, heat dissipation energy consumption control analysis is performed to obtain heat dissipation energy consumption control analysis data; A cooling strategy is constructed based on the heat generation, airflow organization impact analysis data, and heat dissipation energy consumption control analysis data, combined with the cold and hot aisle load operation analysis. Based on the cooling strategy, a cooling simulation of the data center is performed to obtain the cooling simulation results. Based on the cooling simulation results, the cooling strategy is optimized to obtain an optimized cooling strategy. An adaptive control system is constructed, and based on the optimized cooling strategy, the adaptive control system controls the hot aisle and cold aisle for data center cooling.

2. The data center cooling control method utilizing hot aisles according to claim 1, characterized in that, The construction of a digital twin model of the data center, and the analysis of the data center's heat generation based on the digital twin model, includes: A 3D model of the data center is constructed based on the building data and equipment parameters of the data center; A mapping analysis is performed between the 3D model and the object entities in the data center to obtain the offset value of the mapping point. Based on the offset value of the mapping point, the 3D model is corrected to obtain the corrected 3D model. Analyze the equipment loss in the data center, and construct a digital twin model based on the equipment loss and the corrected 3D model; The heat source distribution is simulated based on a digital twin model to obtain the corresponding temperature field. Based on the corresponding temperature field and the evaporation point temperature analysis, the heat generation of the data center is analyzed using a heat generation analysis model.

3. The data center cooling control method utilizing hot aisles according to claim 1, characterized in that, The process involves determining airflow organization simulation data for the data center based on a digital twin model, and then performing airflow organization impact analysis based on this simulation data to obtain airflow organization impact analysis data, including: The airflow organization simulation is performed based on the digital twin model to obtain airflow organization simulation data, and the airflow organization simulation data is evaluated to obtain airflow organization evaluation data. Based on the airflow organization evaluation data, an airflow organization impact analysis was conducted to obtain airflow organization impact analysis data.

4. The data center cooling control method utilizing hot aisles according to claim 1, characterized in that, The heat dissipation energy consumption control analysis based on airflow organization influence analysis data is used to obtain heat dissipation energy consumption control analysis data, including: A cooling energy consumption control model is constructed based on the power of the cooling system in the hot and cold aisles and the airflow velocity in the data center, using airflow organization influence analysis data. A constraint function is constructed based on the total energy consumption target, and heat dissipation energy consumption control analysis is performed by combining the constraint function and the cooling energy consumption control model with the particle swarm algorithm to obtain heat dissipation energy consumption control analysis data.

5. The data center cooling control method utilizing hot aisles according to claim 1, characterized in that, The cooling strategy, constructed based on the analysis data of heat generation, airflow organization, and heat dissipation energy consumption control, combined with the analysis of hot and cold aisle load operation, includes: A load operation analysis model was constructed based on historical hot and cold aisle temperature difference data. Temperature prediction data for hot and cold channels is obtained based on data from analysis of heat generation, airflow organization, and heat dissipation energy consumption control. Based on the load operation analysis model, the load operation status of the hot and cold aisles is analyzed using temperature prediction data to obtain load operation status data. The control parameters of the hot and cold aisles are determined based on the analysis data of heat generation, airflow organization, heat dissipation energy consumption control, and load operation status. Set thermal safety parameters, and construct a cooling strategy using Bayesian optimizer data based on control parameters, thermal safety parameters, and heat dissipation energy consumption control analysis data.

6. The data center cooling control method utilizing hot aisles according to claim 1, characterized in that, The process of performing a cooling simulation of the data center based on the cooling strategy, obtaining cooling simulation results, and optimizing the cooling strategy based on the cooling simulation results to obtain an optimized cooling strategy includes: The cooling strategy is input into the simulation software to simulate the cooling of the data center and obtain the cooling simulation results. Feedback data is extracted based on the cooling simulation results, and the cooling strategy is optimized based on the feedback data to obtain an optimized cooling strategy.

7. The data center cooling control method utilizing hot aisles according to claim 1, characterized in that, The construction of an adaptive control system, and the control of hot and cold aisles for data center cooling based on the optimized cooling strategy, includes: Establish an object model for the data center, and build an internal model controller based on the object model; A state error system is constructed using a fractional-order complex network system based on an object model; The parameters of a conventional PID controller are tuned based on the equivalent model generated by the object model to obtain the parameter-tuned conventional PID controller. An adaptive control system is constructed based on an internal model controller, a state error system, and a conventional PID controller with tuned parameters. In the process of cooling the data center by controlling the hot aisle and cold aisle based on the optimized cooling strategy, the deviation value between the real-time temperature of the data center and the preset target temperature is detected, and the adjustment parameters are generated by the adaptive control system based on the deviation value. The operating parameters of the hot aisle and cold aisle are adjusted in real time based on the adjustment parameters.

8. A data center cooling control device utilizing hot aisles, characterized in that, The device includes: Heat generation analysis module: used to construct a digital twin model of the data center and analyze the heat generation of the data center based on the digital twin model; Airflow organization impact analysis module: used to determine the airflow organization simulation data of the data center based on the digital twin model, and to perform airflow organization impact analysis based on the airflow organization simulation data to obtain airflow organization impact analysis data; The heat dissipation energy consumption control and analysis module is used to perform heat dissipation energy consumption control analysis based on airflow organization influence analysis data, and obtain heat dissipation energy consumption control and analysis data. Cooling strategy module: used to construct a cooling strategy based on the heat generation, airflow organization impact analysis data and heat dissipation energy consumption control analysis data, combined with the hot and cold aisle load operation analysis; Strategy optimization module: used to perform cooling simulation of the data center based on the cooling strategy, obtain cooling simulation results, and optimize the cooling strategy based on the cooling simulation results to obtain an optimized cooling strategy; Cooling module: Used to build an adaptive control system, and based on the optimized cooling strategy, combine the adaptive control system to control the hot aisle and cold aisle for data center cooling.

9. An electronic device, the electronic device comprising a processor and a memory, characterized in that, The memory is used to store instructions, and the processor is used to invoke the instructions in the memory to cause the electronic device to execute the data center cooling control method using hot aisles as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on an electronic device, cause the electronic device to perform the data center cooling control method utilizing hot aisles as described in any one of claims 1 to 7.

Images