A data center energy efficiency management method and system based on digital twin

Abstract

The present application provides a data center energy efficiency management method and system based on digital twins. Among them, a digital twin of the data center is constructed; the actual operating status of the data center is synchronized to the digital twin in real time; based on the digital twin, the impact of different energy efficiency optimization strategies on the energy efficiency of the data center is simulated; the energy efficiency optimization strategy with the best evaluation result on the digital twin is selected, and the best energy efficiency strategy is applied to the energy efficiency management of the data center to improve the energy efficiency of the data center and reduce operating costs; the actual energy efficiency changes of the data center after the application of the energy efficiency optimization strategy are monitored, and the monitoring results are fed back to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy. The technical solution provided by the present application can use a systematic evaluation method to quantify the effect of the energy efficiency optimization strategy to improve the flexibility of data center energy efficiency management.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data management technology, and in particular, to a data center energy efficiency management method and system based on digital twins. Background Art

[0002] With the development of information technology, data centers have become one of the important infrastructures supporting the operation of modern society. However, the construction and operation of data centers are facing increasing pressure on energy consumption. In order to achieve sustainable development, improving the energy efficiency of data centers has become an urgent issue to be solved.

[0003] At present, data center energy efficiency management mainly relies on traditional monitoring and manual adjustment methods. Usually, data centers are equipped with a series of monitoring systems to collect various operating data. Based on these operating data, managers will regularly analyze the energy consumption of data centers and adjust the working mode of the cooling system, adjust the load distribution of the physical infrastructure, and optimize the energy supply strategy based on experience and preset rules.

[0004] However, existing energy efficiency management solutions lack a systematic evaluation method to quantify the effectiveness of energy efficiency optimization strategies, making it difficult to form a closed loop in the optimization process and to continuously improve and optimize energy efficiency optimization strategies. Summary of the invention

[0005] The embodiments of the present application provide a data center energy efficiency management method and system based on digital twins, which are used to solve the problem that there is a lack of systematic evaluation methods in the prior art to quantify the effects of energy efficiency optimization strategies, resulting in poor flexibility and low intelligence in data center energy efficiency management.

[0006] In a first aspect, an embodiment of the present application provides a data center energy efficiency management method based on digital twins, including:

[0007] Constructing a digital twin of a data center, the digital twin including a digitized representation of the data center's physical infrastructure, energy consumption data, environmental parameters, and operating status information;

[0008] Synchronize the actual operating status of the data center to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center;

[0009] Based on the digital twin, simulating the impact of different energy efficiency optimization strategies on the energy efficiency of the data center, wherein the energy efficiency optimization strategies include adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy;

[0010] Based on the multiple simulation results in the digital twin, an evaluation index system is defined, wherein the evaluation index system includes at least energy consumption reduction rate, equipment service life impact, operating cost savings, and strategy implementation feasibility;

[0011] Using the evaluation index system to comprehensively evaluate all energy efficiency optimization strategies simulated on the digital twin, and obtaining a comprehensive evaluation result;

[0012] According to the comprehensive evaluation results, the energy efficiency optimization strategy with the highest score is selected as the optimal strategy;

[0013] Converting the optimal strategy into specific execution instructions, including but not limited to adjusting control parameters of the cooling system, reallocating loads of the physical infrastructure, and optimizing energy supply;

[0014] Applying the execution instructions to the actual operation of the data center through an automated control system or manual intervention to implement the optimal energy efficiency optimization strategy;

[0015] Monitor the actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy, and feed back the monitoring results to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy.

[0016] Optionally, the real-time synchronization of the actual operating status of the data center to the digital twin to ensure that the digital twin can dynamically reflect the current operating status of the data center includes:

[0017] The physical infrastructure, energy consumption data, environmental parameters and operation status information of the data center are collected in real time through different sensors deployed in the data center;

[0018] Use data fusion technology to integrate data streams from different sensors to form a unified data view;

[0019] The unified data view is transmitted to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center.

[0020] Optionally, based on the digital twin, simulating the impact of different energy efficiency optimization strategies on the energy efficiency of the data center, the energy efficiency optimization strategy includes adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy, including:

[0021] By means of the data analysis module integrated in the digital twin, a working mode parameter set of the cooling system is set, wherein the parameter set at least includes the start / stop time, the operating frequency and the temperature of the cooling medium of the cooling device;

[0022] In the digital twin, simulating the influence of the working mode parameter set of the cooling system on the temperature distribution and energy consumption inside the data center to obtain a first simulation result;

[0023] By means of the resource scheduling module in the digital twin, the load distribution of the physical infrastructure is adjusted according to the load distribution of the IT equipment, wherein the adjustment at least includes adjusting the power supply and cooling resources to better match the current IT load demand;

[0024] On the digital twin, simulating the impact of the load distribution of the physical infrastructure on the overall energy efficiency and equipment performance of the data center to obtain a second simulation result;

[0025] Optimizing the energy supply strategy through the energy management module in the digital twin, wherein the optimization at least includes adjusting the power supply time by using the peak-valley electricity price strategy, introducing the proportion of renewable energy, and adjusting the switching logic of the backup power supply;

[0026] On the digital twin, simulating the impact of the optimized energy supply strategy on the energy consumption and cost of the data center to obtain a third simulation result;

[0027] Compare multiple simulation results under different energy efficiency optimization strategies to determine the optimal combination of energy efficiency optimization strategies.

[0028] Optionally, the monitoring of actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy and feeding back the monitoring results to the digital twin for correcting model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy include:

[0029] Monitor actual energy efficiency change data of the data center after implementing the optimal strategy to obtain monitoring results;

[0030] The monitoring results are fed back to the digital twin, and the model parameters of the digital twin are corrected according to the monitoring results to continuously optimize the energy efficiency optimization strategy.

[0031] Optionally, the evaluation index system is used to comprehensively evaluate all energy efficiency optimization strategies simulated on the digital twin to obtain a comprehensive evaluation result, including:

[0032] The comprehensive evaluation results are calculated using the following formula group:

[0033] ;

[0034] ;

[0035] ;

[0036] ;

[0037] ;

[0038] in, Indicates the comprehensive evaluation results. represents the energy consumption reduction rate after the implementation of energy efficiency optimization strategy, A score representing the impact on equipment life after the implementation of energy efficiency optimization strategies, represents the amount of operating cost savings after the implementation of the energy efficiency optimization strategy, The score representing the feasibility of the energy efficiency optimization strategy after its implementation. Respectively expressed as The weight of

[0039] in, After implementing the energy efficiency optimization strategy, all devices in the data center In time The total energy consumption, Indicates Devices at time The actual energy consumption, It is The weight of each device is set according to the energy consumption ratio of the device; It means that under the same conditions, all devices in the data center will In time Baseline energy consumption, Indicates Devices at time Baseline energy consumption; It represents the ratio of energy consumption after implementing energy efficiency optimization strategy to baseline energy consumption; It indicates the reduction ratio of energy consumption relative to the baseline energy consumption after implementing the energy efficiency optimization strategy;

[0040] in, : indicates that all The summation is performed on each device; Indicates Predicted remaining service life of equipment after implementation of energy efficiency optimization strategy Remaining useful life predicted before implementation of energy efficiency optimization strategy The difference between the predicted remaining service life before the energy efficiency optimization strategy is implemented is divided by ; Indicates The weight of the impact of each device on its service life;

[0041] in, After implementing the energy efficiency optimization strategy, all devices in the data center In time The weighted total operating cost, Indicates Devices at time The actual operating costs, Indicates The weight of the impact of each device on operating costs; It means that under the same conditions, all devices in the data center are In time The weighted baseline operating cost of Indicates Devices at time Baseline operating costs; It represents the ratio of the weighted total operating cost after implementing the energy efficiency optimization strategy to the baseline weighted total operating cost; It represents the reduction ratio of weighted total operating cost relative to the baseline operating cost after implementing the energy efficiency optimization strategy;

[0042] in, Indicates that all The average difficulty of implementing the strategies, is the number of strategies, Indicates that all The sum of the difficulty of implementing the strategies, Represents an expression based on the Gaussian function, used to measure the The deviation between the implementation difficulty of a strategy and the target difficulty level, Indicates The difficulty of implementing a strategy, Indicates the target difficulty level. The target difficulty level is set with an ideal difficulty threshold. When the difficulty of implementing a strategy is close to the ideal difficulty threshold, the feasibility score of the strategy implementation is the highest. Represents the standard deviation, which is used to adjust the width of the Gaussian function curve.

[0043] Optionally, the feeding back the monitoring result to the digital twin, and correcting the model parameters of the digital twin according to the monitoring result to continuously optimize the energy efficiency optimization strategy, includes:

[0044] The model parameters of the digital twin are corrected by the following set of formulas:

[0045] ;

[0046] ;

[0047] in, represents the model parameters after correction; represents the original model parameters; Represents the difference between the actual energy efficiency change and the expected energy efficiency change, Indicates Actual energy efficiency changes of each device; Indicates Expected change in energy efficiency of each device; Indicates The weight of each device for the energy efficiency change error; Represents the correction coefficient, which is used to control the correction step length. The value range is .

[0048] In a second aspect, an embodiment of the present application provides a data center energy efficiency management system based on digital twins, including:

[0049] A construction module for constructing a digital twin of a data center, the digital twin including a digitized representation of the physical infrastructure, energy consumption data, environmental parameters, and operating status information of the data center;

[0050] A synchronization module, used to synchronize the actual operating status of the data center to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center;

[0051] A simulation module, for simulating the impact of different energy efficiency optimization strategies on the energy efficiency of the data center based on the digital twin, wherein the energy efficiency optimization strategies include adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy;

[0052] A selection module is used to define an evaluation index system based on multiple simulation results in the digital twin, wherein the evaluation index system includes at least energy consumption reduction rate, equipment service life impact, operating cost savings, and strategy implementation feasibility; use the evaluation index system to comprehensively evaluate all energy efficiency optimization strategies simulated on the digital twin to obtain a comprehensive evaluation result; based on the comprehensive evaluation result, select the energy efficiency optimization strategy with the highest score as the optimal strategy; convert the optimal strategy into specific execution instructions, wherein the execution instructions include adjusting the control parameters of the cooling system, reallocating the load of the physical infrastructure, and optimizing the energy supply; and apply the execution instructions to the actual operation of the data center through an automated control system or manual intervention to implement the optimal energy efficiency optimization strategy;

[0053] A monitoring module is used to monitor the actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy, and to feed back the monitoring results to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy.

[0054] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a data center energy efficiency management method based on digital twins as described in any one of the first aspects.

[0055] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a data center energy efficiency management method based on digital twins as described in any one of the first aspects.

[0056] In an embodiment of the present application, a digital twin of a data center is constructed, and the digital twin includes a digital representation of the physical infrastructure, energy consumption data, environmental parameters, and operating status information of the data center; the actual operating status of the data center is synchronized to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center; based on the digital twin, the impact of different energy efficiency optimization strategies on the energy efficiency of the data center is simulated, and the energy efficiency optimization strategy includes adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy; the energy efficiency optimization strategy with the best evaluation result on the digital twin is selected, and the best energy efficiency strategy is applied to the energy efficiency management of the data center to improve the energy efficiency of the data center and reduce operating costs; the actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy are monitored, and the monitoring results are fed back to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy. The technical solution provided by the present application can systematically evaluate the method to quantify the effect of the energy efficiency optimization strategy to improve the flexibility of the energy efficiency management of the data center.

[0057] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 A flowchart of a data center energy efficiency management method based on digital twins provided in an embodiment of the present application;

[0060] Figure 2 A schematic diagram of the structure of a data center energy efficiency management system based on digital twins provided in an embodiment of the present application;

[0061] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0063] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0064] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0065] Figure 1 A flowchart of a data center energy efficiency management method based on digital twins is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0066] 101. Construct a digital twin of a data center, wherein the digital twin includes a digital representation of the physical infrastructure, energy consumption data, environmental parameters, and operating status information of the data center;

[0067] In this step, building a digital twin of a data center means creating a highly accurate virtual model that reflects the actual physical facilities, energy consumption, environmental parameters (such as temperature, humidity, etc.) and real-time operating status of the data center. The digital twin includes not only static data center structure information, but also dynamic operational data, allowing managers to understand the current status of the data center through this virtual model and simulate different operating scenarios to predict future behavior. Building a digital twin usually requires integrating data from different sources, such as sensors, control systems, and other IT infrastructure management systems.

[0068] The following is a brief introduction to the concepts involved:

[0069] Physical Infrastructure: refers to all hardware facilities in the data center, such as servers, routers, switches, cooling systems, power supply equipment, etc.

[0070] Energy Consumption Data: refers to the actual power consumption of each device in the data center, including but not limited to the power consumption of servers and air conditioning systems.

[0071] Environmental Parameters: including temperature, humidity, air quality and other indicators. These parameters directly affect the operating efficiency and equipment life of the data center.

[0072] Operational State Information: refers to the working status of equipment in the data center, such as server load, network traffic, fault alarms, etc.

[0073] In the embodiment of this application, it is assumed that a digital twin of a data center is being constructed. The data center includes multiple racks, each of which is equipped with multiple servers and is equipped with a precision air conditioning system and an uninterruptible power supply system. The following is a specific example of the construction process:

[0074] Physical infrastructure modeling: Collect information about all hardware devices in the data center, including model, location, connection relationship, etc., and create corresponding digital models in a virtual environment.

[0075] Energy consumption data collection: Deploy sensors and monitoring software to monitor the energy consumption of each device in the data center in real time, and map this data to the energy consumption attributes of the corresponding equipment in the digital twin.

[0076] Environmental parameter monitoring: Install environmental monitoring equipment such as temperature and humidity sensors to obtain real-time environmental parameters inside the data center and input these data into the corresponding modules of the digital twin.

[0077] Integration of operation status information: Integrate the monitoring system in the data center to collect operation status information such as server load and network traffic, and reflect it in the digital twin.

[0078] In an embodiment of the present application, a digital twin of a data center is constructed, which includes a server room, a cooling system, a power supply system, etc. First, the location, specifications, connection methods and other information of all key equipment are entered into the digital twin platform to form a three-dimensional layout diagram of the data center. Secondly, various sensors are installed to monitor key parameters such as temperature, humidity, and power consumption in real time, and these data are transmitted to the digital twin in real time. Furthermore, the existing data center infrastructure management system (DCIM) and building automation system (BA) are integrated to ensure that the digital twin can access the status and energy consumption data of the relevant equipment. Finally, historical data is imported into the digital twin, and these data are used to calibrate the model so that it can more accurately reflect the operation of the actual data center.

[0079] The effect of this step is that data center managers can remotely monitor the status of the data center and evaluate the impact of different strategies through simulation tests, so as to make more informed decisions. The purpose is to improve the operational efficiency and reliability of the data center by integrating various data sources and utilizing advanced simulation technology. The design principle is to combine IoT technology, cloud computing and big data analysis capabilities to build a virtual mirror that can reflect the real-world data center. Compared with traditional solutions, digital twins provide a more dynamic and interactive way to manage and optimize data centers, reducing the delays and misjudgment risks caused by relying on manual inspections, and also laying the foundation for future intelligent operations.

[0080] 102. Synchronize the actual operating status of the data center to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center;

[0081] Optionally, the real-time synchronization of the actual operating status of the data center to the digital twin in step 102 to ensure that the digital twin can dynamically reflect the current operating status of the data center, including: real-time collection of the physical infrastructure, energy consumption data, environmental parameters and operating status information of the data center through different sensors deployed in the data center; using data fusion technology to integrate data streams from different sensors to form a unified data view; and transmitting the unified data view to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center.

[0082] In this step, we will introduce in detail how to collect key data of the data center in real time through sensors deployed in the data center, and integrate this data using data fusion technology to ensure that the digital twin can dynamically reflect the current operating status of the data center:

[0083] Sensors: used to monitor various physical quantities in the data center in real time, such as temperature sensors, humidity sensors, current sensors, etc.

[0084] Data Fusion Technology: refers to a method of obtaining information from multiple data sources and combining the information to infer or estimate the optimal state of an event.

[0085] Unified Data View: refers to integrating data from different sensors into a whole to better understand and analyze the status of the data center.

[0086] Real-Time Transmission: refers to the transmission process of data from the collection point to the processing platform with no delay or very short delay.

[0087] In the embodiment of the present application, various types of sensors are first deployed in the data center, for example:

[0088] The temperature sensor is used to measure the temperature distribution in the equipment room.

[0089] Humidity Sensor is used to monitor air humidity.

[0090] Current transformers are used to detect the current consumption of servers and other equipment.

[0091] The voltage sensor is used to detect the voltage level of the power supply line.

[0092] Network Traffic Monitor is used to monitor the data transmission of network devices.

[0093] Furthermore, data fusion technology is used to integrate data streams from different sensors. For example, the data from all sensors can be received through the Central Control System, and algorithms can be used to eliminate redundant information, fill in missing data, etc. to form a unified data view. Real-time transmission to the digital twin: The processed unified data view is transmitted to the digital twin of the data center in real time through a high-speed network connection to ensure that the digital twin can instantly reflect the current operating status of the data center.

[0094] Effect, purpose and design principle of this step:

[0095] The core purpose of this step is to ensure that the digital twin is consistent with the actual data center, so that any operation and simulation on the twin can be based on the latest actual data. Compared with traditional manual inspection or scheduled data upload, real-time synchronization provides higher reliability and accuracy, and can detect and respond to problems faster.

[0096] By synchronizing data in real time, digital twins can more effectively support energy efficiency management and optimization decisions. For example, when an abnormally high temperature in a certain area is detected, the cooling system’s operating mode can be adjusted to respond quickly to avoid equipment failures caused by overheating.

[0097] Assume that in a data center, there are the following sensors deployed:

[0098] The 10 temperature sensors are distributed in different cabinets.

[0099] There are 5 humidity sensors located on different floors.

[0100] 20 current transformers are connected to servers and other key equipment.

[0101] 1 network traffic monitor is connected to the core switch.

[0102] When these sensors start working, they send data to the central control system every few seconds. The central control system uses data fusion algorithms to organize this data and send the organized information to the digital twin. For example, if the temperature suddenly rises somewhere, the central control system will immediately transmit this information to the digital twin along with the associated humidity, current consumption and other data, so that managers can immediately see the problem and take corresponding measures.

[0103] 103. Based on the digital twin, simulate the impact of different energy efficiency optimization strategies on the energy efficiency of the data center, wherein the energy efficiency optimization strategies include adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy;

[0104] Optionally, the digital twin-based simulation in step 103 simulates the impact of different energy efficiency optimization strategies on the energy efficiency of the data center, and the energy efficiency optimization strategy includes adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy, including: setting the working mode parameter set of the cooling system through the data analysis module integrated in the digital twin, and the parameter set at least includes the start / stop time, operating frequency and temperature of the cooling medium of the cooling equipment; in the digital twin, simulating the impact of the working mode parameter set of the cooling system on the internal temperature distribution and energy consumption of the data center to obtain a first simulation result; adjusting the physical infrastructure according to the load distribution of IT equipment through the resource scheduling module in the digital twin. The load distribution of the implementation is implemented, and the adjustment at least includes adjusting the power supply and cooling resources to better match the current IT load demand; on the digital twin, the impact of the physical infrastructure load distribution on the overall energy efficiency and equipment performance of the data center is simulated to obtain a second simulation result; through the energy management module in the digital twin, the energy supply strategy is optimized, and the optimization at least includes adjusting the power supply time using the peak and valley electricity price strategy, introducing the proportion of renewable energy use, and adjusting the switching logic of the backup power supply; on the digital twin, the impact of the optimized energy supply strategy on the energy consumption and cost of the data center is simulated to obtain a third simulation result; and multiple simulation results under different energy efficiency optimization strategies are compared to determine the optimal energy efficiency optimization strategy combination.

[0105] In this step, different energy efficiency optimization strategies will be simulated based on the digital twin, and their impact on the energy efficiency of the data center will be evaluated. Specifically, the working mode of the cooling system will be adjusted, the load distribution of the physical infrastructure will be adjusted, and the energy supply strategy will be optimized:

[0106] Data Analysis Module: used to process and analyze various data integrated in the digital twin to support decision-making.

[0107] Cooling System Operation Parameters Set: includes the start / stop time, operating frequency and temperature of the cooling medium of the cooling equipment.

[0108] Resource Scheduling Module: Responsible for managing the load distribution of the physical infrastructure within the data center to ensure efficient use of resources.

[0109] Energy Management Module: used to optimize energy supply strategies, including adjusting power supply time and introducing renewable energy.

[0110] In the embodiment of the present application, the working mode parameter set of the cooling system is set:

[0111] The start / stop time, operating frequency, and temperature of the cooling medium of the cooling equipment are set in the data analysis module of the digital twin.

[0112] For example, cooling equipment can be set to run less frequently during off-peak hours and the temperature of the cooling water can be adjusted to reduce energy consumption.

[0113] The impact of the working mode parameter set of the simulated cooling system on the temperature distribution and energy consumption inside the data center:

[0114] The digital twin is used to simulate the impact of changes in the above settings on the temperature distribution inside the data center.

[0115] For example, it simulates the impact of reducing the frequency of cooling equipment operation during a specific period of time on the temperature rise inside the data center and the resulting changes in energy consumption.

[0116] Redistribute the load on the physical infrastructure:

[0117] The resource scheduling module in the digital twin is used to redistribute the load of the physical infrastructure.

[0118] Simulate the impact of load distribution of physical infrastructure on the overall energy efficiency and equipment performance of the data center:

[0119] The impact of the above load redistribution strategy on the overall energy efficiency and equipment performance of the data center is simulated in the digital twin.

[0120] For example, the total energy consumption changes of the data center and the performance changes of the server after simulating load balancing.

[0121] Optimizing energy supply strategies:

[0122] Use the energy management module in the digital twin to optimize the energy supply strategy, such as using peak and valley electricity price strategies to adjust the power supply time, introduce the proportion of renewable energy such as solar energy, and adjust the switching logic of backup power supplies.

[0123] For example, you could set it up to use more electricity during times when electricity prices are lower, and consider using solar power to supplement grid power during the day.

[0124] Simulate the impact of optimized energy supply strategy on data center energy consumption and cost:

[0125] The impact of the above optimized energy supply strategy on the energy consumption and cost of the data center is simulated in the digital twin.

[0126] For example, simulating the impact of using solar power generation during the day on the total energy consumption and operating costs of a data center.

[0127] Compare multiple simulation results under different energy efficiency optimization strategies:

[0128] Compare the above simulation results to find the best energy efficiency optimization strategy combination in different dimensions (such as energy consumption reduction, cost savings, etc.).

[0129] Effect, purpose and design principle of this step:

[0130] The main purpose of this step is to find the best strategy combination under various conditions by simulating different energy efficiency optimization strategies. Compared with the traditional trial and error method, this method can find the best solution through multiple attempts in a virtual environment without interfering with the actual data center operation. This can not only improve the energy efficiency of the data center, but also significantly reduce operating costs.

[0131] Suppose there are several strategies that need to be simulated:

[0132] Strategy A: Increase the operating frequency of cooling equipment at night (when electricity prices are low) and adjust the cooling water temperature to a lower level.

[0133] Strategy B: Rational deployment of redundant infrastructure to achieve reasonable distribution of energy and cooling loads.

[0134] Strategy C: Use solar power during the day and increase grid power when electricity prices are low.

[0135] The simulation results show:

[0136] Strategy A: After increasing the frequency of cooling equipment operation at night, the temperature inside the data center rose slightly during the day, but the overall energy consumption was reduced by 10%.

[0137] Strategy B: After redistributing the load, the overall server utilization rate increased by 15% and the energy consumption decreased by 5%.

[0138] Strategy C: After using solar power, daytime energy consumption was reduced by 8% and operating costs were reduced by 12%.

[0139] On the whole, the strategy combination A+B+C performed best in terms of energy consumption reduction and cost savings, and was therefore identified as the optimal energy efficiency optimization strategy combination.

[0140] 104. Selecting an energy efficiency optimization strategy with the best evaluation result on the digital twin, and applying the best energy efficiency strategy to the energy efficiency management of the data center to improve the energy efficiency of the data center and reduce operating costs;

[0141] Optionally, the selection of the energy efficiency optimization strategy with the best evaluation result on the digital twin in step 104, and applying the optimal energy efficiency strategy to the energy efficiency management of the data center, includes: defining an evaluation index system based on multiple simulation results in the digital twin, the evaluation index system at least including energy consumption reduction rate, equipment service life impact, operating cost savings and strategy implementation feasibility; using the evaluation index system to comprehensively evaluate all energy efficiency optimization strategies simulated on the digital twin to obtain a comprehensive evaluation result; based on the comprehensive evaluation result, selecting the energy efficiency optimization strategy with the highest score as the optimal strategy; converting the optimal strategy into specific execution instructions, the execution instructions include but are not limited to adjusting the control parameters of the cooling system, reallocating the load of the physical infrastructure, and optimizing the energy supply; applying the execution instructions to the actual operation of the data center through an automated control system or manual intervention to implement the optimal energy efficiency optimization strategy.

[0142] In this step, an evaluation index system is defined based on multiple simulation results in the digital twin, and this system is used to comprehensively evaluate all simulated energy efficiency optimization strategies, and finally the strategy with the highest score is selected as the optimal strategy. In addition, the optimal strategy is converted into specific execution instructions and applied to the operation of the actual data center:

[0143] Evaluation Indicator System: A set of standards used to evaluate the effectiveness of energy efficiency optimization strategies, including energy consumption reduction rate, impact on equipment lifespan, operational cost savings, and feasibility of implementation.

[0144] Comprehensive Evaluation Result: A comprehensive evaluation score or ranking obtained by quantitatively comparing the performance of all energy efficiency optimization strategies in the evaluation index system.

[0145] Execution Commands: Convert the selected optimal strategy into actual operational commands, such as adjusting the control parameters of the cooling system, redistributing the load of the physical infrastructure, and optimizing the way energy is supplied.

[0146] Automation Control System or Manual Intervention: Instructions are automatically executed by the automation control system, or the administrator manually adjusts the equipment configuration according to the instructions to implement energy efficiency optimization strategies.

[0147] In the present application embodiment:

[0148] Define the evaluation indicator system:

[0149] Energy consumption reduction rate: The percentage of energy consumption reduction brought about by the energy efficiency optimization strategy in the simulation results.

[0150] Impact on equipment life: The impact of the evaluation strategy on the long-term operating stability of the equipment.

[0151] Operational cost savings: Calculate the amount of cost savings after implementing the strategy.

[0152] Feasibility of strategy implementation: Consider whether the strategy is easy to implement and its impact on daily operations.

[0153] Comprehensive evaluation using the evaluation indicator system:

[0154] Assuming there are three energy efficiency optimization strategies (A, B, C), the evaluation results are as follows:

[0155] Strategy A: Energy consumption is reduced by 10%, the impact on equipment service life is small, operating cost savings are 50,000 yuan, and implementation feasibility is high.

[0156] Strategy B: Energy consumption reduction rate is 12%, which has a significant impact on the service life of equipment, and the operating cost savings is RMB 30,000. The feasibility of implementation is average.

[0157] Strategy C: Energy consumption reduction rate is 8%, the impact on equipment service life is small, operating cost savings are RMB 40,000, and implementation feasibility is high.

[0158] Select the energy efficiency optimization strategy with the highest score:

[0159] Taking all indicators into consideration, Strategy C performs well in terms of energy consumption reduction rate, operating cost savings and implementation feasibility. Although its energy consumption reduction rate is not as good as Strategy B, Strategy C is selected as the optimal strategy because of its small impact on equipment service life and strong implementation feasibility.

[0160] Convert the optimal strategy into specific execution instructions:

[0161] Specific instructions for strategy C may include adjusting the operating frequency of the cooling system, reallocating some computing tasks to low-load servers, and adjusting the power supply schedule.

[0162] Implement optimal strategies through automated control systems or human intervention:

[0163] Use automated control systems to adjust the operating frequency of cooling systems, or administrators can manually redistribute computing tasks and adjust power supply schedules based on instructions.

[0164] Effect, purpose and design principle of this step:

[0165] The purpose of this step is to ensure that the selected energy efficiency optimization strategy can not only improve energy efficiency in the short term, but also ensure the normal operation of the equipment in the long term, while taking into account the feasibility and cost-effectiveness of the strategy implementation. Compared with traditional solutions, this method selects the optimal strategy by comprehensively evaluating the performance of multiple dimensions, rather than deciding based on the effect of a single aspect, so it is more scientific and reasonable.

[0166] Assume that after comprehensive evaluation, strategy C is finally selected as the optimal strategy. The following are the specific implementation steps:

[0167] Adjust the operating frequency of the cooling system:

[0168] Reduce the operating frequency of the cooling system from 80% to 70% and further reduce it to 60% during off-peak hours.

[0169] Redistribute computing tasks:

[0170] Transfer some computing tasks from servers with higher load to servers with lower load to balance the load among servers.

[0171] Adjustment of electricity supply schedule:

[0172] Increase electricity supply during the night time when electricity prices are lower, and reduce electricity consumption during the day time when electricity prices are higher.

[0173] Through the above adjustments, it is expected that the energy consumption of the data center will be reduced by about 8%, and the operating costs will be reduced by about 40,000 yuan. At the same time, the service life of the equipment will be less affected and the feasibility of implementation will be higher. These measures will help improve the energy efficiency of the data center and reduce operating costs.

[0174] Optionally, the step 104 uses the evaluation index system to comprehensively evaluate all energy efficiency optimization strategies simulated on the digital twin to obtain a comprehensive evaluation result, including:

[0175] The comprehensive evaluation results are calculated using the following formula group:

[0176] ;

[0177] ;

[0178] ;

[0179] ;

[0180] ;

[0181] in, Indicates the comprehensive evaluation results. represents the energy consumption reduction rate after the implementation of energy efficiency optimization strategy, A score representing the impact on equipment life after the implementation of energy efficiency optimization strategies, represents the amount of operating cost savings after the implementation of the energy efficiency optimization strategy, The score representing the feasibility of the energy efficiency optimization strategy after its implementation. Respectively expressed as The weight of

[0182] in, After implementing the energy efficiency optimization strategy, all devices in the data center In time The total energy consumption, Indicates Devices at time The actual energy consumption, It is The weight of each device is set according to the energy consumption ratio of the device; It means that under the same conditions, all devices in the data center are In time Baseline energy consumption, Indicates Devices at time Baseline energy consumption; It represents the ratio of energy consumption after implementing energy efficiency optimization strategy to baseline energy consumption; It indicates the reduction ratio of energy consumption relative to the baseline energy consumption after implementing the energy efficiency optimization strategy;

[0183] in, : indicates that all The summation is performed on each device; Indicates Predicted remaining service life of equipment after implementation of energy efficiency optimization strategy Remaining useful life predicted before implementation of energy efficiency optimization strategy The difference between the predicted remaining service life before the energy efficiency optimization strategy is implemented is divided by ; Indicates The weight of the impact of each device on its service life;

[0184] in, After implementing the energy efficiency optimization strategy, all devices in the data center In time The weighted total operating cost, Indicates Devices at time The actual operating costs, Indicates The weight of the impact of each device on operating costs; It means that under the same conditions, all devices in the data center will In time The weighted baseline operating cost of Indicates Devices at time Baseline operating costs; It represents the ratio of the weighted total operating cost after implementing the energy efficiency optimization strategy to the baseline weighted total operating cost; It represents the reduction ratio of weighted total operating cost relative to the baseline operating cost after implementing the energy efficiency optimization strategy;

[0185] in, Indicates that all The average difficulty of implementing the strategies, is the number of strategies, Indicates that all The sum of the difficulty of implementing the strategies, Represents an expression based on the Gaussian function, used to measure the The deviation between the implementation difficulty of a strategy and the target difficulty level, Indicates The difficulty of implementing a strategy, Indicates the target difficulty level. The target difficulty level is set with an ideal difficulty threshold. When the difficulty of implementing a strategy is close to the ideal difficulty threshold, the feasibility score of the strategy implementation is the highest. Represents the standard deviation, which is used to adjust the width of the Gaussian function curve.

[0186] In this step, a series of formulas will be used to calculate the comprehensive evaluation results. , which is used to evaluate all energy efficiency optimization strategies simulated on the digital twin. The following is a detailed explanation of each concept:

[0187] Comprehensive evaluation results : It represents the total score after weighted summation of all evaluation indicators.

[0188] Energy consumption reduction rate : Indicates the percentage of energy consumption reduction relative to the baseline after the implementation of the energy efficiency optimization strategy.

[0189] Impact of equipment service life : Indicates the change in the remaining service life of the equipment after the implementation of the energy efficiency optimization strategy compared with the baseline life when the strategy is not implemented.

[0190] Operational cost savings : Indicates the percentage of savings relative to the baseline operating cost after the implementation of energy efficiency optimization strategies.

[0191] Feasibility of strategy implementation : Indicates the difficulty of implementing the energy efficiency optimization strategy, measured by the deviation from the target difficulty level.

[0192] The calculation formula is:

[0193] ;

[0194] in Represent the weights of the four evaluation indicators respectively.

[0195] The calculation formula is:

[0196] ;

[0197] Indicates the energy consumption reduction rate after implementing the strategy.

[0198] The calculation formula is: ;

[0199] A fraction representing the impact of the equipment's useful life.

[0200] The calculation formula is: ;

[0201] Represents operational cost savings.

[0202] The calculation formula is:

[0203] ;

[0204] A score indicating the feasibility of implementing the strategy.

[0205] In the embodiment of the present application, the following data are assumed:

[0206] Number of devices ;Weight is the energy consumption of the equipment; the proportion is assumed to be 0.4, 0.3, 0.3, and the baseline energy consumption 1000kWh, 800kWh, 700kWh respectively; Energy consumption after implementation of the strategy 900kWh, 720kWh, 630kWh respectively; baseline operating cost 500 yuan, 400 yuan, and 350 yuan respectively; the operating costs after implementing the strategy 450 yuan, 360 yuan, 315 yuan respectively; baseline equipment life 5 years, 4 years, and 3 years respectively; the predicted service life after implementing the strategy They are 4.5 years, 3.8 years, and 2.7 years respectively; the weight of the impact of equipment service life All are 1; weight of operating cost impact 1; target difficulty level Difficulty in implementing the strategy They are 2.5, 3, and 3.5 respectively; standard deviation ; Assume that the weights are .

[0207] calculate :

[0208] ;

[0209] calculate :

[0210] ;

[0211] calculate :

[0212] ;

[0213] calculate :

[0214] ;

[0215] ;

[0216] calculate :

[0217] ;

[0218] Effect, purpose and design principle of this step

[0219] The main purpose of this step is to objectively evaluate and select the optimal strategy by quantitatively analyzing the effects of various energy efficiency optimization strategies. Compared with traditional qualitative evaluation, this method based on quantitative indicators is more scientific and reliable because it takes into account the influence of multiple factors and comprehensively considers all evaluation indicators through weighted average.

[0220] Assuming that the final calculated They are 5.5975, 6.2, and 5.8, corresponding to strategies A, B, and C. Then, based on the comprehensive evaluation results, strategy B with the highest score is selected as the optimal strategy.

[0221] 105. Monitor the actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy, and feed back the monitoring results to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy.

[0222] Optionally, the monitoring in step 105 of the actual energy efficiency change of the data center after applying the energy efficiency optimization strategy and feeding back the monitoring results to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy includes: monitoring the actual energy efficiency change data of the data center after implementing the optimal strategy to obtain monitoring results; feeding back the monitoring results to the digital twin, and correcting the model parameters of the digital twin according to the monitoring results to continuously optimize the energy efficiency optimization strategy.

[0223] Furthermore, the step of feeding back the monitoring result to the digital twin and correcting the model parameters of the digital twin according to the monitoring result to continuously optimize the energy efficiency optimization strategy includes:

[0224] The model parameters of the digital twin are corrected by the following set of formulas:

[0225] ;

[0226] ;

[0227] in, represents the model parameters after correction; represents the original model parameters; Represents the difference between the actual energy efficiency change and the expected energy efficiency change, Indicates Actual energy efficiency changes of each device; Indicates Expected change in energy efficiency of each device; Indicates The weight of each device for the energy efficiency change error; Represents the correction coefficient, which is used to control the correction step length. The value range is .

[0228] In this step, we will explain in detail how to monitor the actual energy efficiency changes after implementing the energy efficiency optimization strategy and feed these monitoring results back to the digital twin to correct the model parameters of the digital twin, thereby continuously optimizing the energy efficiency optimization strategy. The following is a detailed explanation of each concept:

[0229] Monitoring Results: refers to the actual energy efficiency change data of the data center after implementing the optimal energy efficiency optimization strategy, including energy consumption reduction rate, impact on equipment life, operating cost savings, etc.

[0230] Feedback Mechanism: Feedback the monitoring results to the digital twin to adjust the model parameters to make the model closer to reality.

[0231] Model Parameter Correction: Adjust the model parameters of the digital twin based on the monitoring results so that the model more accurately reflects the actual operating status of the data center.

[0232] In the embodiment of the present application, it is assumed that an energy efficiency optimization strategy has been implemented and a set of monitoring results have been obtained. Now it is necessary to feed back these monitoring results to the digital twin and calibrate the model parameters according to the monitoring results.

[0233] Monitor the actual energy efficiency change data after implementing the optimal strategy and obtain the monitoring results:

[0234] Assume there is a set of devices (Device⋅1,⋅Device⋅2,⋅Device⋅3).

[0235] The actual energy efficiency changes after implementing the strategy are: Device⋅1:⋅-5%⋅ (actual reduction), Device⋅2:⋅-3%⋅ (actual reduction), Device⋅3:⋅-4%⋅ (actual reduction).

[0236] The expected energy efficiency changes are: Device⋅1:⋅-4%⋅ (expected decrease), Device⋅2:⋅-5%⋅ (expected decrease), Device⋅3:⋅-3%⋅ (expected decrease).

[0237] Assumption Weight Both are ⋅1.

[0238] Correct the model parameters of the digital twin according to the monitoring results:

[0239] Use the formula group for correction:

[0240] ;

[0241] Calculation ⋅ :

[0242] ;

[0243] Assuming the correction coefficient ⋅α⋅=⋅0.5, the corrected model parameters for:

[0244] ;

[0245] Effect, purpose and design principle of this step:

[0246] The main purpose of this step is to continuously correct the model parameters of the digital twin through real-time monitoring and feedback mechanisms to make it more accurately reflect the actual operation of the data center. The purpose of this is to continuously optimize the energy efficiency optimization strategy and ensure that each optimization is based on the latest and most accurate data.

[0247] Compared with traditional static optimization methods, this method can better adapt to changes in data center operating conditions through real-time feedback and dynamic adjustment, and improve the effectiveness and adaptability of energy efficiency optimization strategies.

[0248] Assume that in a certain period, the following data is monitored:

[0249] The actual energy efficiency change of Device⋅1⋅ is ⋅-5%, and the expected energy efficiency change is ⋅-4%.

[0250] The actual energy efficiency change of Device⋅2⋅ is ⋅-3%, and the expected energy efficiency change is ⋅-5%.

[0251] The actual energy efficiency change of Device⋅3⋅ is ⋅-4%, and the expected energy efficiency change is ⋅-3%.

[0252] Based on the above data, we can calculate:

[0253] ;

[0254] Assuming the initial model parameters For a certain value, the correction factor is ⋅0.5, then the new model parameters ⋅ is:

[0255] ;

[0256] Through this correction process, the model parameters of the digital twin are updated to better reflect the operation of the actual data center.

[0257] Figure 2 A structural diagram of a data center energy efficiency management system based on digital twins is provided for an embodiment of the present application, such as Figure 2 As shown, the device comprises:

[0258] A construction module 21 is used to construct a digital twin of a data center, wherein the digital twin includes a digital representation of the physical infrastructure, energy consumption data, environmental parameters, and operating status information of the data center;

[0259] A synchronization module 22, used to synchronize the actual operating status of the data center to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center;

[0260] A simulation module 23 is used to simulate the impact of different energy efficiency optimization strategies on the energy efficiency of the data center based on the digital twin, wherein the energy efficiency optimization strategy includes adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy;

[0261] A selection module 24 is used to select the energy efficiency optimization strategy with the best evaluation result on the digital twin, and apply the best energy efficiency strategy to the energy efficiency management of the data center to improve the energy efficiency of the data center and reduce the operating cost;

[0262] The monitoring module 25 is used to monitor the actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy, and feed back the monitoring results to the digital twin to correct the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy.

[0263] Figure 2 The data center energy efficiency management system based on digital twin can perform Figure 1 The implementation principle and technical effects of the data center energy efficiency management method based on digital twins described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the data center energy efficiency management system based on digital twins in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0264] In one possible design, Figure 2 The data center energy efficiency management system based on digital twins of the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0265] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0266] The processing component 32 is used to: construct a digital twin of the data center, which includes a digital representation of the physical infrastructure, energy consumption data, environmental parameters and operating status information of the data center; synchronize the actual operating status of the data center to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center; based on the digital twin, simulate the impact of different energy efficiency optimization strategies on the energy efficiency of the data center, and the energy efficiency optimization strategy includes adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy; select the energy efficiency optimization strategy with the best evaluation result on the digital twin, and apply the best energy efficiency strategy to the energy efficiency management of the data center to improve the energy efficiency of the data center and reduce operating costs; monitor the actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy, and feed back the monitoring results to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy.

[0267] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0268] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0269] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0270] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0271] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0272] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0273] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The embodiment shown is a data center energy efficiency management method based on digital twins.

[0274] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0275] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0276] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions to ensure that a computer device (which can be a personal computer, a server, or a network device, etc.) executes the methods described in each embodiment or some parts of the embodiment.

[0277] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data center energy efficiency management method based on digital twins, characterized in that: include: Constructing a digital twin of a data center, the digital twin including a digitized representation of the data center's physical infrastructure, energy consumption data, environmental parameters, and operating status information; Synchronize the actual operating status of the data center to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center; Based on the digital twin, simulating the impact of different energy efficiency optimization strategies on the energy efficiency of the data center, wherein the energy efficiency optimization strategies include adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy; Based on the multiple simulation results in the digital twin, an evaluation index system is defined, wherein the evaluation index system includes at least energy consumption reduction rate, equipment service life impact, operating cost savings, and strategy implementation feasibility; Using the evaluation index system to comprehensively evaluate all energy efficiency optimization strategies simulated on the digital twin, and obtaining a comprehensive evaluation result; According to the comprehensive evaluation results, the energy efficiency optimization strategy with the highest score is selected as the optimal strategy; Converting the optimal strategy into specific execution instructions, the execution instructions including adjusting control parameters of the cooling system, reallocating loads of the physical infrastructure, and optimizing energy supply; Applying the execution instructions to the actual operation of the data center through an automated control system or manual intervention to implement the optimal energy efficiency optimization strategy; Monitor the actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy, and feed back the monitoring results to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy.

2. The method according to claim 1, characterized in that The real-time synchronization of the actual operating status of the data center to the digital twin to ensure that the digital twin can dynamically reflect the current operating status of the data center includes: The physical infrastructure, energy consumption data, environmental parameters and operation status information of the data center are collected in real time through different sensors deployed in the data center; Use data fusion technology to integrate data streams from different sensors to form a unified data view; The unified data view is transmitted to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center.

3. The method according to claim 1, characterized in that Based on the digital twin, simulating the impact of different energy efficiency optimization strategies on the energy efficiency of the data center, the energy efficiency optimization strategy includes adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy, including: By means of the data analysis module integrated in the digital twin, a working mode parameter set of the cooling system is set, wherein the parameter set at least includes the start / stop time, the operating frequency and the temperature of the cooling medium of the cooling device; In the digital twin, simulating the influence of the working mode parameter set of the cooling system on the temperature distribution and energy consumption inside the data center to obtain a first simulation result; By means of the resource scheduling module in the digital twin, the load distribution of the physical infrastructure is adjusted according to the load distribution of the IT equipment, wherein the adjustment at least includes adjusting the power supply and cooling resources to match the load requirements of the IT equipment; On the digital twin, simulating the impact of the load distribution of the physical infrastructure on the overall energy efficiency and equipment performance of the data center to obtain a second simulation result; Optimizing the energy supply strategy through the energy management module in the digital twin, wherein the optimization at least includes adjusting the power supply time by using the peak-valley electricity price strategy, introducing the proportion of renewable energy, and adjusting the switching logic of the backup power supply; On the digital twin, simulating the impact of the optimized energy supply strategy on the energy consumption and cost of the data center to obtain a third simulation result; Compare multiple simulation results under different energy efficiency optimization strategies to determine the optimal combination of energy efficiency optimization strategies.

4. The method according to claim 1, characterized in that: The monitoring of actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy, and feeding back the monitoring results to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy, includes: Monitor actual energy efficiency change data of the data center after implementing the optimal strategy to obtain monitoring results; The monitoring results are fed back to the digital twin, and the model parameters of the digital twin are corrected according to the monitoring results to continuously optimize the energy efficiency optimization strategy.

5. The method according to claim 1, characterized in that The evaluation index system is used to comprehensively evaluate all energy efficiency optimization strategies simulated on the digital twin to obtain a comprehensive evaluation result, including: The comprehensive evaluation results are calculated using the following formula group: ； ； ； ； ； in, Indicates the comprehensive evaluation results. represents the energy consumption reduction rate after the implementation of energy efficiency optimization strategy, A score representing the impact on equipment life after the implementation of energy efficiency optimization strategies, represents the amount of operating cost savings after the implementation of the energy efficiency optimization strategy, The score representing the feasibility of the energy efficiency optimization strategy after its implementation. Respectively expressed as The weight of in, After implementing the energy efficiency optimization strategy, all devices in the data center In time The total energy consumption, Indicates Devices at time The actual energy consumption, It is The weight of each device is set according to the energy consumption ratio of the device; It means that under the same conditions, all devices in the data center are In time Baseline energy consumption, Indicates Devices at time Baseline energy consumption; It represents the ratio of energy consumption after implementing energy efficiency optimization strategy to baseline energy consumption; It indicates the reduction ratio of energy consumption relative to the baseline energy consumption after implementing the energy efficiency optimization strategy; in, : indicates that all The summation is performed on each device; Indicates Predicted remaining service life of equipment after implementation of energy efficiency optimization strategy Remaining useful life predicted before implementation of energy efficiency optimization strategy The difference between the predicted remaining service life before the energy efficiency optimization strategy is implemented is divided by ; Indicates The weight of the impact of each device on its service life; in, After implementing the energy efficiency optimization strategy, all devices in the data center In time The weighted total operating cost, Indicates Devices at time The actual operating costs, Indicates The weight of the impact of each device on operating costs; It means that under the same conditions, all devices in the data center are In time The weighted baseline operating cost of Indicates Devices at time Baseline operating costs; It represents the ratio of the weighted total operating cost after implementing the energy efficiency optimization strategy to the baseline weighted total operating cost; It represents the reduction ratio of weighted total operating cost relative to the baseline operating cost after implementing the energy efficiency optimization strategy; in, Indicates that all The average difficulty of implementing the strategies. is the number of strategies, Indicates that all The sum of the difficulty of implementing the strategies, Represents an expression based on the Gaussian function, used to measure the The deviation between the implementation difficulty of a strategy and the target difficulty level, Indicates The difficulty of implementing a strategy, Indicates the target difficulty level. The target difficulty level is set with an ideal difficulty threshold. When the difficulty of implementing a strategy is close to the ideal difficulty threshold, the feasibility score of the strategy implementation is the highest. Represents the standard deviation, which is used to adjust the width of the Gaussian function curve.

6. The method according to claim 4, characterized in that Feeding back the monitoring result to the digital twin, and correcting the model parameters of the digital twin according to the monitoring result to continuously optimize the energy efficiency optimization strategy, includes: The model parameters of the digital twin are corrected by the following set of formulas: ； ； in, represents the model parameters after correction; represents the original model parameters; Represents the difference between the actual energy efficiency change and the expected energy efficiency change, Indicates Actual energy efficiency changes of each device; Indicates Expected change in energy efficiency of each device; Indicates The weight of each device for the energy efficiency change error; Represents the correction coefficient, which is used to control the correction step length. The value range is .

7. A data center energy efficiency management system based on digital twins, characterized in that: include: A construction module for constructing a digital twin of a data center, the digital twin including a digitized representation of the physical infrastructure, energy consumption data, environmental parameters, and operating status information of the data center; A synchronization module, used to synchronize the actual operating status of the data center to the digital twin in real time to ensure that the digital twin can dynamically reflect the current operating status of the data center; A simulation module, for simulating the impact of different energy efficiency optimization strategies on the energy efficiency of the data center based on the digital twin, wherein the energy efficiency optimization strategies include adjusting the working mode of the cooling system, adjusting the load distribution of the physical infrastructure, and optimizing the energy supply strategy; A selection module is used to define an evaluation index system based on multiple simulation results in the digital twin, wherein the evaluation index system includes at least energy consumption reduction rate, equipment service life impact, operating cost savings, and strategy implementation feasibility; use the evaluation index system to comprehensively evaluate all energy efficiency optimization strategies simulated on the digital twin to obtain a comprehensive evaluation result; based on the comprehensive evaluation result, select the energy efficiency optimization strategy with the highest score as the optimal strategy; convert the optimal strategy into specific execution instructions, wherein the execution instructions include adjusting the control parameters of the cooling system, reallocating the load of the physical infrastructure, and optimizing the energy supply; and apply the execution instructions to the actual operation of the data center through an automated control system or manual intervention to implement the optimal energy efficiency optimization strategy; A monitoring module is used to monitor the actual energy efficiency changes of the data center after applying the energy efficiency optimization strategy, and to feed back the monitoring results to the digital twin for correcting the model parameters of the digital twin to continuously optimize the energy efficiency optimization strategy.

8. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a data center energy efficiency management method based on digital twins as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a data center energy efficiency management method based on digital twins as described in any one of claims 1 to 6 is implemented.

Images