An online diagnosis and optimization method for energy efficiency of data center air conditioning terminal

Abstract

The present application relates to the technical field of data processing and optimization, in particular to a kind of data center air conditioner end energy efficiency online diagnosis and optimization method.The method comprises the following steps: obtaining data center end air conditioning system;Real-time monitoring is carried out on the power consumption of data center end air conditioning system and the power consumption of end air conditioning equipment, and equipment power consumption data is obtained;Real-time analysis and processing are carried out on equipment power consumption data, and utilization efficiency evaluation index is calculated;The utilization efficiency evaluation index is evaluated for the energy efficiency of computer room, and the evaluation result of the energy efficiency of computer room is obtained.The present application realizes real-time judgment of the energy efficiency of computer room end by data processing technology, pattern recognition technology and intelligent optimization technology, quickly identifies the energy efficiency short board of computer room air conditioner end equipment, simultaneously, from the operation mechanism of air conditioner end, carries out end air conditioner operation optimization, to reduce the energy consumption of air conditioner end system operation.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and optimization, and in particular to an online diagnosis and optimization method for energy efficiency of air-conditioning terminals in a data center. Background Art

[0002] Data centers are known for their high energy consumption, with air conditioning systems accounting for approximately 40% of total energy consumption. Improving data center energy efficiency is crucial for reducing their carbon emissions. The air conditioning system primarily consists of the air conditioning water system and the air conditioning terminal system. Due to the complex and large number of equipment involved, the air conditioning terminal system is one of the most energy-intensive components in a data center. Technologies to improve the energy efficiency of air conditioning terminal systems include free cooling, cold plate cooling, heat pipe cooling, immersion cooling, and spray cooling. However, the application of these new technologies is highly dependent on geographical conditions, limiting their practical application. Currently, most data centers still employ traditional energy-saving retrofits to reduce air conditioning energy consumption. Traditional energy-saving retrofits for air conditioning terminal systems focus solely on optimizing the supply air temperature and water valve opening parameters of the terminal equipment, failing to consider the impact of the combined operation of the terminal equipment on air conditioning terminal system energy efficiency. Summary of the Invention

[0003] Based on this, it is necessary to provide an online diagnosis and optimization method for the energy efficiency of data center air conditioning terminals to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a method for online diagnosis and optimization of energy efficiency of air conditioning terminals in a data center is provided, the method comprising the following steps:

[0005] Step S1: Acquire the terminal air conditioning system of the data center; monitor the power consumption of the IT equipment in the computer room and the terminal air conditioning equipment in real time to obtain the power consumption data of the equipment;

[0006] Step S2: Analyze and process the equipment power consumption data in real time to calculate the utilization efficiency evaluation index; evaluate the energy efficiency of the computer room based on the utilization efficiency evaluation index to obtain the power efficiency evaluation result of the computer room;

[0007] Step S3: Locate computer rooms with low energy efficiency based on the results of the computer room power efficiency evaluation to obtain a list of computer rooms to be optimized; optimize the terminal air conditioning operating parameters in the list of computer rooms to be optimized to obtain the air conditioning operating optimization parameters;

[0008] Step S4: Verify the energy consumption reduction effect of the air conditioning operation optimization parameters to obtain the energy consumption optimization verification results; perform energy utilization efficiency feedback adjustment based on the energy consumption optimization verification results to obtain the terminal air conditioning operation optimization report to perform online diagnosis and optimization of air conditioning terminal energy efficiency.

[0009] The present invention captures the power consumption of the data center's terminal air conditioning system and monitors the power consumption of the computer room's IT equipment and terminal air conditioning equipment in real time. This allows accurate collection of equipment power consumption data, providing a precise energy consumption data base for the data center. By analyzing and processing this data in real time, utilization efficiency evaluation indicators are calculated, which are then used to evaluate the energy efficiency of the computer room, quantify the data center's energy efficiency performance, and identify areas of energy inefficiency. Based on the evaluation results, computer rooms with low energy efficiency are located, a list of computer rooms to be optimized is generated, and terminal air conditioning operating parameters are optimized to improve the energy efficiency of these inefficient computer rooms. The energy consumption reduction effect of the optimized air conditioning operating parameters is verified, and energy utilization efficiency feedback adjustments are made based on these verification results. Ultimately, a terminal air conditioning operation optimization report is generated to ensure the effectiveness of the optimization measures, reduce energy consumption, and improve energy utilization efficiency, providing a scientific basis for online diagnosis and optimization of air conditioning terminal energy efficiency. Therefore, the present invention utilizes data processing, pattern recognition, and intelligent optimization technologies to determine the energy efficiency of the computer room terminal in real time, quickly identify energy efficiency shortcomings of the computer room's air conditioning terminal equipment, and optimize terminal air conditioning operation based on the terminal air conditioning terminal's operating mechanism, thereby reducing the operating energy consumption of the air conditioning terminal system.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Obtain the terminal air conditioning system of the data center;

[0012] Step S12: measuring the power consumption of IT equipment in the computer room on the terminal air conditioning system of the data center to obtain power consumption data of IT equipment in the computer room;

[0013] Step S13: measuring the power consumption of the terminal air-conditioning equipment of the data center terminal air-conditioning system to obtain the power consumption data of the terminal air-conditioning equipment;

[0014] Step S14: Integrate the power consumption data of the IT equipment in the computer room and the power consumption data of the terminal air-conditioning equipment to obtain the equipment power consumption data.

[0015] The present invention obtains the terminal air-conditioning system of the data center, and this process provides the necessary foundation for the subsequent energy consumption data collection. By measuring the power consumption of the IT equipment in the computer room, the power consumption data of the IT equipment in the computer room can be accurately obtained, providing key input parameters for the energy consumption analysis of the data center. Next, the power consumption of the terminal air-conditioning equipment is measured to obtain the power consumption data of the terminal air-conditioning equipment, which further enriches the dimension of the energy consumption data of the data center. Finally, the power consumption data of the IT equipment in the computer room and the power consumption data of the terminal air-conditioning equipment are integrated to obtain comprehensive equipment power consumption data, which provides detailed data support for the energy consumption management of the data center, so that energy consumption analysis and optimization work can be carried out based on complete and accurate data, thereby improving the accuracy and effectiveness of the energy efficiency management of the data center.

[0016] Preferably, step S14 includes the following steps:

[0017] Step S141: Pre-processing the power consumption data of IT equipment in the computer room and the power consumption data of the terminal air-conditioning equipment to obtain equipment pre-processing data;

[0018] Step S142: performing feature synchronization on the device preprocessing data to obtain device feature synchronization data; performing feature alignment on the device feature synchronization data to generate device feature alignment data;

[0019] Step S143: performing structured inspection on the device feature alignment data to obtain structured inspection data; performing data fusion on the structured inspection data to obtain device power consumption data.

[0020] The present invention pre-processes the power consumption data of the IT equipment in the computer room and the power consumption data of the terminal air-conditioning equipment to obtain the equipment pre-processing data. This step ensures the cleanliness and consistency of the data and provides a high-quality data foundation for subsequent analysis. Next, the equipment pre-processing data is feature synchronized to obtain equipment feature synchronization data, and these data are feature aligned to generate equipment feature alignment data. This process optimizes the structure of the data and makes it more suitable for analysis and modeling. Then, the equipment feature alignment data is structured tested to obtain structured test data. This test step ensures the accuracy and reliability of the data and provides a solid foundation for further data processing. Finally, the structured test data is data fused to obtain equipment power consumption data. This fusion process integrates multi-source data to form a comprehensive data set, which provides detailed and structured power consumption information for data center energy consumption analysis and optimization. Through this series of data processing steps, the data center can obtain more accurate and structured power consumption data, thereby improving the efficiency and accuracy of energy consumption analysis.

[0021] Preferably, step S2 includes the following steps:

[0022] Step S21: Analyze the device power consumption data in real time to obtain a power consumption data stream; extract key features from the power consumption data stream to obtain key power consumption parameters;

[0023] Step S22: Identify the power consumption pattern of the key power consumption parameters to obtain the power consumption behavior pattern; monitor the power consumption trend of the power consumption behavior pattern to obtain power consumption trend data;

[0024] Step S23: quantifying the electricity utilization efficiency of the electricity consumption trend data to generate an efficiency evaluation index;

[0025] Step S24: performing an energy efficiency evaluation on the computer room based on the utilization efficiency evaluation index to obtain an evaluation result of the power efficiency of the computer room.

[0026] The present invention analyzes equipment power usage data in real time to generate a power data stream. This process ensures data timeliness and dynamic monitoring capabilities, providing a continuous data stream for capturing power usage behavior. Key power parameters are extracted from the power data stream. This step accurately identifies key factors influencing energy consumption and lays the foundation for in-depth analysis of power usage behavior. Next, power usage patterns are identified for these key power parameters to generate power behavior patterns. Power usage trends are then monitored within these patterns to generate power trend data. This helps reveal the regularity and changing trends of power usage behavior, providing a basis for prediction and optimization. The power trend data is then quantified to generate a power utilization efficiency evaluation index. This step converts power utilization trends into quantifiable efficiency indicators, providing a specific metric for evaluating energy efficiency. Finally, the power utilization efficiency of the computer room is evaluated using the efficiency evaluation index to generate a power efficiency evaluation result. This evaluation result directly reflects the energy efficiency level of the computer room, providing clear guidance and basis for energy efficiency management and optimization. Through this series of coherent data processing and analysis steps, data centers can achieve an in-depth understanding of electricity usage behavior and accurate assessment of energy efficiency, thereby effectively guiding the implementation of energy-saving and consumption-reduction measures.

[0027] Preferably, step S24 includes the following steps:

[0028] Step S241: normalizing the utilization efficiency evaluation index to obtain a standardized evaluation index; and assigning weights to the standardized evaluation index to obtain a weighted evaluation index;

[0029] Step S242: performing a comprehensive calculation on the weighted evaluation indicators to obtain a comprehensive score of the power efficiency of the computer room; and classifying the comprehensive score of the power efficiency of the computer room to obtain a level evaluation of the power efficiency of the computer room;

[0030] Step S243: presenting the results of the level evaluation of the power efficiency of the computer room, and obtaining the evaluation results of the power efficiency of the computer room.

[0031] The present invention normalizes the utilization efficiency evaluation indicators to obtain standardized evaluation indicators. This step ensures comparability between different indicators and provides a unified data standard for subsequent analysis. Next, the standardized evaluation indicators are weighted to obtain weighted evaluation indicators. This process rationally assigns weights to each indicator based on its importance in the energy efficiency evaluation, making the evaluation results more scientific and objective. Then, the weighted evaluation indicators are comprehensively calculated to obtain a comprehensive score for the computer room's electrical energy efficiency. This step combines multiple evaluation indicators into a quantitative score that intuitively reflects the overall level of the computer room's electrical energy efficiency. The comprehensive score for the computer room's electrical energy efficiency is graded to obtain a computer room's electrical energy efficiency rating. This classification provides clear grade identification for the computer room's energy efficiency, facilitating comparison and identification of high and low energy efficiency levels. Finally, the results of the computer room's electrical energy efficiency rating are presented to obtain a computer room's electrical energy efficiency evaluation result. This presentation makes the energy efficiency evaluation results more intuitive and easy to understand, allowing decision makers to quickly grasp the energy efficiency status of the computer room and take appropriate optimization measures. Through this series of data processing and evaluation steps, the data center can accurately evaluate and effectively manage the power efficiency of the computer room, thereby guiding energy efficiency optimization work and improving energy utilization efficiency.

[0032] Preferably, step S3 includes the following steps:

[0033] Step S31: setting a threshold for the power efficiency evaluation results of the computer room to obtain preliminary screening data of inefficient computer rooms;

[0034] Step S32: removing abnormal values ​​from the preliminarily screened inefficient computer room data to obtain inefficient parameter-removed data;

[0035] Step S33: Prioritize the preliminarily screened inefficient computer room data based on the inefficient parameter elimination data to obtain a priority list of inefficient computer rooms; extract computer rooms with low energy efficiency from the priority list of inefficient computer rooms to obtain a list of computer rooms to be optimized;

[0036] Step S34: Optimize the terminal air-conditioning operating parameters for the list of computer rooms to be optimized to obtain the air-conditioning operating optimization parameters.

[0037] The present invention sets thresholds for the results of the computer room electricity efficiency evaluation to obtain data for preliminary screening of inefficient computer rooms. This step, by setting thresholds, identifies computer rooms with poor energy efficiency performance and provides targets for subsequent optimization work. Next, outliers are removed from the preliminary screening of inefficient computer room data to obtain inefficient parameter-elimination data. This process ensures data accuracy, eliminates abnormal data that affects the analysis results, and improves the reliability of inefficient computer room identification. Then, the preliminary screening of inefficient computer room data is prioritized based on the inefficient parameter-elimination data to obtain a priority list of inefficient computer rooms. This step sorts the computer rooms according to their energy efficiency performance and provides a basis for optimizing resource allocation. The priority list of inefficient computer rooms is then extracted to obtain a list of computer rooms to be optimized. This extraction process further identifies the computer rooms that require priority energy efficiency optimization, ensuring the targeted nature of the optimization work. Finally, the terminal air conditioning operating parameters in the list of computer rooms to be optimized are optimized to obtain optimized air conditioning operating parameters. This optimization process directly targets the specific conditions of the inefficient computer rooms and formulates improvement measures aimed at improving their energy efficiency performance. Through this series of precise data screening, outlier processing, priority sorting and parameter optimization steps, data centers can efficiently identify and optimize inefficient computer rooms, thereby improving overall energy efficiency.

[0038] Preferably, step S34 includes the following steps:

[0039] Step S341: collecting initial operating parameters of the terminal air conditioners in the list of computer rooms to be optimized to obtain basic operating data of the air conditioners;

[0040] Step S342: Perform performance analysis on the basic data of air conditioner operation to obtain operation performance indicators;

[0041] Step S343: Optimizing the key performance indicators to obtain performance indicator optimization data;

[0042] Step S344: Adjust the operating parameters of the list of computer rooms to be optimized based on the performance indicator optimization data to obtain air conditioning operation optimization parameters.

[0043] The present invention collects the initial operating parameters of the terminal air-conditioning for the list of computer rooms to be optimized, and obtains the basic data of air-conditioning operation. This step provides the original and necessary data support for the air-conditioning performance analysis. The basic data of air-conditioning operation is subjected to performance analysis to obtain the operating performance indicators. This analysis process can reveal the current performance level and existing problems of the air-conditioning system. The key performance indicators are optimized to obtain performance indicator optimization data. This optimization processing step formulates specific improvement measures based on the performance analysis results, aiming to improve the performance of the air-conditioning system. Based on the performance indicator optimization data, the operating parameters of the list of computer rooms to be optimized are adjusted to obtain the air-conditioning operation optimization parameters. This parameter adjustment step concretizes the optimization measures and provides optimized parameter settings for the actual operation of the air-conditioning system. Through this series of coherent steps from data collection to performance analysis, and then to optimization processing and parameter adjustment, the data center can accurately optimize the performance of the terminal air-conditioning system, ensure that the air-conditioning system operates in the best state, and thus improve the energy efficiency and stability of the entire computer room.

[0044] Preferably, step S344 includes the following steps:

[0045] Step S3441: Identify factors affecting air conditioning energy efficiency based on the performance index optimization data to obtain an energy efficiency optimization target;

[0046] Step S3442: performing parameter association mapping on the energy efficiency optimization target to obtain parameter adjustment mapping data;

[0047] Step S3443: Dynamically adjust the list of computer rooms to be optimized according to the parameter adjustment mapping data to obtain computer room operation adjustment data;

[0048] Step S3444: Perform feedback loop optimization on the computer room operation adjustment data to obtain air conditioning operation optimization parameters.

[0049] The present invention identifies the factors affecting air conditioning energy efficiency on the performance index optimization data to obtain the energy efficiency optimization target. This step can clarify the key factors affecting air conditioning energy efficiency and provide a clear improvement direction for subsequent energy efficiency optimization. Parameter association mapping is performed on the energy efficiency optimization target to obtain parameter adjustment mapping data. This process provides a scientific basis for precise adjustment by identifying the relationship between energy efficiency influencing factors and adjustable parameters. The list of computer rooms to be optimized is dynamically adjusted according to the parameter adjustment mapping data to obtain computer room operation adjustment data. This dynamic adjustment step enables the operating parameters of the computer room to be optimized according to real-time data to adapt to changing energy efficiency requirements. Feedback loop optimization is performed on the computer room operation adjustment data to obtain air conditioning operation optimization parameters. This feedback loop optimization step ensures that the optimization measures can be continuously iterated and adjusted according to the actual operating results to achieve the best energy efficiency performance. Through this series of coherent steps, the data center can achieve refined management of the air conditioning system, optimize energy efficiency, reduce energy consumption, and improve the overall energy efficiency level.

[0050] Preferably, step S4 includes the following steps:

[0051] Step S41: Compare energy consumption data before and after the implementation of the air-conditioning operation optimization parameters to obtain energy consumption comparison data;

[0052] Step S42: performing statistical analysis on the energy consumption comparison data to obtain energy consumption statistical results; performing trend identification on the energy consumption statistical results to obtain energy consumption trend data;

[0053] Step S43: Evaluate the effect of the energy consumption trend analysis to obtain energy consumption optimization verification results;

[0054] Step S44: Based on the energy consumption optimization verification result, energy utilization efficiency feedback adjustment is performed to obtain a terminal air-conditioning operation optimization report to perform air-conditioning terminal energy efficiency online diagnosis and optimization operations.

[0055] The present invention compares the energy consumption data before and after the implementation of the air conditioning operation optimization parameters to obtain energy consumption comparison data. This step can directly demonstrate the effect of the optimization measures and provide a quantitative basis for evaluating the optimization effect. The energy consumption comparison data is statistically analyzed to obtain energy consumption statistical results, and the energy consumption statistical results are trend-identified to obtain energy consumption trend data. This helps to understand the regularity and long-term trend of energy consumption changes and provide data support for further energy consumption prediction and optimization. The energy consumption trend is analyzed and the effect is evaluated to obtain energy consumption optimization verification results. This evaluation result can verify the actual effect of the optimization measures and ensure the correctness of the optimization direction. Based on the energy consumption optimization verification results, feedback adjustment of energy utilization efficiency is performed to obtain a terminal air conditioning operation optimization report. This report provides detailed guidance and basis for performing online diagnosis and optimization of air conditioning terminal energy efficiency, ensuring the continuous improvement of optimization measures and maximization of implementation effects. Through this series of steps, the data center can achieve continuous monitoring and optimization of the energy efficiency of the air conditioning system, improve energy utilization efficiency, and reduce operating costs.

[0056] Preferably, step S44 includes the following steps:

[0057] Step S441: performing energy consumption reduction analysis on the energy consumption optimization verification result to obtain energy consumption analysis data;

[0058] Step S442: performing efficiency impact assessment on the energy consumption analysis data to obtain efficiency influencing factors; performing weight adjustment on the efficiency influencing factors to obtain adjusted weight data;

[0059] Step S443: Applying feedback loop to the adjusted weights to obtain real-time optimization parameters; monitoring the effects of the real-time optimization parameters to obtain a terminal air conditioning operation optimization report;

[0060] Step S444: Continuously optimize the terminal air conditioning system of the data center based on the terminal air conditioning operation optimization report to perform online diagnosis and optimization of the air conditioning terminal energy efficiency.

[0061] The present invention analyzes energy consumption reductions based on the energy optimization verification results to generate energy consumption analysis data. This step enables detailed analysis of the specific values ​​and components of energy consumption reductions, providing accurate data support for further energy efficiency improvements. The energy consumption analysis data is then subjected to an efficiency impact assessment to identify efficiency influencing factors. These factors are then weighted to generate adjusted weighted data. This process ensures that the importance of each influencing factor is properly reflected in energy efficiency optimization, optimizing resource allocation and optimization strategies. The adjusted weights are then applied in a feedback loop to generate real-time optimization parameters. The effects of these parameters are monitored to generate a terminal air conditioning operation optimization report. This step enables dynamic adjustment and real-time monitoring of optimization measures, ensuring their effectiveness and timeliness. Based on the terminal air conditioning operation optimization report, the data center's terminal air conditioning system is continuously optimized to perform online energy efficiency diagnosis and optimization. This continuous optimization process ensures the continuous improvement of the data center's terminal air conditioning system's energy efficiency, maximizing energy utilization and optimizing costs. Through this series of coherent steps, data centers can achieve refined management of their air conditioning systems, optimize energy efficiency, reduce energy consumption, improve overall energy efficiency, and ensure the ongoing effectiveness of optimization measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flowchart of the steps of an online diagnosis and optimization method for energy efficiency of air conditioning terminals in a data center;

[0063] Figure 2 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0064] Figure 3 for Figure 2 Detailed implementation steps of step S44 are shown in the flowchart;

[0065] Figure 4 This is a control logic diagram for an online diagnosis and optimization method of energy efficiency of air conditioning terminals in data centers;

[0066] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0067] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0068] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0069] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0070] To achieve this, please refer to Figures 1 to 4 , a method for online diagnosis and optimization of energy efficiency of air conditioning terminals in a data center, the method comprising the following steps:

[0071] Step S1: Acquire the terminal air conditioning system of the data center; monitor the power consumption of the IT equipment in the computer room and the terminal air conditioning equipment in real time to obtain the power consumption data of the equipment;

[0072] Step S2: Analyze and process the equipment power consumption data in real time to calculate the utilization efficiency evaluation index; evaluate the energy efficiency of the computer room based on the utilization efficiency evaluation index to obtain the power efficiency evaluation result of the computer room;

[0073] Step S3: Locate computer rooms with low energy efficiency based on the results of the computer room power efficiency evaluation to obtain a list of computer rooms to be optimized; optimize the terminal air conditioning operating parameters in the list of computer rooms to be optimized to obtain the air conditioning operating optimization parameters;

[0074] Step S4: Verify the energy consumption reduction effect of the air conditioning operation optimization parameters to obtain the energy consumption optimization verification results; perform energy utilization efficiency feedback adjustment based on the energy consumption optimization verification results to obtain the terminal air conditioning operation optimization report to perform online diagnosis and optimization of air conditioning terminal energy efficiency.

[0075] The present invention captures the power consumption of the data center's terminal air conditioning system and monitors the power consumption of the computer room's IT equipment and terminal air conditioning equipment in real time. This allows accurate collection of equipment power consumption data, providing a precise energy consumption data base for the data center. By analyzing and processing this data in real time, utilization efficiency evaluation indicators are calculated, which are then used to evaluate the energy efficiency of the computer room, quantify the data center's energy efficiency performance, and identify areas of energy inefficiency. Based on the evaluation results, computer rooms with low energy efficiency are located, a list of computer rooms to be optimized is generated, and terminal air conditioning operating parameters are optimized to improve the energy efficiency of these inefficient computer rooms. The energy consumption reduction effect of the optimized air conditioning operating parameters is verified, and energy utilization efficiency feedback adjustments are made based on these verification results. Ultimately, a terminal air conditioning operation optimization report is generated to ensure the effectiveness of the optimization measures, reduce energy consumption, and improve energy utilization efficiency, providing a scientific basis for online diagnosis and optimization of air conditioning terminal energy efficiency. Therefore, the present invention utilizes data processing, pattern recognition, and intelligent optimization technologies to determine the energy efficiency of the computer room terminal in real time, quickly identify energy efficiency shortcomings of the computer room's air conditioning terminal equipment, and optimize terminal air conditioning operation based on the terminal air conditioning terminal's operating mechanism, thereby reducing the operating energy consumption of the air conditioning terminal system.

[0076] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart showing the steps of an online diagnosis and optimization method for the energy efficiency of a data center air conditioning terminal according to the present invention. In this example, the online diagnosis and optimization method for the energy efficiency of a data center air conditioning terminal includes the following steps:

[0077] Step S1: Acquire the terminal air conditioning system of the data center; monitor the power consumption of the IT equipment in the computer room and the terminal air conditioning equipment in real time to obtain the power consumption data of the equipment;

[0078] In an embodiment of the present invention, first, by deploying devices such as smart sensors and industrial smart gateways, real-time data collection of power consumption of IT equipment and terminal air conditioning equipment in the computer room is achieved. These sensors can monitor electrical indicators including but not limited to current, voltage, temperature, and power, and upload the data to a cloud platform via IoT communication technologies such as DLT / 645 and Modbus. The cloud platform integrates IoT, cloud computing, and big data technologies to compare, calculate, analyze, and record the collected data, enabling remote control, real-time alarms, statistical calculations, energy-saving management, and big data analysis for power safety and energy management. Next, the data center computer room environmental monitoring system monitors power supply and distribution information, precision air conditioning terminal information, temperature, humidity, water leakage, and other environmental parameters in real time, and uploads the data to a unified network management monitoring room (center) via the local area network for unified supervision. When the system detects that a parameter exceeds a safety threshold, it can provide multiple alarm methods such as interface alarms, multimedia voice alarms, SMS alarms, and telephone alarms, and record events for access and analysis. Finally, the intelligent control system of the refrigeration system collects relevant operating parameters of systems such as the refrigeration station, terminal air conditioners and IT loads, and uses automated management tools to reduce the dimension, reduce noise, and clean the parameters. After that, a special tool is used to perform correlation analysis on the completed tables to find the key parameters related to the power utilization ratio. Using artificial intelligence (AI) technology, the energy efficiency of the refrigeration system is optimized by automatically adjusting the various parameters of the refrigeration system.

[0079] Step S2: Analyze and process the equipment power consumption data in real time to calculate the utilization efficiency evaluation index; evaluate the energy efficiency of the computer room based on the utilization efficiency evaluation index to obtain the power efficiency evaluation result of the computer room;

[0080] In this embodiment of the present invention, the data center's terminal air conditioning system first uses smart sensors and gateway devices to collect real-time power usage data from IT equipment and air conditioning equipment, including electrical indicators such as current, voltage, and power. This data is uploaded to a cloud platform via IoT communication technology for storage and analysis. The cloud platform utilizes big data analysis technologies to compare, calculate, analyze, and record the collected data, enabling remote control, real-time alarms, statistical calculations, energy-saving management, and big data analysis for power safety and energy management. Specifically, the data center collects relevant operating parameters from systems such as refrigeration stations, terminal air conditioning units, and IT loads. Automated management tools are used to reduce the dimensions, reduce noise, and cleanse these parameters. Correlation analysis is then performed to identify key parameters related to the energy utilization ratio (EUR). Artificial intelligence (AI) technology is used to automatically adjust various refrigeration system parameters to optimize refrigeration system energy efficiency. The technical principle includes a 5-minute real-time data collection cycle, an EUR model with an accuracy of 99.50%, and an EUR reduction of 8% to 15%. Finally, the data center intelligent operation and management platform manages the data center's power system, environmental system, security system, power distribution system, HVAC system, fire protection system, servers and other infrastructure through a unified platform, and maximizes the operational efficiency and reliability of the data center through data analysis and aggregation.

[0081] Step S3: Locate computer rooms with low energy efficiency based on the results of the computer room power efficiency evaluation to obtain a list of computer rooms to be optimized; optimize the terminal air conditioning operating parameters in the list of computer rooms to be optimized to obtain the air conditioning operating optimization parameters;

[0082] In an embodiment of the present invention, first, the energy efficiency of the computer room is monitored and evaluated in real time through the data center intelligent operation and management platform (WiseEMP-DCIM) in combination with energy efficiency evaluation indicators such as PUE (Power Usage Effectiveness). The platform uses big data analysis technology, intelligent prediction and aggregation data to identify computer rooms with low energy efficiency and optimize the terminal air-conditioning operating parameters for the list of computer rooms to be optimized. Using AI technology, such as Huawei's iCooling@AI solution, through the reinforcement learning MPC algorithm, various scenarios are covered, including the number of air conditioners, internal and external unit models, layout differences, etc., to achieve micro-module support for cloud-based reasoning and optimization. On this basis, the genetic algorithm (GA) is used to optimize the refrigeration system. The algorithm simulates the natural selection and genetic mechanism of biological evolution, starting from a group of solutions (populations), and improving the solution through iterative selection, crossover and mutation until the optimization stop condition is met.

[0083] Step S4: Verify the energy consumption reduction effect of the air conditioning operation optimization parameters to obtain the energy consumption optimization verification results; perform energy utilization efficiency feedback adjustment based on the energy consumption optimization verification results to obtain the terminal air conditioning operation optimization report to perform online diagnosis and optimization of air conditioning terminal energy efficiency.

[0084] In an embodiment of the present invention, first, a neural network optimization algorithm is used to automatically adjust the air conditioning operating parameters to achieve energy consumption reduction. The algorithm simulates human brain neurons to establish a neural network model including an input layer, a hidden layer, and an output layer. By collecting historical energy consumption data as training samples, the neural network model is trained to predict energy consumption and adjust the operating parameters. Next, the card edge control algorithm is applied to monitor the operating status of the air conditioning system in real time, and the operating parameters are dynamically adjusted to ensure the comfort of the indoor environment while reducing energy consumption. The algorithm monitors indoor and outdoor temperatures, air conditioning operating time, APF and other data in real time, and judges the comfort of the indoor environment based on the monitoring data, and then adjusts the air conditioning operating parameters to perform online diagnosis and optimization of the air conditioning terminal energy efficiency.

[0085] Preferably, step S1 includes the following steps:

[0086] Step S11: Obtain the terminal air conditioning system of the data center;

[0087] Step S12: measuring the power consumption of IT equipment in the computer room on the terminal air conditioning system of the data center to obtain power consumption data of IT equipment in the computer room;

[0088] Step S13: measuring the power consumption of the terminal air-conditioning equipment of the data center terminal air-conditioning system to obtain the power consumption data of the terminal air-conditioning equipment;

[0089] Step S14: Integrate the power consumption data of the IT equipment in the computer room and the power consumption data of the terminal air-conditioning equipment to obtain the equipment power consumption data.

[0090] In this embodiment of the present invention, real-time monitoring of the data center's terminal air conditioning system is first achieved by deploying smart sensors and smart meters. Smart sensors collect environmental parameters within the computer room, such as temperature and humidity, while smart meters are installed at the input and output terminals of the UPS (uninterrupted power supply) to measure the power consumption of the power supply system. Monitoring of the cooling system's power consumption includes power consumption by the compressor, chilled water pump, cooling water system, and terminal chilled water system in the indoor air conditioning terminal and water-cooled refrigeration system. Next, to measure the power consumption of the computer room's IT equipment, a high-precision power quality analyzer is used to monitor IT equipment in real time. This instrument provides detailed power parameters, including current, voltage, power factor, and energy consumption. Power consumption of the terminal air conditioning equipment is measured by installing meters at key nodes in the air conditioning system, including but not limited to cooling towers, chillers, cooling pumps, and refrigeration pumps. The power consumption data of the computer room's IT equipment and the terminal air conditioning equipment are then integrated, a step involving data fusion technology. By constructing a multimodal data integration model, the collected power data is fed into the model for weighting, feature fusion, and data dimensionality reduction. Finally, the data center energy consumption analysis system conducts a comprehensive analysis of the collected power consumption data of IT equipment and air-conditioning equipment to obtain the PUE (Power Usage Effectiveness) and CLF (Cooling Load Factor) values ​​of each data center. These values ​​are key indicators for measuring data center energy efficiency.

[0091] Preferably, step S14 includes the following steps:

[0092] Step S141: Pre-processing the power consumption data of IT equipment in the computer room and the power consumption data of the terminal air-conditioning equipment to obtain equipment pre-processing data;

[0093] Step S142: performing feature synchronization on the device preprocessing data to obtain device feature synchronization data; performing feature alignment on the device feature synchronization data to generate device feature alignment data;

[0094] Step S143: performing structured inspection on the device feature alignment data to obtain structured inspection data; performing data fusion on the structured inspection data to obtain device power consumption data.

[0095] In this embodiment of the present invention, first, during the data preprocessing phase, data cleaning techniques are used to process raw electricity usage data. This includes steps such as removing outliers, filling missing values, and normalizing data. For example, mean filling is used to handle missing current readings, and voltage data is normalized using the Z-score normalization method to eliminate the influence of different dimensions. Next, during the feature synchronization phase, a multimodal data integration model is used to time-align data from different sensors to ensure consistency across time series across different data sources. For example, temperature sensor data is synchronized with power data recorded by a power quality analyzer through timestamp matching for subsequent analysis. During the feature alignment phase, cross-modal alignment techniques are used to map features from different modalities to the same feature space for easy comparison and analysis. For example, principal component analysis (PCA) is used to perform dimensionality reduction on electricity usage data from IT equipment and air conditioning equipment to extract key features. Subsequently, during the structured verification phase, structured verification is performed on the aligned device feature data to ensure data consistency and integrity. For example, a data model is constructed to verify that the data conforms to the expected format and type, eliminating data records that do not meet structured requirements. Finally, in the data fusion phase, data fusion technology is used to integrate the structured, verified data to form a comprehensive view of device electricity usage. For example, a weighted fusion algorithm can be used to assign different weights to data from different sources based on their reliability and accuracy, thereby synthesizing the final device electricity usage data.

[0096] Preferably, step S2 includes the following steps:

[0097] Step S21: Analyze the device power consumption data in real time to obtain a power consumption data stream; extract key features from the power consumption data stream to obtain key power consumption parameters;

[0098] Step S22: Identify the power consumption pattern of the key power consumption parameters to obtain the power consumption behavior pattern; monitor the power consumption trend of the power consumption behavior pattern to obtain power consumption trend data;

[0099] Step S23: quantifying the electricity utilization efficiency of the electricity consumption trend data to generate an efficiency evaluation index;

[0100] Step S24: performing an energy efficiency evaluation on the computer room based on the utilization efficiency evaluation index to obtain an evaluation result of the power efficiency of the computer room.

[0101] In this embodiment of the present invention, first, equipment power usage data is analyzed in real time to generate a power data stream. This step uses power quality analyzers such as the E6500 and VICTOR5000, which can monitor and record parameters such as current, voltage, and power in real time to generate power data streams. These data streams contain detailed power usage information for IT equipment and air conditioning equipment at different time points. Next, key features are extracted from the power data streams to obtain key power parameters. Data preprocessing techniques, such as missing data handling and data merging, ensure data integrity and consistency. Feature extraction techniques, such as principal component analysis (PCA), are then used to extract key power parameters, such as peak current and average power, from the large amount of raw data. Subsequently, power pattern recognition is performed on these key power parameters to obtain power usage patterns. In this step, machine learning algorithms, such as K-Means clustering, are applied to perform pattern recognition on the power parameters to distinguish different power usage behaviors, such as high-load and low-load periods. Furthermore, power usage trends are monitored based on the power usage patterns to obtain power usage trend data. Using time series analysis techniques, such as structural equation models, we monitor the changing trends of electricity usage over time, generating electricity usage trend data. This electricity usage trend data is then used to quantify electricity utilization efficiency and generate efficiency evaluation indicators. Using data fusion technology, we combine electricity usage data from various sources to quantify electricity efficiency and generate evaluation indicators such as the energy efficiency ratio (EER) and coefficient of performance (COP). Finally, we evaluate the energy efficiency of the computer room using the efficiency evaluation indicators to obtain the evaluation results. Using a weighted fusion algorithm, we comprehensively consider multiple evaluation indicators to evaluate the electricity usage efficiency of the computer room, obtaining final evaluation results, such as the Power Use Effectiveness (PUE) value, to assess the energy efficiency level of the computer room.

[0102] Preferably, step S24 includes the following steps:

[0103] Step S241: normalizing the utilization efficiency evaluation index to obtain a standardized evaluation index; and assigning weights to the standardized evaluation index to obtain a weighted evaluation index;

[0104] Step S242: performing a comprehensive calculation on the weighted evaluation indicators to obtain a comprehensive score of the power efficiency of the computer room; and classifying the comprehensive score of the power efficiency of the computer room to obtain a level evaluation of the power efficiency of the computer room;

[0105] Step S243: presenting the results of the level evaluation of the power efficiency of the computer room, and obtaining the evaluation results of the power efficiency of the computer room.

[0106] In an embodiment of the present invention, the utilization efficiency evaluation index is first normalized to obtain a standardized evaluation index. In this step, the Min-Max normalization method is used to scale the original data to the interval [0, 1]. Next, the standardized evaluation index is weighted to obtain a weighted evaluation index. The weight assignment is based on the importance of each index to energy efficiency. For example, the PUE value is assigned a higher weight because it directly reflects the energy efficiency level of the data center. The weight is determined through expert scoring or the analytic hierarchy process (AHP) to ensure that the weight of each index reflects its relative importance in the overall evaluation. Then, the weighted evaluation index is comprehensively calculated to obtain a comprehensive score for the power efficiency of the computer room. In this step, the arithmetic mean method or the weighted harmonic mean method is used to combine the weighted indicators to obtain a comprehensive score that comprehensively reflects the power efficiency of the computer room. Furthermore, the comprehensive score of the power efficiency of the computer room is graded to obtain a grade evaluation of the power efficiency of the computer room. The ratings are categorized into several levels, such as "Excellent," "Good," "Fair," and "Poor," based on the numerical range of the scores. The specific grading criteria are set according to industry or internal company standards. Finally, the results of the computer room's electrical energy efficiency rating are presented, resulting in the evaluation results. In this step, data visualization technologies, such as D3.js combined with the React framework, are used to visually display the evaluation results in the form of charts, enabling operations and maintenance personnel to quickly understand the computer room's energy efficiency status and make appropriate optimization decisions.

[0107] Preferably, step S3 includes the following steps:

[0108] Step S31: setting a threshold for the power efficiency evaluation results of the computer room to obtain preliminary screening data of inefficient computer rooms;

[0109] Step S32: removing abnormal values ​​from the preliminarily screened inefficient computer room data to obtain inefficient parameter-removed data;

[0110] Step S33: Prioritize the preliminarily screened inefficient computer room data based on the inefficient parameter elimination data to obtain a priority list of inefficient computer rooms; extract computer rooms with low energy efficiency from the priority list of inefficient computer rooms to obtain a list of computer rooms to be optimized;

[0111] Step S34: Optimize the terminal air-conditioning operating parameters for the list of computer rooms to be optimized to obtain the air-conditioning operating optimization parameters.

[0112] In an embodiment of the present invention, a threshold is first set for the results of the computer room power efficiency evaluation to obtain preliminary data for inefficient computer rooms. In this step, the threshold is determined using the quantile method in statistics. For example, computer rooms with a PUE value greater than a certain percentile are defined as inefficient. Based on the distribution of computer room PUE values, a reasonable threshold, such as the 90th percentile, is determined. All computer rooms above this threshold are preliminarily identified as inefficient. Next, outliers are removed from the preliminarily screened inefficient computer room data to obtain inefficient parameter-removed data. This outlier removal process calculates the mean and standard deviation and sets a range (e.g., mean ± 3 times the standard deviation) to identify outliers. Values ​​outside this range are considered outliers and removed from the data set to ensure the accuracy of subsequent analysis. Then, the preliminarily screened inefficient computer room data is prioritized based on the inefficient parameter-removed data to obtain a priority list of inefficient computer rooms. In this step, a multi-objective optimization algorithm, such as NSGA-II, is used, which can simultaneously consider multiple optimization objectives to prioritize inefficient computer rooms. Factors considered during sorting include energy consumption, cost, and environmental impact. Furthermore, the priority list of inefficient computer rooms is extracted to identify computer rooms with low energy efficiency, resulting in a list of computer rooms to be optimized. In this step, clustering algorithms such as DBSCAN are used, which can cluster data based on density and identify computer rooms with low energy efficiency. By setting appropriate epsilon and min_samples parameters, the DBSCAN algorithm can identify computer rooms with low density, i.e., the computer rooms to be optimized. Finally, the terminal air conditioning operating parameters of the list of computer rooms to be optimized are optimized to obtain the optimized air conditioning operating parameters. The optimization process uses a genetic algorithm, which continuously iterates and optimizes the air conditioning operating parameters through steps such as population initialization, fitness evaluation, selection, crossover, and mutation to achieve the goal of reducing energy consumption. For example, by adjusting parameters such as temperature setting values ​​and operating time, the optimal operating parameter combination is found to maximize energy efficiency.

[0113] Preferably, step S34 includes the following steps:

[0114] Step S341: collecting initial operating parameters of the terminal air conditioners in the list of computer rooms to be optimized to obtain basic operating data of the air conditioners;

[0115] Step S342: Perform performance analysis on the basic data of air conditioner operation to obtain operation performance indicators;

[0116] Step S343: Optimizing the key performance indicators to obtain performance indicator optimization data;

[0117] Step S344: Adjust the operating parameters of the list of computer rooms to be optimized based on the performance indicator optimization data to obtain air conditioning operation optimization parameters.

[0118] In this embodiment of the present invention, initial operating parameters of the terminal air conditioners in the list of computer rooms to be optimized are first collected to obtain basic air conditioner operating data. In this step, building automation systems (BAS) or data center infrastructure management (DCIM) software are used to collect real-time operating parameters of the terminal air conditioners, including but not limited to compressor speed, inverter frequency, fan speed, and surface cooling valve opening, using various sensors installed on the air conditioning systems, such as temperature, humidity, and pressure sensors. Next, performance analysis is performed on the basic air conditioner operating data to obtain operating performance indicators. In this step, big data analysis techniques are used to statistically analyze and calculate key performance indicators, such as energy efficiency ratio (EER), coefficient of performance (COP), and energy consumption. The key performance indicators are then optimized to obtain optimized performance indicator data. In this step, machine learning algorithms, such as neural networks or support vector machines (SVMs), are applied to perform pattern recognition and prediction on the performance indicators, identify key factors affecting energy efficiency, and propose optimization directions. Furthermore, based on the optimized performance indicator data, operating parameters are adjusted for the list of computer rooms to obtain optimized air conditioner operating parameters. In this step, genetic algorithms or particle swarm optimization (PSO) algorithms are used to iteratively search for optimal operating parameters, such as set temperature and wind speed, by simulating natural selection or group behavior to maximize energy efficiency.

[0119] Preferably, step S344 includes the following steps:

[0120] Step S3441: Identify factors affecting air conditioning energy efficiency based on the performance index optimization data to obtain an energy efficiency optimization target;

[0121] Step S3442: performing parameter association mapping on the energy efficiency optimization target to obtain parameter adjustment mapping data;

[0122] Step S3443: Dynamically adjust the list of computer rooms to be optimized according to the parameter adjustment mapping data to obtain computer room operation adjustment data;

[0123] Step S3444: Perform feedback loop optimization on the computer room operation adjustment data to obtain air conditioning operation optimization parameters.

[0124] In this embodiment of the present invention, factors influencing air conditioner energy efficiency are first identified within the performance indicator optimization data to obtain an energy efficiency optimization target. In this step, big data analysis techniques are employed to collect historical energy consumption data, including indoor and outdoor temperatures, air conditioner operating hours, and APF, and then a machine learning algorithm is used to establish an energy consumption prediction model. For example, data analysis revealed that the number of air supply levels and set temperature have a significant impact on air conditioner energy efficiency. Next, parameter association mapping is performed on the energy efficiency optimization target to obtain parameter adjustment mapping data. In this step, the particle swarm optimization (PSO) algorithm is used for parameter optimization. Key parameters include inertia weight, self-learning factor, and swarm learning factor. These parameters are adjusted to find the optimal air conditioner operating parameters. Then, the list of computer rooms to be optimized is dynamically adjusted based on the parameter adjustment mapping data to obtain computer room operation adjustment data. In this step, dynamic adjustment algorithms, such as DQN network parameter adjustment, are applied to achieve performance optimization. The DQN network continuously adjusts its strategy through reinforcement learning to adapt to the changing environment and optimize energy efficiency. Finally, a feedback loop optimization is performed on the computer room operation adjustment data to obtain the optimized air conditioner operating parameters. Feedback control mechanisms, such as the card-edge control algorithm, monitor the air conditioning system's operating status in real time and dynamically adjust operating parameters to ensure indoor comfort while reducing energy consumption. For example, real-time monitoring of indoor and outdoor temperatures, air conditioning operating hours, and APF data can be used to adjust air conditioning operating parameters such as temperature setpoints and fan speeds accordingly.

[0125] As an example of the present invention, refer to Figure 2 As shown, in this example, step S4 includes:

[0126] Step S41: Compare energy consumption data before and after the implementation of the air-conditioning operation optimization parameters to obtain energy consumption comparison data;

[0127] Step S42: performing statistical analysis on the energy consumption comparison data to obtain energy consumption statistical results; performing trend identification on the energy consumption statistical results to obtain energy consumption trend data;

[0128] Step S43: Evaluate the effect of the energy consumption trend analysis to obtain energy consumption optimization verification results;

[0129] Step S44: Based on the energy consumption optimization verification result, energy utilization efficiency feedback adjustment is performed to obtain a terminal air-conditioning operation optimization report to perform air-conditioning terminal energy efficiency online diagnosis and optimization operations.

[0130] In this embodiment of the present invention, energy consumption data before and after the air conditioning operation optimization parameters are implemented is first compared to obtain energy consumption comparison data. In this step, a comprehensive energy management system is used to query energy consumption comparisons for different energy types within the query time period, by region, department, circuit, and network. This includes year-on-year, month-on-month, and horizontal comparisons. By logging into the energy management system platform, selecting the corresponding hierarchical dimension and energy type, and setting the query time dimension and range, the system automatically calculates and displays the energy consumption comparison results. Next, statistical analysis is performed on the energy consumption comparison data to obtain energy consumption statistics. Simultaneously, trends are identified within the energy consumption statistics to obtain energy consumption trend data. In this step, big data analysis techniques are used to conduct in-depth analysis of the collected energy consumption data, calculating the monthly year-on-year energy consumption of each energy source and visually displaying it through charts such as line charts, bar charts, and stacked graphs, with support for saving images to local storage. The effectiveness of the energy consumption trend analysis is then evaluated to obtain energy consumption optimization verification results. In this step, energy efficiency assessment and improvement methods, such as the energy efficiency ratio (EER), are applied to measure the performance of the electrical energy system, identify and quantify energy losses in the system, and provide improvement strategies. Finally, based on the energy consumption optimization verification results, energy efficiency feedback adjustments are made to generate an optimized terminal air conditioning operation report. In this step, data center air conditioning terminal cooling evaluation indicators and abnormality diagnosis methods are used to determine the real-time balance between cooling supply and demand in the computer room, quickly identify energy efficiency shortcomings of the computer room air conditioning terminal equipment, and achieve efficient and accurate cooling supply, thereby improving cooling utilization efficiency.

[0131] As an example of the present invention, refer to Figure 3 As shown, in this example, step S44 includes:

[0132] Step S441: performing energy consumption reduction analysis on the energy consumption optimization verification result to obtain energy consumption analysis data;

[0133] Step S442: performing efficiency impact assessment on the energy consumption analysis data to obtain efficiency influencing factors; performing weight adjustment on the efficiency influencing factors to obtain adjusted weight data;

[0134] Step S443: Applying feedback loop to the adjusted weights to obtain real-time optimization parameters; monitoring the effects of the real-time optimization parameters to obtain a terminal air conditioning operation optimization report;

[0135] Step S444: Continuously optimize the terminal air conditioning system of the data center based on the terminal air conditioning operation optimization report to perform online diagnosis and optimization of the air conditioning terminal energy efficiency.

[0136] In this embodiment of the present invention, energy consumption optimization verification results are first analyzed for energy reduction, generating energy consumption analysis data. This step utilizes a data center air conditioning terminal cooling evaluation index and anomaly diagnosis system. This system collects IT power consumption, terminal air cabinet power consumption, and operating parameters from each computer room, calculates each room's E-ACTE value, and determines the energy consumption of the computer room's air conditioning terminal, thereby generating energy consumption analysis data. Next, efficiency impact assessment is performed on the energy consumption analysis data to determine efficiency influencing factors. These efficiency influencing factors are then weighted to generate adjusted weighted data. This step utilizes a multi-objective optimization method based on a genetic algorithm. This method uses minimizing the system's annual total energy consumption and annual total operating costs as the objective function, with design variables such as the system's cooling capacity, heating capacity, ice storage capacity, and ground-source heat pump power. The optimization algorithm adjusts the weights of each efficiency influencing factor to minimize energy consumption and costs. The adjusted weights are then applied in a feedback loop to generate real-time optimized parameters. Simultaneously, the effectiveness of the real-time optimized parameters is monitored to generate a terminal air conditioning operation optimization report. By applying a neural network optimization algorithm and simulating human brain neurons, the air conditioning operating parameters can be automatically adjusted, and the operating status of the air conditioning system can be monitored and optimized in real time to ensure indoor environmental comfort while reducing energy consumption. Finally, the data center terminal air conditioning system is continuously optimized based on the terminal air conditioning operation optimization report to perform online diagnosis and optimization of the air conditioning terminal energy efficiency. In this step, an air conditioning system energy efficiency online detection and diagnosis analyzer and method are used to monitor and record the pressure, temperature, flow rate of the computer room pipeline and the power consumption data of the water pump, cooling tower, and unit in real time. The water pump efficiency, unit energy efficiency ratio, system energy efficiency ratio, water pump transmission and other data are calculated and analyzed. The analyzed data is compared with relevant data from similar computer rooms to analyze energy costs and the status of computer room equipment, analyze factors affecting energy efficiency, optimize the system's operating strategy, improve the system's overall energy efficiency, and reduce operating costs.

[0137] As an example of the present invention, refer to Figure 4 As shown in FIG. 1 , a control logic diagram of an online diagnosis and optimization method for energy efficiency of a data center air conditioning terminal in this example is shown. Taking the data center of this application as an example, the specific implementation of the present invention is described.

[0138] Smart meters are installed on each floor of the data center to obtain the power consumption of the IT equipment in the computer room and the power consumption of the terminal air conditioners. Specifically, each computer room is equipped with a set of smart meters to monitor the total power consumption of the IT equipment in the cabinet and the total power consumption of the terminal air conditioners. Among them, smart meter 1 monitors the total power consumption of all IT equipment in computer room 1, P 1-1 And the total power consumption of all terminal air conditioners P 1-2 Smart meter 2 monitors the total power consumption P of all IT equipment in computer room 2. 2-1 And the total power consumption of all terminal air conditioners P 2-2Similarly, smart meter N monitors the total power consumption P of all IT equipment in room N. N-1 And the total power consumption of all terminal air conditioners P N-2 Install sensors at the air outlet and return air outlet of the terminal air conditioner to monitor the air supply temperature T of the terminal air conditioner. N1 , return air temperature T N2 , used to preliminarily determine whether the terminal cooling supply meets the cooling load demand of the computer room; fan inverters and water valve opening controllers are installed on the terminal air conditioners to adjust the fan operating frequency and chilled water flow rate;

[0139] Calculate the C-value energy efficiency index of the air conditioning terminal in each computer room:

[0140]

[0141] Among them, C N Indicates the C value of the Nth computer room; P N-2 Indicates the IT power consumption of the Nth computer room; P N-1 Indicates the power consumption of the terminal air conditioner in the Nth computer room; for example, Computer Room 2 Computer Room 3 , in computer room 4 Computer Room N Baseline L base ; Compare the C value data of the computer room cooled by the same type of terminal air conditioner with the energy efficiency baseline.

[0142]

[0143] For the machine room with alarm status, analyze the supply and return air temperature difference of each air cabinet in the machine room. Take the Nth air cabinet as an example, according to the air cabinet supply air temperature T N1 , return air temperature T N2 Calculate the supply and return air temperature difference ΔT N =T N2 -T N1 If ΔTN>temperature difference limit ΔT limit +deviationT de , indicating that the heat exchange effect of the typhoon cabinet is good. If the supply and return air temperature difference of all terminal air conditioners is greater than the temperature difference limit ΔT limit +deviationT de , indicating that the cooling capacity of the computer room is too small, and the proportional integral valve opening of the terminal air-conditioning fan needs to be increased by 2%; if the supply and return air temperature difference ΔTN of the terminal air-conditioning is less than the temperature difference limit, it indicates that the operation of the terminal air-conditioning is abnormal, and further diagnosis of the cause of the abnormal operation of the air cabinet is required.

[0144] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0145] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for online diagnosis and optimization of energy efficiency of air conditioning terminals in a data center, characterized in that: The following steps are involved: Step S1: Acquire the terminal air conditioning system of the data center; monitor the power consumption of the IT equipment in the computer room and the terminal air conditioning equipment in real time to obtain the power consumption data of the equipment; Step S2: Analyze and process the equipment power consumption data in real time to calculate the utilization efficiency evaluation index; The energy efficiency of the computer room is evaluated based on the utilization efficiency evaluation index to obtain the power efficiency evaluation result of the computer room; wherein step S2 includes the following steps: Step S21: Analyze the device power consumption data in real time to obtain a power consumption data stream; extract key features from the power consumption data stream to obtain key power consumption parameters; Step S22: Identify the power consumption pattern of the key power consumption parameters to obtain the power consumption behavior pattern; monitor the power consumption trend of the power consumption behavior pattern to obtain power consumption trend data; Step S23: quantifying the electricity utilization efficiency of the electricity consumption trend data to generate an efficiency evaluation index; Step S24: performing an energy efficiency evaluation on the computer room based on the utilization efficiency evaluation index to obtain an evaluation result of the power efficiency of the computer room; Step S3: Locate computer rooms with low energy efficiency based on the results of the computer room power efficiency evaluation to obtain a list of computer rooms to be optimized; optimize the terminal air conditioning operating parameters in the list of computer rooms to be optimized to obtain the air conditioning operating optimization parameters; Step S4: Verify the energy consumption reduction effect of the air conditioning operation optimization parameters to obtain the energy consumption optimization verification results; perform energy utilization efficiency feedback adjustment based on the energy consumption optimization verification results to obtain the terminal air conditioning operation optimization report to perform online diagnosis and optimization of air conditioning terminal energy efficiency.

2. The online diagnosis and optimization method for energy efficiency of air conditioning terminals in a data center according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtain the terminal air conditioning system of the data center; Step S12: measuring the power consumption of IT equipment in the computer room on the terminal air conditioning system of the data center to obtain power consumption data of IT equipment in the computer room; Step S13: measuring the power consumption of the terminal air-conditioning equipment of the data center terminal air-conditioning system to obtain the power consumption data of the terminal air-conditioning equipment; Step S14: Integrate the power consumption data of the IT equipment in the computer room and the power consumption data of the terminal air-conditioning equipment to obtain the equipment power consumption data.

3. The online diagnosis and optimization method for energy efficiency of data center air conditioning terminals according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: Pre-processing the power consumption data of IT equipment in the computer room and the power consumption data of the terminal air-conditioning equipment to obtain equipment pre-processing data; Step S142: performing feature synchronization on the device preprocessing data to obtain device feature synchronization data; performing feature alignment on the device feature synchronization data to generate device feature alignment data; Step S143: performing structured inspection on the device feature alignment data to obtain structured inspection data; performing data fusion on the structured inspection data to obtain device power consumption data.

4. The online diagnosis and optimization method for energy efficiency of air conditioning terminals in a data center according to claim 1 is characterized in that: Step S24 includes the following steps: Step S241: normalizing the utilization efficiency evaluation index to obtain a standardized evaluation index; and assigning weights to the standardized evaluation index to obtain a weighted evaluation index; Step S242: performing a comprehensive calculation on the weighted evaluation indicators to obtain a comprehensive score of the power efficiency of the computer room; and classifying the comprehensive score of the power efficiency of the computer room to obtain a level evaluation of the power efficiency of the computer room; Step S243: presenting the results of the level evaluation of the power efficiency of the computer room, and obtaining the evaluation results of the power efficiency of the computer room.

5. The online diagnosis and optimization method for energy efficiency of air conditioning terminals in a data center according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: setting a threshold for the power efficiency evaluation results of the computer room to obtain preliminary screening data of inefficient computer rooms; Step S32: removing abnormal values ​​from the preliminarily screened inefficient computer room data to obtain inefficient parameter-removed data; Step S33: Prioritize the preliminarily screened inefficient computer room data based on the inefficient parameter elimination data to obtain a priority list of inefficient computer rooms; extract computer rooms with low energy efficiency from the priority list of inefficient computer rooms to obtain a list of computer rooms to be optimized; Step S34: Optimize the terminal air-conditioning operating parameters for the list of computer rooms to be optimized to obtain the air-conditioning operating optimization parameters.

6. The method for online diagnosis and optimization of energy efficiency of air conditioning terminals in a data center according to claim 5 is characterized in that: Step S34 includes the following steps: Step S341: collecting initial operating parameters of the terminal air conditioners in the list of computer rooms to be optimized to obtain basic operating data of the air conditioners; Step S342: Perform performance analysis on the basic data of air conditioner operation to obtain operation performance indicators; Step S343: Optimizing the key performance indicators to obtain performance indicator optimization data; Step S344: Adjust the operating parameters of the list of computer rooms to be optimized based on the performance indicator optimization data to obtain air conditioning operation optimization parameters.

7. The method for online diagnosis and optimization of energy efficiency of air conditioning terminals in a data center according to claim 6 is characterized in that: Step S344 includes the following steps: Step S3441: Identify factors affecting air conditioning energy efficiency based on the performance index optimization data to obtain an energy efficiency optimization target; Step S3442: performing parameter association mapping on the energy efficiency optimization target to obtain parameter adjustment mapping data; Step S3443: Dynamically adjust the list of computer rooms to be optimized according to the parameter adjustment mapping data to obtain computer room operation adjustment data; Step S3444: Perform feedback loop optimization on the computer room operation adjustment data to obtain air conditioning operation optimization parameters.

8. The method for online diagnosis and optimization of energy efficiency of air conditioning terminals in a data center according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: Compare energy consumption data before and after the implementation of the air-conditioning operation optimization parameters to obtain energy consumption comparison data; Step S42: performing statistical analysis on the energy consumption comparison data to obtain energy consumption statistical results; performing trend identification on the energy consumption statistical results to obtain energy consumption trend data; Step S43: Evaluate the effect of the energy consumption trend analysis to obtain energy consumption optimization verification results; Step S44: Based on the energy consumption optimization verification result, energy utilization efficiency feedback adjustment is performed to obtain a terminal air-conditioning operation optimization report to perform air-conditioning terminal energy efficiency online diagnosis and optimization operations.

9. The method for online diagnosis and optimization of energy efficiency of air conditioning terminals in a data center according to claim 8, characterized in that: Step S44 includes the following steps: Step S441: performing energy consumption reduction analysis on the energy consumption optimization verification result to obtain energy consumption analysis data; Step S442: performing efficiency impact assessment on the energy consumption analysis data to obtain efficiency influencing factors; performing weight adjustment on the efficiency influencing factors to obtain adjusted weight data; Step S443: Applying feedback loop to the adjusted weights to obtain real-time optimization parameters; monitoring the effects of the real-time optimization parameters to obtain a terminal air conditioning operation optimization report; Step S444: Continuously optimize the terminal air conditioning system of the data center based on the terminal air conditioning operation optimization report to perform online diagnosis and optimization of the air conditioning terminal energy efficiency.

Images