Air conditioning operation and maintenance system and method for air-cooled data center and electronic equipment

Abstract

The embodiment of the present application relates to the air conditioning operation and maintenance technical field, disclose an air-cooled data center air conditioning operation and maintenance system, method and electronic equipment.The system comprises: data acquisition module and energy-saving module;The data acquisition module is used for collecting air conditioner operation data and air conditioner environment data;The energy-saving module is used for establishing air conditioner system operation model, the air conditioner system operation model includes white box model, grey box model and fourth paradigm compact data model, and according to the air conditioner operation data and air conditioner environment data, respectively output the air conditioner operation optimization strategy corresponding to the white box model, the grey box model and the fourth paradigm compact data model.Through the above mode, the embodiment of the present application realizes the energy-saving operation of air conditioning equipment in air-cooled data center.

Description

Technical Field

[0001] This invention relates to the field of air conditioning operation and maintenance technology, specifically to an air conditioning operation and maintenance system, method, and electronic equipment for an air-cooled data center. Background Technology

[0002] With the continuous acceleration of network infrastructure construction, the number of data centers is constantly increasing, and at the same time, the requirements for data center operation and maintenance systems are also constantly rising. Based on their capacity, data centers are generally divided into large data centers and small-to-medium-sized data centers.

[0003] Because data center servers generate a large amount of heat during operation, air conditioning equipment is typically used to cool them down in a timely manner to ensure their normal operation. In related technologies, large data centers generally use cooling towers in large chilled water systems to cool the cooling water, thus providing a chilled water source for the data center; while small and medium-sized data centers generally use air-cooled systems, which use cold air to directly cool the refrigerant, thereby providing a reliable cooling environment for the data center. However, in implementing the embodiments of this invention, the inventors discovered that air-cooled data centers in related technologies have high energy consumption, and their air conditioning operation and maintenance only focuses on power and environmental monitoring, lacking itemized metering and energy consumption analysis, and thus lacking energy-saving solutions. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide an air conditioning operation and maintenance system, method and electronic equipment for air-cooled data centers, which are used to solve the problem of lack of energy-saving operation schemes for air conditioning in air-cooled data centers in the prior art.

[0005] According to one aspect of the present invention, an air conditioning operation and maintenance system for an air-cooled data center is provided, characterized in that the system includes: a data acquisition module and an energy-saving module;

[0006] The data acquisition module is used to collect air conditioning operation data and air conditioning environment data;

[0007] The energy-saving module is used to establish an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, the module outputs the air conditioning operation energy-saving strategies corresponding to the white-box model, the gray-box model, and the fourth-paradigm compact data model, respectively.

[0008] In one alternative approach, the data acquisition module is used to collect the air conditioner operation data and the air conditioner environment data in the following manner:

[0009] Data is collected by connecting to a power and environmental monitoring system; and / or,

[0010] Data is collected by connecting to the power equipment and air conditioning terminal equipment within the data center; and / or,

[0011] Data is collected through hardware sensors connected to IoT / 5G networks.

[0012] In one alternative approach, the air conditioning operation energy-saving strategy corresponding to the white box model includes an air conditioning operation parameter optimization strategy, which includes an evaporation cycle rule library, a condensation temperature optimization strategy, a partial load high-efficiency operating point, and energy-saving suggestions for the transmission and distribution system.

[0013] The energy-saving strategy for air conditioning operation corresponding to the gray box model is used to realize the optimal control logic between devices and between devices and the environment, and to control the working status of air conditioners in the corresponding locations according to the load distribution and air conditioner distribution.

[0014] The energy-saving strategy for air conditioning operation corresponding to the fourth paradigm compact data model includes overall energy consumption optimization spatial analysis and real-time monitoring of the data center, predicting the energy consumption of the air conditioning system and finding the optimal solution.

[0015] In one alternative approach, the air conditioning operating data includes air conditioning terminal parameters, which include air supply air temperature, supply air humidity, return air temperature, return air humidity, and fan speed and power.

[0016] The air conditioning environment data includes data center environment parameters and rack parameters. The data center environment parameters include outside temperature, outside humidity, data center temperature, data center humidity, cold aisle temperature, cold aisle humidity, hot aisle temperature, and hot aisle humidity. The rack parameters include front door temperature, front door humidity, rear door temperature, rear door humidity, rack exhaust air velocity, rack power, power distribution cabinet power, and leakage detection parameters.

[0017] In an alternative embodiment, the system further includes a health diagnostic module, which is used for:

[0018] Perform design verification and control optimization for the air conditioning equipment itself; analyze and evaluate the energy consumption of the power distribution system; provide optimization suggestions for the overall monitoring system and equipment system of the computer room; analyze and judge the causes of equipment and computer room abnormalities and failures and provide solutions to the failures.

[0019] In an alternative embodiment, the system further includes an intelligent inspection module, which is used for:

[0020] Environmental data of the data center is collected through remote video, VR / AR technology and intelligent robots, and abnormal data is identified and alerted.

[0021] In one alternative approach, the air conditioning operation and maintenance system further includes a visualization module deployed at the application layer;

[0022] The data acquisition module is deployed at the physical layer, while the energy-saving module, the health diagnosis module, and the intelligent inspection module are deployed at the business layer.

[0023] According to another aspect of the present invention, an air conditioning operation and maintenance method for an air-cooled data center is provided, which is applied to an air conditioning operation and maintenance system for an air-cooled data center. The system includes a data acquisition module and an energy-saving module. The method includes:

[0024] The data acquisition module collects air conditioner operation data and air conditioner environment data;

[0025] The energy-saving module establishes an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, it outputs the air conditioning operation optimization strategies corresponding to the white-box model, the gray-box model, and the fourth-paradigm compact data model, respectively.

[0026] According to another aspect of the present invention, an electronic device is provided, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0027] The memory is used to store at least one executable instruction, which causes the processor to perform the operation of the air conditioning operation and maintenance method for the air-cooled data center described above.

[0028] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores at least one executable instruction, which, when executed on an electronic device, causes the electronic device to perform the operation of the above-described air conditioning operation and maintenance method for an air-cooled data center.

[0029] The air conditioning operation and maintenance system for an air-cooled data center according to this invention includes a data acquisition module and an energy-saving module. The data acquisition module is used to collect air conditioning operation data and air conditioning environment data. The energy-saving module is used to establish an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, the module outputs air conditioning operation energy-saving strategies corresponding to the white-box model, gray-box model, and fourth-paradigm compact data model, respectively. It can be seen that this invention can perform data analysis on air conditioning operation data and air conditioning environment data for an air-cooled data center's air conditioning operation and maintenance system, thereby proposing air conditioning operation energy-saving strategies and reducing air conditioning energy consumption.

[0030] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0031] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0032] Figure 1 This diagram illustrates the structure of an air-cooled data center air conditioning operation and maintenance system provided in an embodiment of the present invention.

[0033] Figure 2 This invention illustrates a schematic diagram of the data acquisition architecture of an air conditioning operation and maintenance system provided in an embodiment of the present invention.

[0034] Figure 3 This invention provides another structural schematic diagram of an air conditioning operation and maintenance system for a wind-cooled data center, as illustrated in an embodiment of the invention.

[0035] Figure 4 A schematic diagram of the model training process provided in an embodiment of the present invention is shown;

[0036] Figure 5 This diagram illustrates the data judgment process of the health diagnosis module provided in an embodiment of the present invention.

[0037] Figure 6 A flowchart illustrating the air conditioning operation and maintenance method for an air-cooled data center provided in an embodiment of the present invention is shown.

[0038] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention is shown. Detailed Implementation

[0039] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0040] Data centers are generally divided into large data centers and small and medium-sized data centers. Large data centers are typically operated and maintained through power and environmental monitoring systems, which also include energy consumption statistics. In contrast, small and medium-sized data centers are generally only operated and maintained through power and environmental monitoring systems, without involving the metering and analysis of individual energy consumption items. Their overall operation and maintenance systems need improvement.

[0041] Large data centers typically employ water-cooled server rooms and utilize data center infrastructure management (DCIM) methods for operation and maintenance. This includes data collection, analysis, and prediction of data center infrastructure data, as well as automated management of data center infrastructure systems and components to optimize infrastructure efficiency. Data center infrastructure data includes air temperature, airflow, water temperature, and water flow data. First, hardware controllers acquire the operational status of infrastructure and components. Then, they analyze whether ambient air temperature, flow rate, water temperature, and water flow are within specified ranges. Finally, they predictively analyze future infrastructure system conditions, future environmental conditions, and future component or component conditions. The operation and maintenance of large data centers involves comprehensive management of temperature, humidity, power, machinery, cooling, and energy. Air conditioning, however, is primarily managed through data monitoring and DCIM unit controllers to adjust parameters such as server room temperature and humidity within normal operating ranges.

[0042] Small and medium-sized data centers deploy numerous critical network service nodes. Currently, most air-cooled data center air conditioners use precision air conditioners or even comfort air conditioners designed for base stations, leading to significant cooling pressure. The current state of data center operations is characterized by phased deployment of different service racks, varying equipment sizes and layouts from different vendors, and multiple air outlet configurations, resulting in chaotic airflow organization. Therefore, assessment and energy-saving analysis are necessary. However, existing operations for small and medium-sized data centers only monitor air conditioning data and lack a suitable operation and maintenance system and complete process methodology for air-cooled data center air conditioning. This includes functions and methods for model building, energy-saving analysis, parameter configuration evaluation, and optimization.

[0043] This invention establishes a model applicable to air-cooled data center air conditioning systems, performs energy-saving optimization analysis, and proposes energy-saving operation solutions to achieve energy conservation and consumption reduction in data centers. It collects, stores, and performs big data analysis and application of air conditioning operation data from data centers in various locations, conducts dynamic real-time simulation of the data center system, and realizes the evaluation and prediction of the computer room environment and the configuration parameters of each device, proposing optimization schemes to solve problems such as poor airflow / local overheating. Furthermore, it proposes a system fault diagnosis method to identify abnormal operating conditions, perform health and fault diagnosis, and propose specific solutions to achieve proactive and predictable maintenance of the air conditioning system, ensuring its safe and reliable operation.

[0044] Figure 1 A schematic diagram of the air conditioning operation and maintenance system for an air-cooled data center according to an embodiment of the present invention is shown. Figure 1 As shown, the system 100 includes a data acquisition module 110 and an energy-saving module 120.

[0045] The data acquisition module 110 is used to collect air conditioning operation data and air conditioning environment data; the energy-saving module 120 is used to establish an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, it outputs air conditioning operation optimization strategies corresponding to the white-box model, gray-box model, and fourth-paradigm compact data model, respectively. It should be noted that the air conditioning operation and maintenance system can be deployed in cloud, virtual machine, and stand-alone modes. It can interface with the environmental monitoring systems of data centers in various locations to achieve cloud data acquisition and monitoring functions, while local data centers can deploy through local clusters.

[0046] Figure 2 A schematic diagram of the data acquisition architecture of the air conditioning operation and maintenance system provided in an embodiment of the present invention is shown. Figure 2As shown, the primary system is a data center air conditioning operation and maintenance system deployed in the cloud, and the secondary system consists of data centers in various locations. The primary system is compatible with and can connect to multiple secondary systems, and each secondary system is independent of the others. The secondary systems can interact with the environmental monitoring system platform through database ports and software protocol point tables. The environmental monitoring system platform collects operational data of the monitored objects through sensors. To enable the data acquisition module 110 to efficiently and stably collect air conditioning operation data and air conditioning environment data, the data acquisition module 110 needs to support the data transmission protocols in the software protocol point table, including but not limited to BACNet, Modbus, and C protocols. Furthermore, the data acquisition system 110 must be able to connect to the power and environmental monitoring systems of various data centers, thereby continuously collecting various data from the power and environmental monitoring system platform and uploading the data to the server deployed in the cloud. It should be noted that the power and environmental monitoring system is a general monitoring system for data centers, monitoring objects including power equipment and the computer room environment. It performs telemetry, remote signaling, and remote control of relevant parameters, monitors the operating status of the system and equipment in real time, and collects and processes relevant data. The monitoring information is uploaded by the collector to the backend environmental monitoring system platform. In addition to collecting air conditioning operation and environmental data by connecting to the power and environmental monitoring system through various protocols and related interfaces, the data acquisition module 110 can also directly connect to the power equipment and air conditioning terminal equipment in the computer room to collect air conditioning operation and environmental data. Furthermore, the data acquisition module 110 can collect air conditioning operation and environmental data through hardware sensors connected to IoT / 5G networks. For example, hardware sensors for the required data can be deployed in the actual physical space of the data center, forming a data monitoring network through IoT networking. Data can be uploaded to the management node via Ethernet, and data can be directly interacted with the management node through standard protocol interfaces to quickly and massively obtain information about the computer room environment and equipment for integration with subsequent modules. Real-time data sources can be integrated into the simulation system through IoT sensors and communication modules to achieve uninterrupted monitoring and processing. In particular, wireless remote monitoring and control functions can be added by building 4G and 5G modules into the device, directly connecting to a unified wireless transmission platform. The wireless transmission module uses wireless radio frequency technology to send the collected information to the server for storage and data analysis.

[0047] In one optional manner, the data acquisition module 110 is used to acquire air conditioning operation data and air conditioning environment data by: acquiring data through connection to a power and environment monitoring system; and / or acquiring data through connection to power equipment and air conditioning terminal equipment within the data center; and / or acquiring data through hardware sensors connected to an IoT / 5G network. The air conditioning operation data includes air conditioning terminal parameters, which include air supply air temperature, supply air humidity, return air temperature, return air humidity, and fan speed and power. The air conditioning environment data includes data center environment parameters; data center environment parameters include outside data center temperature, outside data center humidity, data center temperature, data center humidity, cold aisle temperature, cold aisle humidity, hot aisle temperature, and hot aisle humidity; rack parameters include rack front door temperature, rack front door humidity, rack rear door temperature, rack rear door humidity, rack outlet air velocity, rack power, power distribution cabinet power, and leakage detection parameters.

[0048] In this embodiment of the invention, the data acquisition module 110 supports multiple interface types, such as data source interfaces, proprietary functional module interfaces, third-party functional module interfaces, and third-party system interfaces. All interfaces supported by the data acquisition module 110 are standardized interfaces, meaning they are developed according to standardized protocol specifications. Supported standardized interfaces may include serial bus interfaces, TCP / IP protocol-socket interfaces, SNMP protocol interfaces, BACnet gateway interfaces, database interfaces, and OPC system gateways, etc. Each external interface includes alarm data interfaces and monitoring data interfaces. The interfaces of the data acquisition module 110, through their respective standardized protocol specification documents and version numbers, follow gateway development standards, enabling all data and information from the air conditioning system to be uploaded to the air conditioning operation and maintenance system of this embodiment of the invention via the corresponding interface protocols.

[0049] Figure 3 This diagram illustrates another structural schematic of the air conditioning operation and maintenance system for a wind-cooled data center provided in an embodiment of the present invention. (See diagram below.) Figure 3 As shown, the air conditioning operation and maintenance system 100 of the air-cooled data center includes a data acquisition module 110, an energy-saving module 120, a simulation module 130, a health diagnosis module 140, and an intelligent inspection module 150.

[0050] The data acquisition module 110 acquires data by proactively obtaining air conditioning operation data and environmental data from the centralized monitoring platform via a data source interface. The data format is specified by the centralized monitoring platform using a software-coded point table. The acquisition method is a polling-based event trigger, periodically sending the operating status or collected values ​​of certain devices to the centralized monitoring platform. Data request and return methods can be configured by the requester. Options include batch requesting all collection points, with each point identified by a unique measurement point ID, and returning all point information at once; or batch requesting a single device collection point, with a single device point information returned. During implementation, the interface provider provides the necessary IP address, port number, LSCID (LAN Screen Capture ID), username, and password. The intelligent operation and maintenance system provides interface testing tools to test the IP address, port number, LSCID, username, password, and corresponding database. Successful interface testing, indicating that point data can be sent, is achieved when the interface logs in and returns communication values. After successful integration, the interface provider imports the data points provided by the software coding point table into the platform's data acquisition module 110's own database for input and code testing. The monitoring system checks whether it sends query information to the interface. If successful, the monitoring platform checks whether it can obtain real-time data from the interface and whether the data table has been successfully inserted, indicating successful data feedback. After all data is collected, the collected data can be checked for missing points and errors. Required data is defined and standardized into a message format, stored in the platform's own database. The message format content can be defined according to actual needs. The scope and frequency of data collection can be set by the intelligent operation and maintenance system and the requester, thereby better realizing data interaction between air conditioning operation data and air conditioning environment data and the energy-saving module 120, simulation module 130, health diagnosis module 140, and intelligent inspection module 150.

[0051] In this embodiment, the proprietary functional module interface connects to the energy-saving module 120, simulation module 130, health diagnosis module 140, and intelligent inspection module 150. The data acquisition module 110 integrates with the above systems through its proprietary functional module interface. In this embodiment, the third-party functional module interface can be a core algorithm module interface, including but not limited to the energy-saving module 120, simulation module 130, and health diagnosis module 140. Algorithms and other functions are integrated and used by embedding them into the platform through the third-party functional module interface. In this embodiment, the third-party system interface can be a standardized interface for other applications, allowing the system data of this platform to be transmitted to other third-party platforms.

[0052] The energy-saving module 120 can establish an air conditioning system operation model based on the air conditioning operation data and air conditioning environment data collected by the data acquisition module 110. The data comes from the data collected from relevant equipment points on the centralized monitoring platform within one month, with no fewer than 1000 data entries per device. The data dimensions required are real-time data, rated parameters, and dimensionless parameters. The time granularity is consistent with the data transmission granularity of the centralized monitoring platform; the finer the granularity, the higher the model accuracy and matching degree. Furthermore, before establishing the air conditioning system operation model based on the data collected by the data acquisition module 110, the energy-saving module 120 can perform simple pre-processing on the data, including removing, completing, and cleaning missing, unreasonable, and white noise data. The processed data is then selected, and multiple air conditioning system operation models are established using artificial intelligence algorithms. These air conditioning system operation models include a white-box model, a gray-box model, and a fourth-paradigm compact data model. When establishing the white-box model, a detailed micro-element model of the air conditioning system can be built based on the air conditioning operation data and air conditioning environment data collected by the data acquisition module 110, according to the heat balance equation of the air conditioning heat exchanger. The detailed micro-element model of the air conditioning system includes heat transfer and power consumption models. Based on the detailed micro-element model of the air conditioning system, corresponding air conditioning operation optimization strategies are output, and optimization schemes for the equipment's own performance parameters (COP, Coefficient of Performance) are generated, including an evaporation cycle rule base, condensation temperature optimization strategies, high-efficiency operating points under partial load, and energy-saving suggestions for the transmission and distribution system. When establishing the gray-box model, machine learning can be performed based on the air conditioning operation data and air conditioning environment data collected by the data acquisition module 110. The relationship between the air conditioning system operation parameters is established through neural network algorithms, and the relationship between parameters such as outdoor meteorological environment parameters of the data center, IT equipment power, air conditioning equipment power, and total air conditioning energy consumption is established. Thus, a gray-box model is built, and corresponding air conditioning operation optimization strategies are output, generating optimization schemes between devices and between devices and the environment. This includes centralized management of the air conditioning cluster based on the backup / round-robin function, cascading function, and competition avoidance operation function of the air conditioning system, combined with an adaptive cluster power and energy consumption monitoring system. Finally, the working status of the air conditioners in the corresponding locations is controlled according to the load distribution and air conditioner distribution. The fourth paradigm compact data model is a given set of inputs and parameters that uses predefined internal states to generate output data. In this embodiment of the invention, the overall heat balance equation of the data center is adopted, that is, the balance between the heat load of the rack and the cooling capacity of the air conditioning, to establish the fourth paradigm compact data model, and output the corresponding air conditioning operation optimization strategy, generate an overall energy consumption optimization scheme for the data center, predict the overall air conditioning system energy consumption space and find the optimal solution.

[0053] Among these methods, multiple physical models are established using artificial intelligence algorithms to form an air conditioning system operation model. This model includes physical models of the air conditioning equipment and the computer room environment. The establishment of the air conditioning equipment physical model also innovatively proposes several methods and combinations. One method is a white-box model, which uses the collected air conditioning data and physical formulas to establish a detailed micro-element model of the air conditioning system based on the equipment's operating principle and the heat exchanger heat balance equation, including heat transfer and power consumption models. A second method is a gray-box model, which combines the collected computer room environment data and air conditioning data. Based on a large amount of historical operating data, machine learning methods, such as neural network algorithms, are used to establish the relationships between air conditioning system operating parameters. This involves establishing relationships between outdoor meteorological environmental parameters, IT equipment power, air conditioning equipment power, and total air conditioning energy consumption to build the air conditioning system operation model. A third method is a fourth-paradigm compact data model, which uses a predefined set of inputs and parameters to generate output data using predefined internal states. In this method, the overall heat balance equation of the computer room is used to balance the heat load of the server racks and the cooling capacity of the air conditioning system to establish the computer room system operation model. It should be noted that the air conditioning system operation model is a physical model, while the white-box model, gray-box model, and fourth paradigm model are algorithmic models. The physical model can be compared with reality, which in turn can correct the algorithmic model.

[0054] Figure 4 A schematic diagram of the model training process provided in an embodiment of the present invention is shown. Figure 4 As shown, in the process of establishing the air conditioning system operation model, an initial model can be established first through the data in the system database of the data acquisition module 110, then the model is trained and the model parameters are output; the model is corrected by the output model parameters and the verification data, and the training of the model is guided until the trained model meets the requirements.

[0055] Based on artificial neural network algorithms, deep learning, and mathematical modeling, the energy-saving module 120 can progressively optimize parameters involving adjustable data in the collected data to obtain the minimum energy consumption and corresponding optimal parameter values ​​of the air conditioning system operation model. This allows it to output configuration optimization schemes and energy-saving optimization strategies for air conditioning system operation parameters under different levels, regions, seasons, and load rate scenarios. The energy-saving module 120 has a training function. The air conditioning system operation model is validated using operating data from the database within three days, verifying that the deviation between the output parameters of the air conditioning system operation model and the actual operating parameters is within 5%. In actual operation, when the deviation between the measured power consumption and the model prediction exceeds 10%, model training and updating are triggered, with retraining occurring on average once a month. On average, optimization strategies are output twice a month during actual operation.

[0056] The simulation module 130 employs computer numerical simulation technology to simulate the operational status of the data center. It uses real-time operational data from equipment such as air conditioning and IT loads as input to the simulation software, which then outputs the simulation results of the data center in real time. Furthermore, based on the data acquired by the data acquisition module 110, the simulation module 130 can generate 3D point maps or visualized simulation results using methods such as fitting and fuzzy forests. In particular, the simulation module 130 can be combined with data acquired by hardware sensors based on IoT / 5G networks in the data acquisition module 110 to achieve continuous real-time dynamic twinning. This allows data center maintenance personnel to monitor the thermal and humidity environment and airflow organization of the data center in real time, providing real-time guidance for on-site operation and maintenance, and enabling early fault warnings.

[0057] The simulation module 130 simulates the operational status of the data center server room, including physical modeling, simulation modeling, and thermal and environmental assessment. First, using the actual server room as the object, a two-dimensional or three-dimensional model is created in the form of electronic drawings. The model dimensions are based on the actual area of ​​the server room, and the physical objects within the server room are labeled and located. The server room model also includes server room information, such as whether the server room has an underfloor or suspended ceiling, the height of the underfloor, cable tray layout, the location and quantity of lighting fixtures, beams, columns, etc. Server rack information includes dimensions (width, height, and depth), rack location, and the number of racks. Air conditioning information includes the type, location, and number of air conditioning units. Specifically, two-dimensional modeling can be done using software such as AutoCAD, while three-dimensional modeling can be done using software such as Solidworks. The software used needs to be data compatible, meeting internationally accepted format settings to satisfy the requirements for data interface, integration, access, and interaction with the platform. In particular, when using three-dimensional software, it is usually necessary to import the three-dimensional graphic format into a model segmentation platform, dividing the three-dimensional model into many small units as preprocessing for finite element analysis.

[0058] The air conditioning operation and maintenance system is integrated with the simulation modeling software platform. Simulation boundary conditions are set, including detailed parameters for the computer room (such as whether hot and cold aisles are enclosed, floor permeability), detailed parameters for the server racks (such as the number of servers, server power, server size, overall rack power consumption, rack air leakage, rack temperature limits, and required airflow for heat dissipation), and detailed parameters for the air conditioning system (such as air supply and return air configuration, power, cooling capacity, airflow, fan speed, design temperature control methods such as return or supply air temperature, design temperature limits, and sensor locations). All model information is acquired through the platform's own database, resulting in a complete mapping and representation of the computer room and air conditioning facilities. Simulation calculations and analysis are then performed. The simulation model is validated using real-time data collected from the platform's database of the computer room's ambient temperature and humidity.

[0059] When input conditions such as the power consumption of the computer room air conditioning equipment or server racks change and exceed the set threshold range, the real-time simulation is restarted, and the results are output. Secondly, model calibration is required to update the baseline model and ensure the accuracy of the simulation results. Multiple iterative calculations are performed based on the above formulas. Calculation monitoring points and residuals can be set to aid in judgment. The iteration ends when the system reaches the specified residual accuracy or iteration step count, causing the calculation results to converge. After the calculation is completed, the results are output, including the simulation results under the operating conditions at a certain moment, the thermal simulation results at that moment (i.e., the temperature field cloud map of any plane in the computer room), the environmental simulation results (i.e., the air conditioning airflow streamline diagrams (including supply and return airflow streamline diagrams), the utilization rate of each air conditioner, the air volume distribution diagram (airflow distribution diagram of the ventilation floor), the overheating status diagram of each cabinet, the heat load distribution diagram of the computer room, and various screenshots that can mark the location and data of the highest / lowest temperature and velocity values, the distribution of different key sections (horizontal or vertical direction), etc. It can effectively simulate the airflow organization, temperature field, velocity field, etc. of the computer room in real time and present them in an intuitive form such as data and pictures, thereby identifying high temperature points or unreasonable airflow organization in the computer room, providing effective basis for the construction and operation and maintenance of the computer room.

[0060] The calculation can also target and shut down a high-utilization air conditioner. This involves canceling the parameter and boundary condition inputs, resubmitting the calculation, and outputting the results. If the output is satisfactory, the user can skip directly to the optimization evaluation step. If the result is unsatisfactory, the user proceeds to the next step, optimization simulation. Based on the output, the user can optimize the solution. The optimization can adjust the operating boundary conditions, including detailed parameters for the computer room (closed hot and cold aisles, floor permeability), detailed parameters for the server racks (server layout, air leakage, temperature rise), and detailed parameters for the air conditioners (supply and return air type, power, cooling capacity, airflow, fan speed, temperature control method such as return or supply air temperature, temperature limits, sensor locations, etc.). The user resubmits the calculation and outputs the results. If satisfied, the user proceeds to the evaluation step; otherwise, the optimization simulation step is repeated until the output is satisfactory and conforms to actual operating parameters. Finally, an assessment of the computer room's thermal environment is conducted. Through thermal and environmental simulations, the environmental conditions of the computer room can be visually displayed. Based on the results, temperature field analysis, flow rate analysis, and load analysis can be performed to determine whether the capacity of the existing air conditioning equipment meets the overall cooling demand. If not, suggested solutions are provided, such as adjusting the operating parameters of the air conditioning equipment or reducing the load on process equipment to adapt to the actual cooling requirements. The temperature field distribution in the computer room is analyzed to determine if there are any localized hotspots. Velocity and vector field distributions are analyzed to determine the rationality of the airflow organization in the computer room. Finally, a design scheme analysis is performed to match the input boundary conditions corresponding to the results.

[0061] The health diagnosis module 140 is used to verify the design and optimize the control of the air conditioning equipment itself; analyze and evaluate the energy consumption of the transmission and distribution system; and output optimization suggestions for the overall monitoring system and equipment system of the computer room. Furthermore, the health diagnosis module 140 can first acquire data collected by the data acquisition module 110 through sensors and determine whether the data is normal.

[0062] Figure 5 This diagram illustrates the data assessment process of the health diagnosis module provided in an embodiment of the present invention. Figure 5As shown, the health diagnosis module 140 reads data from the system database in the data acquisition module 110. After data preprocessing, it first performs sensor FDD (Fault Detection and Diagnosis). If a sensor fault is detected, the sensor fault detection result is output. If a non-sensor fault is detected, the health algorithm model, i.e., the health rule base, is used for judgment. If the health rule base contains corresponding judgment rules, the judgment result is output according to the corresponding judgment rules. When judging according to the judgment rules, the constraint relationship condition formula can be composed of expert experience and relevant data center operation specifications to compare the standard value with the actual value. If no corresponding judgment rule exists, the fluctuation range of the preprocessed data compared with the historical data is used to determine whether there is similar historical data, and the judgment result is output.

[0063] In this embodiment, the health algorithm model uses the Drools tool in a Java project to configure the health model, i.e., the health rule base, as a triple file for algorithm execution and result output. The air conditioning system health rule base evaluates the overall data center server room and air conditioning system and outputs optimization suggestions. Specific evaluation methods include design verification of the air conditioning equipment itself and energy consumption analysis and evaluation of the distribution system; specific optimization suggestions may include group control system optimization suggestions, equipment control optimization suggestions, and server room airflow optimization suggestions, etc. In addition, the health diagnosis module 140 can also analyze equipment and server room faults, determine the causes of faults, and output fault solutions, thereby guiding the air conditioning operation and maintenance work of on-site personnel.

[0064] The intelligent inspection module 150 can collect environmental data of the data center server room through remote video, VR / AR technology, and intelligent robots. It also supplements the data collected by the data acquisition module 110, calibrating and alerting users to abnormal data. The intelligent inspection module 150 can not only collect data on the server room environment, including temperature, humidity, and airflow speed of the equipment, but also remotely transmit server room images via VR / AR technology. Specifically, the platform system uses a web browser front-end remotely, while the data center site uses mobile glasses for transmission. Data transmission is divided into two parts: first, system data interaction where the glasses identify on-site equipment and access backend equipment data; second, real-time audio and video communication data interaction between the expert and the site. The terminal glasses data source is deployed on the same dedicated server as the platform. Real-time audio and video communication is achieved via WebRTC. The module has call and received functions; after connection, the platform software (expert side) can display the real-time audio and video images transmitted from the glasses (the interface seen by the glasses wearer). The audio and video images on the platform software can also be transmitted to the glasses wearer in real time. Manual annotations on both sides can be displayed in real time, enabling real-time transmission of text, documents, and images. This provides a more accurate and efficient visual service for on-site data center maintenance personnel and remote technical experts.

[0065] The data acquisition module 110 is deployed at the physical layer, sending the acquired data to the data layer for processing. The energy-saving module 120, simulation module 130, health diagnosis module 140, and intelligent inspection module 150 are deployed at the business layer, calling the processed data generated by the data layer and generating processing results for display at the application layer. Furthermore, the data acquisition module 110 can be located in various data centers, while the energy-saving module 120, simulation module 130, health diagnosis module 140, and intelligent inspection module 150 can be located in the cloud. The data acquisition module 110 interacts with these modules via IoT / 5G networks. The air conditioning operation and maintenance system 100 for the air-cooled data center can also include a visualization module, which can display 2D or 3D views of the data center's air conditioning system, showing the system's operation diagram and air conditioning equipment parameter diagrams. Furthermore, the visualization module can also display the processing results of the energy-saving module 120, simulation module 130, health diagnosis module 140, and intelligent inspection module 150.

[0066] The air conditioning operation and maintenance system for an air-cooled data center according to this invention includes a data acquisition module and an energy-saving module. The data acquisition module is used to collect air conditioning operation data and air conditioning environment data. The energy-saving module is used to establish an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, the module outputs air conditioning operation energy-saving strategies corresponding to the white-box model, gray-box model, and fourth-paradigm compact data model, respectively. It can be seen that this invention can perform data analysis on air conditioning operation data and air conditioning environment data for an air-cooled data center's air conditioning operation and maintenance system, thereby proposing air conditioning operation energy-saving strategies and reducing air conditioning energy consumption.

[0067] Figure 6 This diagram illustrates a flow chart of an air conditioning operation and maintenance method for an air-cooled data center according to an embodiment of the present invention. The method is applied to an air conditioning operation and maintenance system for an air-cooled data center, and the system includes a data acquisition module and an energy-saving module. Figure 6 As shown, the method includes:

[0068] Step 301: The data acquisition module collects air conditioner operation data and air conditioner environment data.

[0069] The data acquisition module can collect air conditioning operation data and air conditioning environment data in the data center. This module uses sensors installed in the data center to collect these data and transmits it to the cloud via IoT / 5G networks.

[0070] Step 302: The energy-saving module establishes an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, the module outputs the air conditioning operation optimization strategies corresponding to the white-box model, the gray-box model, and the fourth-paradigm compact data model, respectively.

[0071] Among them, the energy-saving module can output corresponding air conditioning operation optimization strategies according to the characteristics of different models by establishing white box model, gray box model and fourth paradigm compact data model, so as to make the air conditioning system of the data center safer and more energy-efficient.

[0072] The air conditioning operation and maintenance system for an air-cooled data center according to this invention includes a data acquisition module and an energy-saving module. The data acquisition module is used to collect air conditioning operation data and air conditioning environment data. The energy-saving module is used to establish an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, the module outputs air conditioning operation energy-saving strategies corresponding to the white-box model, gray-box model, and fourth-paradigm compact data model, respectively. It can be seen that this invention can perform data analysis on air conditioning operation data and air conditioning environment data for an air-cooled data center's air conditioning operation and maintenance system, thereby proposing air conditioning operation energy-saving strategies and reducing air conditioning energy consumption.

[0073] Figure 7 The diagram shows a schematic of the electronic device structure according to an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the electronic device.

[0074] like Figure 7 As shown, the electronic device may include: a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0075] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. Communication interface 404 is used to communicate with other network elements such as clients or other servers. The processor 402 executes program 410, specifically performing the relevant steps in the above-described embodiment of the air conditioning operation and maintenance method for air-cooled data centers.

[0076] Specifically, program 410 may include program code, which includes computer-executable instructions.

[0077] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0078] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0079] Specifically, program 410 can be called by processor 402 to cause the electronic device to perform the following operations:

[0080] Collect air conditioning operation data and air conditioning environment data;

[0081] An air conditioning system operation model is established, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, the air conditioning operation optimization strategies corresponding to the white-box model, the gray-box model, and the fourth-paradigm compact data model are output respectively.

[0082] The air conditioning operation and maintenance system for an air-cooled data center according to this invention includes a data acquisition module and an energy-saving module. The data acquisition module is used to collect air conditioning operation data and air conditioning environment data. The energy-saving module is used to establish an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and air conditioning environment data, the module outputs air conditioning operation energy-saving strategies corresponding to the white-box model, gray-box model, and fourth-paradigm compact data model, respectively. It can be seen that this invention can perform data analysis on air conditioning operation data and air conditioning environment data for an air-cooled data center's air conditioning operation and maintenance system, thereby proposing air conditioning operation energy-saving strategies and reducing air conditioning energy consumption.

[0083] This invention provides a computer-readable storage medium storing at least one executable instruction that, when executed on an electronic device, causes the electronic device to perform the air conditioning operation and maintenance method for an air-cooled data center as described in any of the above method embodiments.

[0084] This invention provides an air conditioning operation and maintenance device for an air-cooled data center, used to execute the aforementioned air conditioning operation and maintenance method for an air-cooled data center.

[0085] This invention provides a computer program that can be called by a processor to enable an electronic device to execute the air conditioning operation and maintenance method for an air-cooled data center as described in any of the above method embodiments.

[0086] This invention provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, which, when executed on a computer, cause the computer to perform the air conditioning operation and maintenance method for an air-cooled data center as described in any of the above method embodiments.

[0087] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0088] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0089] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim.

[0090] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0091] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. An air conditioning operation and maintenance system for an air-cooled data center, characterized in that, The system includes: a data acquisition module and an energy-saving module; The data acquisition module is used to collect air conditioning operation data and air conditioning environment data; The energy-saving module is used to establish an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and the air conditioning environment data, it outputs air conditioning operation energy-saving strategies corresponding to the white-box model, the gray-box model, and the fourth-paradigm compact data model, respectively. The air conditioning operation energy-saving strategy corresponding to the white-box model includes an air conditioning operation parameter optimization strategy, which includes an evaporation cycle rule base, a condensing temperature optimization strategy, a partial load high-efficiency operating point, and energy-saving suggestions for the transmission and distribution system. The air conditioning operation energy-saving strategy corresponding to the gray-box model is used to achieve optimal control logic between devices and between devices and the environment, and to control the working status of air conditioners at corresponding locations based on load distribution and air conditioner distribution. The air conditioning operation energy-saving strategy corresponding to the fourth-paradigm compact data model includes overall energy consumption optimization spatial analysis and real-time monitoring of the data center, predicting and optimizing the air conditioning system energy consumption.

2. The system according to claim 1, characterized in that, The data acquisition module is used to collect the air conditioner operation data and air conditioner environment data in the following ways: Data is collected by connecting to a power and environmental monitoring system; and / or, Data is collected by connecting to the power equipment and air conditioning terminal equipment within the data center; and / or, Data is collected through hardware sensors connected to IoT / 5G networks.

3. The system according to claim 1 or 2, characterized in that, The air conditioning operation data includes air conditioning terminal parameters, which include air supply air temperature, supply air humidity, return air temperature, return air humidity, and fan speed and power. The air conditioning environment data includes data center environment parameters and rack parameters. The data center environment parameters include outside temperature, outside humidity, data center temperature, data center humidity, cold aisle temperature, cold aisle humidity, hot aisle temperature, and hot aisle humidity. The rack parameters include front door temperature, front door humidity, rear door temperature, rear door humidity, rack exhaust air velocity, rack power, power distribution cabinet power, and leakage detection parameters.

4. The system according to claim 1, characterized in that, The system also includes a health diagnosis module, which is used for: Perform design verification and control optimization for the air conditioning equipment itself; analyze and evaluate the energy consumption of the power distribution system; provide optimization suggestions for the overall monitoring system and equipment system of the computer room; analyze and judge the causes of equipment and computer room abnormalities and failures and provide solutions to the failures.

5. The system according to claim 4, characterized in that, The system also includes an intelligent inspection module, which is used for: Environmental data of the data center is collected through remote video, VR / AR technology and intelligent robots, and abnormal data is identified and alerted.

6. The system according to claim 5, characterized in that, The air conditioning operation and maintenance system also includes a visualization module deployed at the application layer; The data acquisition module is deployed at the physical layer, while the energy-saving module, the health diagnosis module, and the intelligent inspection module are deployed at the business layer.

7. A method for the operation and maintenance of air conditioning in an air-cooled data center, characterized in that, An air conditioning operation and maintenance system for air-cooled data centers, the system comprising a data acquisition module and an energy-saving module, the method comprising: The data acquisition module collects air conditioner operation data and air conditioner environment data; The energy-saving module establishes an air conditioning system operation model, which includes a white-box model, a gray-box model, and a fourth-paradigm compact data model. Based on the air conditioning operation data and the air conditioning environment data, it outputs air conditioning operation energy-saving strategies corresponding to the white-box model, the gray-box model, and the fourth-paradigm compact data model, respectively. The air conditioning operation energy-saving strategy corresponding to the white-box model includes an air conditioning operation parameter optimization strategy, which includes an evaporation cycle rule base, a condensing temperature optimization strategy, a high-efficiency operating point for partial load, and energy-saving suggestions for the transmission and distribution system. The air conditioning operation energy-saving strategy corresponding to the gray-box model is used to achieve optimal control logic between devices and between devices and the environment, and to control the working status of air conditioners at corresponding locations based on load distribution and air conditioner distribution. The air conditioning operation energy-saving strategy corresponding to the fourth-paradigm compact data model includes overall energy consumption optimization spatial analysis and real-time monitoring of the data center, predicting and optimizing the air conditioning system energy consumption.

8. An electronic device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation of the air conditioning operation and maintenance method for an air-cooled data center as described in claim 7.

9. A computer-readable storage medium, characterized in that, The storage medium stores at least one executable instruction, which, when executed on an electronic device, causes the electronic device to perform the operation of the air conditioning operation and maintenance method for an air-cooled data center as described in claim 7.

Images