Energy-saving optimization method and system for data center machine room based on virtual energy storage

Abstract

The invention discloses an energy-saving optimization method and system for a data center machine room based on virtual energy storage, and belongs to the technical field of heating and ventilation systems. The RC model is adopted for modeling and used for predicting the temperature change rate and degree of the machine room at different set temperatures, and therefore operation of the air conditioning system is more accurately controlled. An energy-saving optimization method based on virtual energy storage is achieved through rolling time domain optimization, the future thermal environment temperature is predicted through an air conditioner-building RC model within the future finite time range, and constraints are added to guarantee the reliability of IT equipment. And the system is optimized, the optimal set temperature of the air conditioning system in a period of time in the future is determined, and the solved optimal set value at the next moment serves as the reference of the actual optimal set temperature. And continuously performing optimization in a limited time range in the future at the next moment, and continuously rolling forwards so as to achieve the purposes of real-time optimization and temperature reference giving.

Description

Technical Field

[0001] The present invention belongs to the technical field of HVAC systems, and in particular relates to an energy-saving optimization method and system for a data center computer room based on virtual energy storage. Background Art

[0002] Virtual energy storage is a modeling method that equates the air conditioning-building system to a virtual energy storage device. The air conditioning-building system is similar to a traditional energy storage device and has the ability to store heat. With the help of the virtual energy storage concept, the air conditioning-building environment is equivalent to an energy storage device and integrated into the scheduling strategy. For the computer room, it can maintain the thermal environment required for the reliable operation of the equipment. For operators, they can use the energy storage characteristics of the air conditioning-building environment to adjust the operating conditions of the air conditioning equipment according to the peak and valley electricity prices, thereby reducing energy consumption and saving costs.

[0003] Rolling horizon optimization is a dynamic optimization technology. For a dynamically changing and uncertain system, rolling horizon optimization technology only solves an optimization problem with a limited time range in each decision step. It is an optimization algorithm with advantages such as real-time performance. As time goes by, this optimization process will continue to roll forward, that is, a limited number of steps will be optimized again at the next decision moment.

[0004] Data centers are the computing infrastructure for the digital transformation of various industries, and the number of data centers is increasing. Currently, data centers are facing the problem of high energy consumption. For air-cooled data centers, the energy consumption of the HVAC system accounts for about 40%. The airflow management at the air-cooled end of the data center is relatively complex. At the same time, a large number of data centers currently use rule-based control methods to fix the set temperature and air volume of air-conditioning equipment. It is impossible to predict the rate and degree of temperature change in the computer room at different set temperatures in real time, resulting in low accuracy. Therefore, there is a large room for optimization of HVAC system air-conditioning equipment. Summary of the invention

[0005] The purpose of the present invention is to overcome the problem that the existing data center adopts a rule-based control method, which is unable to predict in real time the rate and degree of temperature change in the computer room under different set temperatures, resulting in low accuracy and high energy consumption, and to provide an energy-saving optimization method and system for a data center computer room based on virtual energy storage.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A method for energy saving optimization of a data center computer room based on virtual energy storage comprises the following steps: Obtain and monitor the environmental data and equipment operation status data of the data center room; Store and analyze acquired environmental data and equipment operating status data; Building an air-conditioning-building RC model based on the environmental data and the equipment operation status data, and iteratively predicting the thermal environment of the computer room in a limited time in the future through the air-conditioning-building RC model to obtain a thermal environment prediction value; Modeling the energy consumption of the HVAC equipment in the data center computer room, and calculating the energy consumption of each air conditioner at each moment based on the energy consumption model; Based on the predicted value of the thermal environment and the energy consumption value of the air conditioner, the recommended value of the air conditioner operating condition at the next moment is obtained through the rolling optimization algorithm; Control the air conditioner to operate according to the recommended values ​​of the working conditions.

[0007] The air conditioning-building RC model constructed based on the environmental data and the equipment operation status data includes a cold channel RC model and a hot channel RC model.

[0008] The formula of the cold channel RC model is: ; in, is the area of ​​the cold channel physical barrier, in units of ; For the The rack is in the Exhaust volume at a moment, in units of ; For the The air volume of the air conditioner, in ; For the The IT equipment power at a moment in time, in ; For the The rack exhaust temperature at a given moment, in ; For the The outlet temperature of the air conditioner, in ; is the constant pressure specific heat capacity of air, in ; is the convective heat transfer coefficient of the cold channel physical barrier, in units of ; is the air quality of the cold channel, in ; For the The cold channel temperature at the moment, in ; For the +1 cold channel temperature at a certain moment, in ; For the The hot channel temperature at the moment, in ; is the length of one time step in hours.

[0009] The formula of the hot channel RC model is: ; in, is the area of ​​the computer room wall, in units of ; For the The air conditioner is in The return air temperature at a certain moment, in ; is the air quality of the hot aisle, in ; is the convection heat transfer coefficient of the wall, in units of ; For the The hot channel temperature at the moment, in ; is the temperature of the external environment, in units of .

[0010] The formula of the energy consumption model is as follows: ; in, For the The air conditioner is in of the moment

[0011] No. Air conditioning in the The energy consumption at each moment is:

[0012] in, Indicates the air density.

[0013] Based on the predicted value of the thermal environment and the energy consumption value of the air conditioner, the recommended value of the air conditioner operating condition at the next moment is obtained through the rolling optimization algorithm. The specific method is as follows: Set the time granularity v and get the current time t; Determine whether the current time t has reached the preset decision moment. If not, enter the optimization function Sleep(1); Once the decision-making moment is reached, the basic information of the data center room, weather information and local electricity price information are used as the basic input of the optimization algorithm; The scheduling cycle is discretized in time into The state of the next time stage in the model is determined by the state of the current time stage; Obtain temperature information of the data center room in real time and input it into the time domain rolling optimization algorithm as real-time feedback; According to the current electricity price information, thermal environment forecast value and air conditioning energy consumption value, the recommended value of air conditioning operating conditions at the next moment is calculated.

[0014] The processing strategy of the rolling optimization algorithm is as follows: Increase the output of air conditioning equipment when electricity prices are low, and store cooling energy in the air conditioning-building system; When electricity prices are high, the cold stored in the air-conditioning-building system is used to cool the heat generated by the equipment in the computer room, and the output power of the air-conditioning equipment is reduced.

[0015] The thermal environment temperature constraints are as follows:

[0016] in, are the lower and upper temperature limits respectively.

[0017] An energy-saving optimization system for a data center computer room based on virtual energy storage, comprising: Data collection and monitoring module, used to obtain and monitor the environmental data and equipment operation status data of the data center room; Data storage and analysis module: used to store and analyze acquired environmental data and equipment operation status data; An air-conditioning-building RC model building module is used to build an air-conditioning-building RC model based on the environmental data and the equipment operation status data, and iteratively predict the thermal environment of the computer room in a limited time in the future through the air-conditioning-building RC model to obtain a thermal environment prediction value; An energy consumption model building module is used to model the energy consumption of the HVAC equipment in the data center computer room and calculate the energy consumption of each air conditioner at each moment based on the energy consumption model; The optimization algorithm module is used to obtain the recommended value of the air conditioner operating condition at the next moment through a rolling optimization algorithm based on the thermal environment prediction value and the air conditioner energy consumption value; The control execution module is used to control the air conditioner to operate according to the recommended working conditions.

[0018] The control execution module includes the Modbus protocol, which is used to ensure the accuracy and reliability of the control operation.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides an energy-saving optimization method and system for a data center computer room based on virtual energy storage, comprising the following steps: acquiring and monitoring environmental data and equipment operating status data of a data center computer room; storing and analyzing the acquired environmental data and equipment operating status data; building an air-conditioning-building RC model based on the environmental data and equipment operating status data, iteratively predicting the thermal environment of the computer room in a limited future time through the air-conditioning-building RC model, and obtaining a thermal environment prediction value; energy consumption modeling of the HVAC equipment in the data center computer room, and calculating the energy consumption of each air conditioner at each moment based on the energy consumption model; based on the thermal environment prediction value and the energy consumption value of the air conditioner, a rolling optimization algorithm is used to obtain the recommended operating condition value of the air conditioner at the next moment; and the air conditioner is controlled to operate according to the recommended operating condition value. The RC model is used for modeling to predict the rate and degree of temperature change of the computer room at different set temperatures, so as to more accurately control the operation of the air conditioning system. The energy-saving optimization method based on virtual energy storage is implemented by rolling time domain optimization, and the future thermal environment temperature is predicted by the air-conditioning-building RC model within a limited future time range. Optimize the system to determine the optimal set temperature of the air conditioning system in the future, and use the optimal set value at the next moment as a reference for the actual optimal set temperature. Continue to optimize the future limited time range at the next moment, and keep rolling forward to achieve real-time optimization and provide temperature reference.

[0020] Furthermore, constraints are added to the thermal environment temperature to ensure the reliability of IT equipment.

[0021] Furthermore, by utilizing the peak-valley electricity price mechanism, the air conditioner set temperature can be lowered and the cold energy can be stored during periods of low electricity prices. During periods of high electricity prices, the cold energy stored in the environment can be used to appropriately increase the air conditioner set temperature. The thermal inertia of the data center air conditioning-building system can be used to store and release energy, thereby reducing the energy consumption of the data center computer room. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram of a data center room that uses row-level air conditioning.

[0023] Figure 2 It is a flow chart of the present invention.

[0024] Figure 3 A working diagram of a data center energy-saving optimization method based on virtual energy storage.

[0025] Figure 4 It is the program running process of the time domain rolling optimization algorithm.

[0026] Figure 5 This is a schematic diagram of the data center room energy-saving optimization platform's hardware and software systems. DETAILED DESCRIPTION

[0027] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0028] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] Embodiment 1: like Figure 1 As shown, the application background of the present invention is the xxx data center in xx city. The data center adopts the cooling method of row-level air conditioners, and the air conditioning equipment is placed near the IT equipment, which can significantly shorten the airflow path and is a relatively efficient air cooling solution. The cooling system of the data center includes air conditioning equipment in the computer room and outdoor units on the roof, including a fluorine pump module to use a natural cold source. For the interior of the computer room, in order to optimize the airflow organization and further improve the cooling efficiency, the data center adopts a closed cold channel design. In the data center, cold air is supplied from the cold channel and hot air is discharged from the hot channel. The data center isolates the cold channel from the outside world through a physical barrier to prevent the mixing of cold and hot air, thereby improving the cooling efficiency. During the normal operation of the cooling system of the data center, the row-level air conditioners supply cold air to the cold channel. After the cold air cools the IT equipment placed in the rack, the temperature rises and enters the hot channel. The air conditioning equipment cools the air in the hot channel and sends it into the cold channel.

[0030] In order to optimize the energy consumption of the cooling system, the present invention has built a data center computer room optimization software and hardware platform to monitor the computer room environment information, collect operation data, and give the optimal decision for the operation of HVAC equipment. The platform reads the data center environment information and operation status through sensors, summarizes the information, and gives the optimal value of the air conditioning setting temperature at the next moment through a rolling time domain optimization algorithm.

[0031] like Figure 2~3 As shown, the present invention proposes an energy-saving optimization algorithm for a data center computer room based on virtual energy storage and rolling time domain optimization. At the current moment, the parameters required for the operation of the algorithm are obtained through the software and hardware platform of the data center computer room. Subsequently, the RC model of the air-conditioning-building system is used to iteratively predict the thermal environment of the computer room for a limited time in the future. After obtaining the predicted value, the air-conditioning-building energy storage characteristics and peak-valley electricity prices are used to schedule the air-conditioning decision for a period of time in the future, and the optimal value of the air-conditioning operating condition at the next moment is obtained.

[0032] A method for energy saving optimization of a data center computer room based on virtual energy storage comprises the following steps: S1: Obtain environmental data and equipment operation status data of the data center room; S2: Store and analyze the acquired environmental data and equipment operation status data; S3: Building an air-conditioning-building RC model based on the environmental data and the equipment operation status data, and iteratively predicting the thermal environment of the computer room in a limited time in the future through the air-conditioning-building RC model to obtain a thermal environment prediction value; S4: Perform energy consumption modeling on the HVAC equipment in the data center computer room, and calculate the energy consumption of each air conditioner at each moment based on the energy consumption model; S5: Based on the predicted value of the thermal environment and the energy consumption value of the air conditioner, the recommended value of the air conditioner operating condition at the next moment is obtained through the rolling optimization algorithm; S6: Control the air conditioner to operate according to the recommended values ​​of the working conditions.

[0033] Specifically, in S1, environmental data and equipment operation status data include weather data, computer room cold channel temperature, cold channel humidity, hot channel temperature, air conditioning supply and return air temperature and other key indicators. The data can be collected through various sensors (such as temperature sensors, humidity sensors, flow sensors, etc.) and monitoring equipment (such as computer room management system, air conditioning control system, etc.).

[0034] Specifically, in S2, the acquired environmental data is stored in a SQL / NoSQL database and processed, including data cleaning (removing outliers, filling missing values, etc.) and data conversion (such as converting raw data into a format that is easier to analyze) to better understand the characteristics and trends of the data. Historical data analysis is also performed to generate charts and reports to help users gain a deeper understanding of the system's operating conditions and energy-saving effects.

[0035] Specifically, in S3, in the field of architecture, the RC model (Resistance-Capacitance Model) is a tool for simulating the thermal performance of building envelope structures. It uses resistor (R) and capacitor (C) components to describe the resistance and storage capacity of building structures to heat flow by analogy with the electrical transfer process in a circuit. In fact, heat transfer is very similar to electrical conduction. The modeling process of heat transfer can be analogized to the law of electrical conduction. In heat transfer, the relationship between heat transfer and temperature difference between objects can be analogized to the form of current = potential difference / resistance in Ohm's law, and the calculation formula for heat flux is obtained:

[0036] in, is the heat flux in ; is the temperature difference of the heat transfer process, in °C; is the thermal resistance, in units of .

[0037] It can be seen from the above formula that in the heat transfer process, the heat flux is equivalent to the current, the temperature difference is equivalent to the potential difference; the thermal resistance of the heat transfer object is equivalent to the resistance. In the building system considered by the present invention, the thermal resistance of the wall can be calculated by known physical parameters:

[0038] in, is the convection heat transfer coefficient of the inner surface of the enclosure structure, in units of ; is the convection heat transfer coefficient of the outer surface of the enclosure structure; the unit is ; For the The thickness of the wall, in units of ; For the Thermal conductivity of the wall, in units of ; is the wall heat transfer coefficient, which refers to the heat that can be transferred per unit temperature difference between hot and cold fluids per unit time and area, and is expressed in units of .

[0039]

[0040]

[0041] Where C is the heat capacity of the enclosure structure, in units of ; is the specific heat of the wall in ; is the density of the wall material in ; is the wall thickness in .

[0042] In practical applications, combining the needs of different building environments to build a suitable RC thermal network model is of great help for real-time optimization. The RC model can build a relatively simple, easy-to-calculate, and less time-consuming mathematical model. It does not require high computer configuration and has good calculation accuracy. It is a commonly used method for studying heat transfer of building envelopes.

[0043] The following steps should be considered when establishing an RC model: (1) Establish a simplified physical model that fully considers factors such as heat transfer from the outside through the wall, heat storage in the building envelope, and heat balance of indoor air; (2) Apply parameter identification to optimize model parameters. For known maintenance structure parameters, they can be directly determined based on actual conditions. For unknown parameters, node equations are established based on the thermal balance relationship. Parameter identification is performed by measuring actual data to improve the accuracy of the model; (3) Model verification and promotion. After obtaining a more accurate RC model, load forecasting is performed to verify the effectiveness of the model.

[0044] In step (1), the existing RC model mainly includes a 3R2C wall model, a 3R2C roof model and a 2R2C indoor thermal storage model. The commonly used RC model for air conditioning-building systems is the first-order equivalent thermal parameter model:

[0045] in, is the equivalent heat capacity of the air conditioning-building system, in ; For the moment The cooling capacity of the air conditioner, in ; is the equivalent thermal resistance of the air conditioning-building system, in ; For the moment Indoor temperature in ; For the moment The outdoor temperature unit is ; With reference to the common building thermal environment modeling methods in academia and industry, the thermal environment of the data center to which the present invention is applied is modeled, laying the foundation for the thermal environment prediction part of the rolling time domain optimization. Since the data center adopts the design scheme of cold channel closure, it is necessary to apply RC models to model the cold channel and hot channel respectively. Figure 1 shown.

[0046] The RC model of the cold channel in the data center room is as follows:

[0047] in, is the area of ​​the cold channel physical barrier, in units of ; For the The rack is in the Exhaust volume at a moment, in units of ; For the The air volume of the air conditioner, in ; For the The IT equipment power at a moment in time, in ; For the The rack exhaust temperature at a given moment, in ; For the The outlet temperature of the air conditioner, in ; is the constant pressure specific heat capacity of air, in ; is the convective heat transfer coefficient of the cold channel physical barrier, in units of ; is the air quality of the cold channel, in ; For the The cold channel temperature at the moment, in ; For the +1 cold channel temperature at a certain moment, in ; For the The hot channel temperature at the moment, in ; is the length of one time step in hours.

[0048] Similarly, the RC model of the hot channel is as follows:

[0049] in, is the area of ​​the computer room wall, in units of ; For the The air conditioner is in The return air temperature at a certain moment, in ; is the air quality of the hot aisle, in ; is the convection heat transfer coefficient of the wall, in units of ; For the The hot channel temperature at the moment, in ; is the temperature of the external environment, in units of ; In step (2), the data collected by the software and hardware platform is used as input, and the RC model of the hot channel and the cold channel is iterated to obtain the predicted value of the thermal environment for a period of time in the future as a constraint condition. On this basis, it is necessary to ensure that the IT equipment in the computer room operates within a safe temperature range. Considering the difficulty of monitoring the operating temperature of IT equipment, the present invention refers to the "Thermal Guidelines for Data Processing Environment" of the ASHRAE organization. This manual gives the requirements for the thermal environment when IT equipment is running in a high reliability state. According to the operating environment requirements given in the manual, the thermal environment temperature constraints for a period of time in the future are added as follows:

[0050] in, They are the lower and upper temperature limits recommended by ASHRAE.

[0051] Modeling the thermal environment can effectively help data center rooms optimize energy conservation.

[0052] Specifically, in S4, the present invention realizes energy-saving optimization of the data center computer room through virtual energy storage and peak-valley electricity prices, and it is necessary to model the energy consumption of HVAC equipment. To simplify the calculation, an empirical formula is used to establish the relationship between air conditioning COP and supply air temperature:

[0053] in, For the The air conditioner is in of the moment

[0054] Further, Air conditioning in the The energy consumption at each moment is: ; in, Indicates the air density.

[0055] Specifically, in S5, according to the above modeling content, the present invention develops Figure 4 The closed-loop optimization solution based on time domain rolling optimization shown in the figure fully considers the uncertainty of data center room operation and the randomness of outdoor weather and solar radiation, and updates the optimal strategy based on real-time measurement data. The specific method is as follows: Set the time granularity v and get the current time t; Determine whether the current time t has reached the preset decision moment. If not, enter the optimization function Sleep(1), that is, pause for a period of time (such as 1 second), and then check again whether the decision moment has been reached; Once the decision-making moment is reached, the basic information of the data center room, weather information and local electricity price information are used as the basic input of the optimization algorithm; based on this, the scheduling cycle is discretized in time into The state of the next time stage in the model is determined by the state of the current time stage; The sensor network deployed in the computer room obtains the temperature information of important nodes in real time and inputs it into the time domain rolling optimization algorithm as real-time feedback; An optimization problem is established and solved. According to the current electricity price information, thermal environment forecast value and air conditioning energy consumption value, the recommended value of the air conditioning operating condition at the next moment is calculated, thereby realizing online strategy update based on time domain rolling optimization.

[0056] Through the prediction of peak and valley electricity prices in the future and the thermal environment based on the RC model of the building system, a rolling optimization algorithm is designed to obtain the recommended value of the air conditioning operating condition at the next moment. Specifically, in order to save electricity prices, the algorithm can increase the output power of air conditioning equipment when electricity prices are low and store the cold energy in the air conditioning-building system; when electricity prices are high, the cold energy stored in the air conditioning-building system can be used to cool part of the heat generated by IT equipment. At this time, the output power of the air conditioning system can be appropriately reduced, thereby achieving the purpose of saving operating costs. Since the future thermal environment is predicted and thermal environment constraints are added to ensure the reliability of IT equipment, the air conditioning equipment can adjust the operating power in real time according to the rolling optimization algorithm to save operating costs.

[0057] Embodiment 2: like Figure 5 As shown, an energy-saving optimization system for a data center computer room based on virtual energy storage includes: Data collection and monitoring module, used to obtain and monitor the environmental data and equipment operation status data of the data center room; Data storage and analysis module: used to store and analyze acquired environmental data and equipment operation status data; An air-conditioning-building RC model building module is used to build an air-conditioning-building RC model based on the environmental data and the equipment operation status data, and iteratively predict the thermal environment of the computer room in a limited time in the future through the air-conditioning-building RC model to obtain a thermal environment prediction value; An energy consumption model building module is used to model the energy consumption of the HVAC equipment in the data center computer room and calculate the energy consumption of each air conditioner at each moment based on the energy consumption model; The optimization algorithm module is used to obtain the recommended value of the air conditioner operating condition at the next moment through a rolling optimization algorithm based on the thermal environment prediction value and the air conditioner energy consumption value; The control execution module is used to control the air conditioner to operate according to the recommended working conditions.

[0058] The bottom layer of the software and hardware platform is the data acquisition and monitoring module. The system first obtains environmental data in real time through the data acquisition and monitoring module, including key indicators such as temperature, humidity, and energy consumption, to ensure the timeliness and accuracy of the data. These real-time data are not only used for display, but also transmitted to the data storage and analysis module through a standardized data interface. This module is responsible for storing the data in the SQL / NoSQL database, performing historical data analysis, generating charts and reports, and helping users to gain an in-depth understanding of the system's operating conditions and energy-saving effects. Based on data analysis, the optimization algorithm module makes real-time decisions based on real-time and historical data, and uses fine or rough energy-saving optimization algorithms to generate the optimal air-conditioning operation strategy. These strategies are converted into specific control instructions through the control execution module. The module supports manual control by users and defines control protocols such as Modbus to ensure the accuracy and reliability of control operations. Finally, all these operations and status records are displayed to users through the user interface. The user interface provides an intuitive and easy-to-use interactive platform where users can view real-time data, historical data charts and reports, and perform necessary operations and feedback.

[0059] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more servers that can be integrated with the medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0060] Finally, it should be noted that: although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art can understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit can implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0061] Although the present invention has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present invention. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present invention as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present invention. Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations if they fall within the scope of the claims of the present invention and their equivalents.

Claims

1. An energy-saving optimization method for a data center computer room based on virtual energy storage, characterized in that: The steps include: Obtain and monitor the environmental data and equipment operation status data of the data center room; Store and analyze acquired environmental data and equipment operating status data; Building an air-conditioning-building RC model based on the environmental data and the equipment operation status data, and iteratively predicting the thermal environment of the computer room in a limited time in the future through the air-conditioning-building RC model to obtain a thermal environment prediction value; Modeling the energy consumption of the HVAC equipment in the data center computer room, and calculating the energy consumption of each air conditioner at each moment based on the energy consumption model; Based on the predicted value of the thermal environment and the energy consumption value of the air conditioner, the recommended value of the air conditioner operating condition at the next moment is obtained through the rolling optimization algorithm; Control the air conditioner to operate according to the recommended values ​​of the working conditions.

2. The energy-saving optimization method for a data center computer room based on virtual energy storage according to claim 1 is characterized in that: The air conditioning-building RC model constructed based on the environmental data and the equipment operation status data includes a cold channel RC model and a hot channel RC model.

3. The energy-saving optimization method for a data center computer room based on virtual energy storage according to claim 2 is characterized in that: The formula of the cold channel RC model is: ； in, is the area of ​​the cold channel physical barrier, in units of ; For the The rack is in the Exhaust volume at a moment, in units of ; For the The air volume of the air conditioner, in ; For the The IT equipment power at a moment in time, in ; For the The rack exhaust temperature at a given moment, in ; For the The outlet temperature of the air conditioner, in ; is the constant pressure specific heat capacity of air, in ; is the convective heat transfer coefficient of the cold channel physical barrier, in units of ; is the air quality of the cold channel, in ; For the The cold channel temperature at the moment, in ; For the +1 cold channel temperature at a certain moment, in ; For the The hot channel temperature at the moment, in ; is the length of one time step in hours.

4. The energy-saving optimization method for a data center computer room based on virtual energy storage according to claim 3 is characterized in that: The formula of the hot channel RC model is: ； in, is the area of ​​the computer room wall, in units of ; For the The air conditioner is in The return air temperature at a certain moment, in ; is the air quality of the hot aisle, in ; is the convection heat transfer coefficient of the wall, in units of ; For the The hot channel temperature at the moment, in ; is the temperature of the external environment, in units of .

5. The energy-saving optimization method for a data center computer room based on virtual energy storage according to claim 4 is characterized in that: The formula of the energy consumption model is as follows: ； in, For the The air conditioner is in of the moment No. Air conditioning in the The energy consumption at each moment is: in, Indicates the air density.

6. The energy-saving optimization method for a data center computer room based on virtual energy storage according to claim 5 is characterized in that: Based on the predicted value of the thermal environment and the energy consumption value of the air conditioner, the recommended value of the air conditioner operating condition at the next moment is obtained through the rolling optimization algorithm. The specific method is as follows: Set the time granularity v and get the current time t; Determine whether the current time t has reached the preset decision moment. If not, enter the optimization function Sleep(1); Once the decision-making moment is reached, the basic information of the data center room, weather information and local electricity price information are used as the basic input of the optimization algorithm; The scheduling cycle is discretized in time into The state of the next time stage in the model is determined by the state of the current time stage; Obtain temperature information of the data center room in real time and input it into the time domain rolling optimization algorithm as real-time feedback; According to the current electricity price information, thermal environment forecast value and air conditioning energy consumption value, the recommended value of air conditioning operating conditions at the next moment is calculated.

7. The energy-saving optimization method for a data center computer room based on virtual energy storage according to claim 6 is characterized in that: The processing strategy of the rolling optimization algorithm is as follows: Increase the output of air conditioning equipment when electricity prices are low, and store cooling energy in the air conditioning-building system; When electricity prices are high, the cold stored in the air-conditioning-building system is used to cool the heat generated by the equipment in the computer room, and the output power of the air-conditioning equipment is reduced.

8. The energy-saving optimization method for a data center computer room based on virtual energy storage according to claim 1 is characterized in that: The thermal environment temperature constraints are as follows: in, are the lower and upper temperature limits respectively.

9. An energy-saving optimization system for a data center computer room based on virtual energy storage, characterized in that: include: Data collection and monitoring module, used to obtain and monitor the environmental data and equipment operation status data of the data center room; Data storage and analysis module: used to store and analyze acquired environmental data and equipment operation status data; An air-conditioning-building RC model building module is used to build an air-conditioning-building RC model based on the environmental data and the equipment operation status data, and iteratively predict the thermal environment of the computer room in a limited time in the future through the air-conditioning-building RC model to obtain a thermal environment prediction value; An energy consumption model building module is used to model the energy consumption of the HVAC equipment in the data center computer room and calculate the energy consumption of each air conditioner at each moment based on the energy consumption model; The optimization algorithm module is used to obtain the recommended value of the air conditioner operating condition at the next moment through a rolling optimization algorithm based on the thermal environment prediction value and the air conditioner energy consumption value; The control execution module is used to control the air conditioner to operate according to the recommended working conditions.

10. The energy-saving optimization system for a data center computer room based on virtual energy storage according to claim 9, characterized in that: The control execution module includes the Modbus protocol, which is used to ensure the accuracy and reliability of the control operation.

Images