CN-122002769-A - Data center refrigerating system regulation and control method, equipment and computer program product

CN122002769ACN 122002769 ACN122002769 ACN 122002769ACN-122002769-A

Abstract

The application discloses a regulation and control method, equipment and a computer program product of a refrigeration system of a data center, wherein the method comprises the following steps: the space-time point of the target data center refrigerating system is determined by fitting the past operation data (such as the lower tower water temperature of a cooling tower) of the target data center refrigerating system and the environmental data (such as the outdoor dry bulb temperature and the moisture content) of the environment, so as to finish the positioning of the operation state. And calculating theoretical energy efficiency of the target data center refrigerating system by utilizing the tail end load data under different time-space points, the target operation data of the target data center refrigerating system, the target environment data of the environment and the target energy consumption data, and comparing the theoretical energy efficiency with the actual energy efficiency, so that the operation parameters of the system can be properly adjusted according to the comparison result to change the operation state point of the target data center refrigerating system, thereby improving the regulation and control efficiency and accuracy of the target data center refrigerating system and achieving the ideal regulation and control effect.

Inventors

CUI XILIN
JIN HUI
PENG YANGYANG
WU TING
Qin Yaqing

Assignees

科大讯飞股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260327

Claims (10)

1. A method of regulating a refrigeration system of a data center, comprising: Acquiring past operation data of a target data center refrigerating system and environment data of an environment where the past operation data are located, wherein the environment data comprise outdoor dry bulb temperature and moisture content; Fitting the corresponding relation between the lower tower water temperature and the wet bulb temperature by utilizing the outdoor dry bulb temperature, the moisture content and the lower tower water temperature, and converting the three-dimensional state lattice of the outdoor dry bulb temperature, the moisture content and the system load into a two-dimensional coordinate system lattice according to the corresponding relation between the lower tower water temperature and the wet bulb temperature so as to utilize points in the two-dimensional coordinate system lattice to represent space-time points where a target data center refrigerating system is positioned; calculating theoretical energy efficiency of the target data center refrigerating system based on coefficient of performance (COP) calculation criteria by utilizing terminal load data under different time-space points, target operation data of the target data center refrigerating system, target environment data of the environment where the terminal load data is located and target energy consumption data; When the difference value between the actual energy efficiency and the theoretical energy efficiency meets the preset condition, the theoretical energy efficiency is updated by simulating and adjusting the operation parameters of the target data center refrigerating system; when the updated theoretical energy efficiency is better than the theoretical energy efficiency before updating, the operation parameters of the system are adjusted through the control command so as to change the operation state point of the refrigeration system of the target data center.
2. The method of claim 1, wherein said fitting a correspondence between lower column water temperature and wet bulb temperature using said outdoor dry bulb temperature, moisture content and lower column water temperature comprises: Obtaining the outdoor dry bulb temperature and the wet bulb temperature corresponding to the moisture content by inquiring a pre-constructed enthalpy-wet diagram; And fitting a regression equation about the lower tower water temperature and the wet bulb temperature based on a regression analysis method in mathematical statistics to represent the corresponding relationship between the lower tower water temperature and the wet bulb temperature.
3. The method of claim 1, wherein the target data center refrigerant system comprises a chiller, a cooling tower, a water pump, and wherein prior to said utilizing the end load data at different time-space points and the target operational data of the target data center refrigerant system, the target environmental data of the environment in which the target data center refrigerant system is located, the target energy consumption data, calculating theoretical energy efficiency of the target data center refrigerant system based on coefficient of performance COP calculation criteria, the method further comprises: Around each space-time point, fitting a first regression equation about power, load, temperature and flow of cooling water of a chiller based on a regression analysis method in mathematical statistics, fitting a second regression equation about power, load, flow of cooling water, upper tower temperature and lower tower water temperature of a cooling tower based on a regression analysis method in mathematical statistics, and fitting a third regression equation about power and flow of a water pump based on a regression analysis method in mathematical statistics.
4. A method according to claim 3, wherein said calculating theoretical energy efficiency of said target data center refrigeration system based on coefficient of performance COP calculation criteria using end load data at different time-space points and target operational data of the target data center refrigeration system, target environmental data of the environment in which it is located, target energy consumption data, comprises: acquiring end load data and target operation data of a target data center refrigerating system, target environment data of an environment where the end load data and the target operation data are located, and target energy consumption data under different time-space points; The energy consumption of the water pump is determined by taking the values of the temperature and the flow of cooling water contained in target environment data into a first regression equation, taking the values of the load of the cooling tower contained in end load data and the flow of cooling water, the upper tower temperature and the lower tower water temperature contained in target operation data into a second regression equation; Determining the total energy consumption of the target data center refrigerating system by using the energy consumption of the chiller, the energy consumption of the cooling tower and the energy consumption of the water pump; and bringing the value of the total energy consumption of the target data center refrigerating system into the COP calculation formula, and calculating the theoretical energy efficiency of the target data center refrigerating system.
5. The method of claim 1, wherein said calculating an actual energy efficiency of said target data center refrigeration system comprises: And calculating the ratio of the actual load to the actual energy consumption as the actual energy efficiency of the target data center refrigerating system.
6. The method of any of claims 1-5, wherein after changing the operating status point of the target data center refrigeration system by adjusting the operating parameters of the system equipment, the method further comprises: After the target data center refrigerating system is in the changed operation state point and operates stably, recalculating the actual energy efficiency of the target data center refrigerating system, and updating the theoretical energy efficiency again through simulation and adjustment of the operation parameters of the target data center refrigerating system when the difference between the recalculated actual energy efficiency and the updated theoretical energy efficiency meets the preset condition; When the theoretical energy efficiency after the re-updating is better than the theoretical energy efficiency updated last time, the operation parameters of the system are adjusted through the control command, and the operation state point of the refrigeration system of the target data center is changed again; And similarly, continuously adjusting the target data center refrigerating system until the preset adjusting condition is met, and stopping adjusting the system operation parameters to obtain the adjusted target data center refrigerating system.
7. The method of claim 1, wherein the target data center refrigeration system further comprises a board change, the method further comprising: calculating the heat exchange amount of the plate exchanger, and correcting the actual load of the cooling machine by utilizing the heat exchange amount of the plate exchanger through load subtraction to obtain the corrected load of the cooling machine; Correcting the energy consumption of the cooling machine by using the corrected load of the cooling machine to obtain the corrected energy consumption of the cooling machine; Correcting the theoretical energy efficiency of the refrigeration system of the target data center by using the corrected energy consumption of the chiller to obtain corrected theoretical energy efficiency; And when the theoretical energy efficiency after simulation update is better than the theoretical energy efficiency before simulation update, the operating parameters of the system are adjusted through control commands so as to change the operating state point of the refrigerating system of the target data center.
8. The method of claim 7, wherein the method further comprises: When the absolute value of the difference between the heat exchange amount of the plate change and the load of the corrected chiller is smaller than a preset threshold value, controlling the target data center refrigerating system to operate according to the lower limit of the mixed refrigerating mode; Or when the absolute value of the difference between the heat exchange amount of the plate change and the load of the corrected chiller is not smaller than a preset threshold value, controlling the target data center refrigerating system to operate in a completely natural cooling mode.
9. The regulation and control equipment of the refrigeration system of the data center is characterized by comprising a processor, a memory and a system bus; The processor and the memory are connected through the system bus; the memory is for storing one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform the method of any of claims 1-8.
10. A computer program product, characterized in that the program product comprises a computer program which, when executed by an electronic product, is capable of implementing the method of any one of claims 1-8.

Description

Data center refrigerating system regulation and control method, equipment and computer program product Technical Field The present application relates to the field of computer technologies, and in particular, to a method and apparatus for controlling a refrigeration system of a data center, and a computer program product. Background With the rapid development of the fields of artificial intelligence, cloud computing, the internet of things and the like, the scale of a data center serving as a core facility for supporting the operation of a digital infrastructure is continuously enlarged, and the number of the data centers is continuously increased. Because the data center integrates a large amount of core hardware such as servers, switches and storages, the heating density is high, refrigeration is needed throughout the year, and as an important component of the data center, the refrigeration system not only bears an important task of guaranteeing the safe operation of the data center, but also occupies a relatively high energy consumption proportion (such as about 40%), so the energy-saving regulation and control of the refrigeration system is particularly important for reducing the energy consumption of the whole data center. However, the existing data center refrigerating system has single logic (such as a building automation control system), is usually feedback control based on PID, and adjusts and controls the state of equipment by comparing the feedback value of the equipment with a set value, wherein the set value is relatively fixed and single. When the data center refrigerating system adopts a plate exchange and cold machine mixed refrigerating mode, the safe operation of the cold machine is ensured, and meanwhile, the heat exchange capacity of the plate exchange is required to be fully utilized, so that the whole energy consumption is reduced, the control process is complex, the existing single control logic generally adopts single input, and the control requirement cannot be met. In addition, at present, the setting values of equipment such as a refrigeration host, a water pump, a cooling tower and the like in a refrigeration system of a data center are usually adjusted based on experience judgment of engineers, so that the experience of the engineers is relied on, and the adjustment frequency is not guaranteed. The regulation and control effect cannot be accurately fed back, because only the running state of the equipment is directly read from the control system, the energy efficiency information of the equipment cannot be accurately displayed, and if the comparison and adjustment effect is needed, the complicated calculation is needed by staff, so that the regulation and control efficiency and accuracy rate of the refrigeration system of the data center can be reduced, and the final regulation and control effect is affected. Disclosure of Invention The embodiment of the application mainly aims to provide a regulation and control method, equipment and a computer program product for a data center refrigerating system, which can improve the regulation and control efficiency and accuracy of the data center refrigerating system so as to achieve an ideal regulation and control effect. The embodiment of the application provides a regulation and control method of a refrigeration system of a data center, which comprises the following steps: Acquiring past operation data of a target data center refrigerating system and environment data of an environment where the past operation data are located, wherein the environment data comprise outdoor dry bulb temperature and moisture content; Fitting the corresponding relation between the lower tower water temperature and the wet bulb temperature by utilizing the outdoor dry bulb temperature, the moisture content and the lower tower water temperature, and converting the three-dimensional state lattice of the outdoor dry bulb temperature, the moisture content and the system load into a two-dimensional coordinate system lattice according to the corresponding relation between the lower tower water temperature and the wet bulb temperature so as to utilize points in the two-dimensional coordinate system lattice to represent space-time points where a target data center refrigerating system is positioned; calculating theoretical energy efficiency of the target data center refrigerating system based on coefficient of performance (COP) calculation criteria by utilizing terminal load data under different time-space points, target operation data of the target data center refrigerating system, target environment data of the environment where the terminal load data is located and target energy consumption data; When the difference value between the actual energy efficiency and the theoretical energy efficiency meets the preset condition, the theoretical energy efficiency is updated by simulating and adjusting the operation parameters of the target data center refrigerating sys