Data center air conditioner energy-saving optimization control method and device

Abstract

The invention discloses a data center air conditioner energy-saving optimization control method and device, and belongs to the technical field of air conditioner energy consumption optimization. The method comprises the steps that operation parameters of server equipment are obtained; based on the operation parameters of the server equipment, predicting the working state and the operation power of the server equipment by adopting a preset prediction model to obtain prediction results of the working state and the operation power of the server equipment; based on the operation parameters of the server equipment and the prediction result of the working state and the operation power of the server equipment, the optimal control parameters of the air conditioner equipment are determined in combination with the space structure of the data center, the arrangement position information of the server and the power information of non-server equipment in the data center; and the optimal control parameters are sent to air conditioning equipment, so that data center air conditioner energy-saving optimization control is achieved. By adopting the technical scheme of the invention, the energy-saving optimization control of the data center can be effectively realized.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning energy consumption optimization, and in particular to a data center air conditioning energy-saving optimization control method and device. Background Art

[0002] With the development of modern information technology, the number of IDCs (Internet Data Centers) is increasing, and the energy they consume is also increasing. In the modern big data society, data center power consumption accounts for 5% of the total power consumption of all industries in society, and about 30% of the power consumption is generated by the cooling and heat removal system. Data centers often use PUE (Power Usage Effectiveness) to measure the power utilization efficiency of IT equipment in the data center. The closer the PUE value is to 1, the more energy-efficient the data center is.

[0003] At present, one of the reasons for the high energy consumption of the cooling system of the built data center is that the energy-saving transformation is difficult and risky. Whether from the perspective of data security or temperature, the data center server equipment has high security requirements. The data center under energy-saving control has the risk of equipment temperature being too high. At the same time, a large number of control optimization algorithms rely on the internal temperature and power data of the server. For the built data center, it is difficult and there are security risks to obtain this data, and users are not very willing to implement energy-saving transformation.

[0004] Due to the above reasons, many data centers are managed in a rough manner. They do not consider the actual needs of the cabinets for air volume and air temperature from an energy-saving perspective, and often directly set more conservative air-conditioning parameters, resulting in serious over-cooling problems. Summary of the invention

[0005] The present invention provides a data center air conditioning energy-saving optimization control method and device to solve the technical problem that current data centers do not consider the actual needs of cabinets for air supply volume and air supply temperature from the perspective of energy saving, often directly set more conservative air conditioning parameters, and there is serious over-cooling, resulting in energy waste.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] On the one hand, the present invention provides a data center air conditioning energy-saving optimization control method, the cooling method of the data center is air cooling, which includes a server device to be cooled and an air conditioning device for cooling, the method comprising:

[0008] Obtain the operating parameters of the server device;

[0009] Based on the operating parameters of the server device, a preset prediction model is used to predict the working state and operating power of the server device to obtain the prediction results of the working state and operating power of the server device;

[0010] Based on the operating parameters of the server equipment and the predicted results of the working status and operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server and the power information of the non-server equipment in the data center, the optimal control parameters of the air conditioning equipment are determined;

[0011] The optimal control parameters are sent to the air conditioning equipment to achieve energy-saving optimization control of the data center air conditioning.

[0012] Furthermore, the operating parameters include: the air inlet temperature of the server, the air outlet temperature of the server, and the air outlet speed of the server.

[0013] Furthermore, the prediction model is a gated recurrent unit neural network model; the input of the prediction model is the operating parameters of the server device, and the output of the prediction model is the prediction result of the working status and operating power of the server device.

[0014] Furthermore, the optimal control parameters of the air conditioning equipment are determined based on the operating parameters of the server equipment and the prediction results of the working status and operating power of the server equipment, in combination with the spatial structure of the data center, the layout location information of the server, and the power information of the non-server equipment in the data center, including:

[0015] Based on the prediction results of the operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server and the power information of the non-server equipment in the data center, the minimum total cooling capacity required for the data center is determined;

[0016] Calculate the energy saving of data center cooling based on the minimum total cooling capacity required by the data center;

[0017] Based on the operating parameters of the server equipment, calculate the stability of the server temperature in time and space;

[0018] Based on the energy saving degree of data center refrigeration and the stability of server temperature in time and space, combined with the spatial structure of the data center and the layout location information of the servers, the optimal control parameters of the air-conditioning equipment are determined.

[0019] Furthermore, the minimum total cooling capacity P required by the data center cool_min The calculation formula is:

[0020] P cool_min =ωP IT +P other ;

[0021] Among them, P IT represents the predicted result of the operating power of the server equipment; P other Represents the power information of non-server equipment in the data center; ω is the cooling capacity compensation variable, whose value is set by the user based on experience, the spatial structure of the data center and the layout location information of the server.

[0022] Furthermore, the energy saving degree of the data center refrigeration is the ratio of the actual refrigeration capacity of the data center to the minimum total refrigeration capacity required by the data center.

[0023] Furthermore, the calculation formula for the stability of the server temperature in time and space SI is:

[0024]

[0025] Among them, α, β, and γ are adjustment parameters and need to be calibrated based on experience; T i represents the current temperature of the i-th server device; m represents the total number of server devices in the data center; StdDev(T i ) represents the standard deviation of the current temperature of all server devices in the data center; T ij represents the temperature of the i-th server device at the j-th time step; StdDev(T ij ) represents the standard deviation of the temperature of the i-th server device within a preset time period.

[0026] Furthermore, based on the energy saving degree of data center cooling and the stability of server temperature in time and space, combined with the spatial structure of the data center and the layout location information of the servers, the optimal control parameters of the air conditioning equipment are determined, including:

[0027] Based on the spatial structure of the data center and the layout location information of the servers, a fluid simulation model of the data center is constructed; wherein the fluid simulation model of the data center takes the supply air temperature and supply air speed of the air conditioning equipment as input, and takes the outlet air temperature of the server equipment and the operating power of the server equipment as output;

[0028] A multi-objective optimization problem is constructed, and based on the fluid simulation model of the data center, the control parameters of the air conditioning equipment are optimized by a non-dominated genetic optimization algorithm; wherein the multi-objective optimization problem is expressed as:

[0029]

[0030] Among them, SI represents the stability of server temperature in time and space; PI represents the energy saving degree of data center cooling; t as Indicates the air supply temperature of the air conditioning equipment; s aIndicates the air supply speed of the air conditioning equipment.

[0031] The optimal compromise solutions of multiple groups of supply air temperatures and supply air temperatures are obtained through a non-dominated genetic optimization algorithm, and the optimal compromise solutions of multiple groups of supply air temperatures and supply air temperatures are sorted according to the stability of server temperatures in time and space and the energy-saving degree of data center refrigeration. Then, according to the working status of the server equipment, the optimal control parameters of the air-conditioning equipment are screened out from the optimal compromise solutions of multiple groups of supply air temperatures and supply air temperatures.

[0032] Furthermore, the working state of the server device includes: high-load operation state, medium-load operation state, low-load operation state, abnormal heat dissipation state and shutdown state;

[0033] The method of selecting the optimal control parameters of the air conditioning equipment from multiple groups of supply air temperatures and optimal compromise solutions of the supply air temperatures according to the working state of the server equipment includes:

[0034] When the working state of the server equipment is a high-load operation state or a medium-load operation state, a solution with a lower degree of stability of the corresponding server temperature in time and space is selected as the optimal control parameter of the air conditioning equipment;

[0035] When the server equipment is in a low-load operation state, a solution with a lower energy saving degree of the corresponding data center cooling is selected as the optimal control parameter of the air conditioning equipment;

[0036] When the working state of the server equipment is an abnormal heat dissipation state, the solution with the largest corresponding cooling capacity is selected as the optimal control parameter of the air-conditioning equipment.

[0037] On the other hand, the present invention also provides a data center air conditioning energy-saving optimization control device, wherein the cooling method of the data center is air cooling, and the data center includes a server device to be cooled and an air conditioning device for cooling, and the data center air conditioning energy-saving optimization control device includes a data sensor and an edge control module; wherein the edge control module is communicatively connected with the data sensor;

[0038] The data sensor is used to collect the operating parameters of the server equipment and transmit the collected operating parameters of the server equipment to the edge control module; after receiving the data transmitted by the data sensor, the edge control module executes the data center air conditioning energy-saving optimization control method as described above.

[0039] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0040] The present invention obtains the operating parameters of the server equipment; based on the operating parameters of the server equipment, a preset prediction model is used to predict the working state and operating power of the server equipment to obtain the prediction results of the working state and operating power of the server equipment; based on the operating parameters of the server equipment and the prediction results of the working state and operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server and the power information of non-server equipment in the data center, the optimal control parameters of the air-conditioning equipment are determined; thereby, the optimal operating parameters of the air-conditioning can be given, and the energy-saving optimization and regulation of the data center can be effectively realized, and the energy consumption of the air-conditioning can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 It is a schematic diagram of the execution flow of the data center air conditioning energy-saving optimization control method provided by an embodiment of the present invention;

[0043] Figure 2 It is a principle diagram of a data center air conditioning energy-saving optimization control method provided by an embodiment of the present invention;

[0044] Figure 3 is a flow chart of a non-dominated genetic optimization algorithm provided by an embodiment of the present invention;

[0045] Figure 4 It is a flow chart of performing non-dominated genetic optimization by combining Python language and Fluent software provided by an embodiment of the present invention;

[0046] Figure 5 is a schematic diagram of the installation position of the device provided by an embodiment of the present invention in a data center;

[0047] Figure 6 It is a control block diagram of various systems in a data center provided by an embodiment of the present invention.

[0048] Description of reference numerals:

[0049] 1. Sensor at the air outlet; 2. Sensor at the air inlet; 3. Edge control module;

[0050] 4. Server cabinet; 5. Air conditioning unit. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0052] First of all, it should be noted that in the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplarily" is intended to present the concept in a concrete way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0053] First embodiment

[0054] This embodiment provides an energy-saving optimization control method for air conditioning in a data center. The cooling method of the data center is air cooling, and the data center includes server equipment to be cooled and air conditioning equipment for cooling.

[0055] In a feasible implementation, the present invention can be applied to a data center that adopts air cooling as the cooling method and is arranged in a downward air supply elevated floor manner. The data center can have multiple cold and hot channels and multiple air conditioning equipment.

[0056] In a feasible implementation manner, the present invention can be applied to a data center that adopts air cooling as the cooling method, uses row-to-row air conditioners for refrigeration, and has closed cold aisles.

[0057] In a feasible implementation, the present invention can be applied to a data center that adopts air cooling as the cooling method and is arranged in a downward air supply elevated floor manner. The data center is equipped with an active bottom plate and a passive air guide device. The data center can have multiple cold and hot channels and multiple air-conditioning equipment.

[0058] The method can be implemented by an electronic device, and the execution process of the method is as follows: Figure 1 As shown, the following steps are included:

[0059] S1, obtaining the operating parameters of the server device;

[0060] In a feasible implementation manner, the acquired operating parameters of the server device may include parameter information such as server air inlet temperature, server air outlet temperature, and server air outlet speed.

[0061] S2, based on the operating parameters of the server device, using a preset prediction model to predict the working state and operating power of the server device, and obtaining a prediction result of the working state and operating power of the server device;

[0062] In a feasible implementation, a gated recurrent unit neural network can be used to predict the working state and operating power of the server device. The implementation process is as follows: first, the offline operating parameters of the server under different working states are obtained offline; according to the operating parameters and operating state of the server, the gated recurrent unit neural network is trained offline; according to the training results, a suitable neural network is selected and deployed in the edge device to estimate the operating power and operating state of the server. The specific process is as follows:

[0063] First, users need to test on an actual server device. The device does not have to be installed in a real data center environment, but the same sensor devices as in the actual deployment should be deployed at the air inlet and outlet of the server. In addition, a power meter needs to be installed to test the actual power consumption of the server.

[0064] The server is operated under different working conditions, such as high load, low load and shutdown. Under different operating conditions, the server has different heating characteristics, and the operating state of its internal fan and the heat dissipation characteristics of the chip are different. Through sensors and power meters, the server inlet temperature, server outlet temperature, server outlet wind speed data and server power data are collected, and these are paired according to the input-output relationship to form a data set of the server operating under different working conditions.

[0065] The gated recurrent unit neural network is trained offline using the server dataset. The gated recurrent unit neural network has a simpler structure and is more suitable for running in edge devices. The gated recurrent unit updates the gate and resets the gate several times, which can better capture the changing timing information in the server data. The gated recurrent unit is a variant of LSTM. When the input is x, the output h of the gated recurrent unit can be derived using the following variables.

[0066]

[0067] Where: σ and tanh are activation functions, U and W are weight parameters, b is the bias, h (t-1) is the previous output, i and j are the numbers of the dimensions of the input and output data.

[0068] The gated loop unit takes the server inlet temperature, server outlet temperature, and server outlet wind speed data as input, and the server working status and server operating power as output. After training, this model is imported into the edge device to classify and predict the server inlet temperature, server outlet temperature, and server outlet wind speed data collected by sensors in actual control.

[0069] S3, determining optimal control parameters of the air conditioning equipment based on the operating parameters of the server equipment and the predicted results of the working status and operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server, and the power information of the non-server equipment in the data center;

[0070] In a feasible implementation, Figure 2 As shown, the above S3 may include the following steps:

[0071] S31, based on the prediction results of the operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server and the power information of the non-server equipment in the data center, determine the minimum total cooling capacity P required for the data center to match the heat dissipation requirements cool_min ;

[0072] Among them, the minimum total cooling capacity P required by the data center cool_min The actual server power (the predicted result P of the operating power of the server equipment obtained by the prediction model) can be IT represents) and the power information P of non-server equipment in the data center other The calculation method is shown in formula (1):

[0073] P cool_min =ωP IT +P ot her (1)

[0074] The spatial structure of the data center, external ambient temperature and other information will also affect the minimum total cooling capacity required by the data center. This effect can be compensated by adjusting the variable ω in the formula.

[0075] S32, calculating the energy saving degree of cooling of the data center based on the minimum total cooling capacity required by the data center;

[0076] Among them, the ratio of the actual cooling capacity of the data center to the minimum total cooling capacity required by the data center can be used to measure the energy saving degree of data center cooling. The calculation method is shown in formula (2):

[0077]

[0078] In the formula, Q represents the cooling capacity provided by the refrigeration equipment. The closer PI is to 1, the more the cooling capacity provided by the precision air conditioner in the data center matches the cooling needs of the server, that is, the better the energy saving of the data center.

[0079] S33, calculating the temporal and spatial stability of the server temperature based on the operating parameters of the server;

[0080] The temporal and spatial stability of the server temperature can be obtained based on the changes of the server inlet air temperature and the server outlet air temperature in a region and over a period of time. In a feasible implementation, the temporal and spatial stability of the temperature of the server device can be expressed by the calculation method shown in formula (3):

[0081] Assume T ij It is a set of device temperature data within a time period and a certain range, where i represents the device serial number, the value range is m, and j represents the number of time steps of the data, the value range is n.

[0082] According to the above set, the following formula expresses the temperature stability of the device:

[0083]

[0084] In the formula, α, β, and γ are adjustment parameters and need to be calibrated based on experience; T i Indicates the current temperature (operating temperature) of the i-th server device; StdDev(T i ) represents the data set T i The standard deviation of the current temperature of all server devices in the data center space; StdDev(T ij ) is the data set T ij The standard deviation of n temperatures in the history of a device.

[0085] SI measures both the temporal and spatial temperature fluctuations of the device, and can be used to measure the temporal and spatial temperature stability of the device. The smaller this index is, the more stable the device temperature in the data center is. Furthermore, this index can be used to measure the operational safety of the server. Within the safe temperature range, the more stable the server temperature is, the better the operational safety program is; otherwise, the server equipment is at risk of overheating due to sudden demand.

[0086] S34, based on the energy saving degree of the data center cooling and the stability degree of the server temperature in time and space, combined with the spatial structure of the data center and the layout location of the server, determine the optimal control parameters of the air conditioning equipment;

[0087] In a feasible implementation manner, the following may be used: Figure 3The non-dominated genetic optimization algorithm shown in the figure determines the optimal control parameters. Its implementation process is as follows: first, build a control simulation model with air conditioning supply air temperature and air speed as input, and server equipment operating temperature and server operating power as output; extract the characteristics of the model and put it into the edge device; set the initial parameters of the model according to the operating power of the server equipment and the operating status of the server equipment; set the initial air conditioning supply air temperature and air speed, and perform genetic optimization with the spatiotemporal average and energy-saving of the ambient temperature as the goal, calculate the control parameters of the air conditioner or other control means, and obtain a set of feasible control parameter setting value solutions; sort the final optimized air conditioning supply air temperature and air speed parameter results in the order of safety and energy saving as possible air conditioning control parameters. The specific implementation process is as follows:

[0088] The user first needs to establish a CFD fluid simulation model of the data center based on the spatial structure of the data center and the server layout information. The fluid simulation model should use the air supply temperature and air supply speed parameters of the air conditioner as input, and the air outlet temperature of the server equipment and the operating power of the server as output;

[0089] Afterwards, the control parameters of the air conditioner are optimized by the non-dominated genetic optimization algorithm. The multi-objective optimization problem can be defined as finding a feasible solution vector that minimizes the objective function vector, which can be expressed mathematically as:

[0090]

[0091] Where x is the decision variable, F(x) is the objective function composed of multiple contradictory sub-functions, and M(x) and N(x) are constraint functions with independent variable x.

[0092] The optimization goal is to minimize the ratio of the actual cooling capacity of the data center to the minimum total cooling capacity required by the data center, and minimize the temperature spatiotemporal stability index SI of the server equipment. Mathematically, it can be expressed as:

[0093]

[0094] In the formula, t as is the air supply temperature of the air conditioner, s a is the air supply speed of the air conditioner. By running the non-dominated genetic optimization algorithm, the optimal compromise solution between multiple groups of air supply temperatures and air supply temperatures can be obtained. In actual operation, t as With s a The constraint value can be appropriately adjusted according to the specific conditions and requirements of the data center.

[0095] In a feasible implementation, Figure 4As shown, non-dominated genetic optimization can be performed jointly by Python language and Fluent software. Use Python language to run non-dominated genetic optimization related algorithms and processes in the cloud, and use Fluent software to model and mesh the controlled data center. Use the Pyfluent library in Python language to control the air conditioning control parameters of the data center in Fluent software and run the simulation. According to the simulation results, the operating effect of the control parameters is calculated in combination with the formula. After multiple simulations and genetic optimization, the non-dominated optimal solution is finally calculated. Then, according to the server operating status, the most suitable control parameter is selected from all available air conditioning supply air temperature and air supply wind speed combinations, and the parameter is sent to the air conditioner to regulate the operation of the air conditioner, so as to realize energy-saving optimization and regulation of the data center; among them, the server operating status can be divided into high-load operating status, medium-load operating status, low-load operating status, abnormal heat dissipation status and shutdown status.

[0096] In a feasible implementation, according to the operating status of the server equipment, a set of the most suitable control parameters that can meet the requirements are selected from the obtained air supply temperature and air supply speed parameters of the air conditioner, specifically: when the server is running at medium or high load, the selection of control parameters tends to cooling, and the optimal solution with lower SI should be selected; when the server is running at low load, the selection of control parameters tends to energy saving, and the optimal solution with lower PI should be selected. In the abnormal heat dissipation state, a warning is issued and the system operates at the maximum cooling capacity.

[0097] S4, sending the optimal control parameters to the air conditioning equipment to achieve energy-saving optimization control of the data center air conditioning.

[0098] Among them, for the operation control of air conditioning equipment, the air conditioning and active floor of the data center can be directly controlled according to the final selected control parameters. According to the optimal control parameters, the data center air conditioning and other controllable equipment adjust their own operating parameters, thereby controlling the temperature and airflow distribution inside the data center, and realizing energy-saving optimization and regulation of the data center. At the same time, according to the control parameters and control results, relevant suggestions for cabinet layout and airflow optimization can be given to guide operation and maintenance personnel to optimize the layout of data center equipment.

[0099] In a feasible implementation, the edge device displays the selected optimal solution to the operation and maintenance personnel in a visual interface through wired or wireless transmission, showing the calculated optimal control solution and the potential energy saving space of the data center; it displays and describes the current problems of hot and cold mixing and hot air reflow in the data center and the locations of the problems, and gives relevant cabinet layout optimization suggestions. It is convenient for the operation and maintenance personnel to manually adjust the air conditioning control parameters of the data center, set reasonable automatic control strategies, and rearrange the cabinets or equipment positions.

[0100] In a feasible implementation, the edge device directly communicates with the air conditioning controller, sends the selected optimal control solution to the air conditioning controller, and directly controls the air supply temperature parameters of the air conditioning, thereby achieving the energy-saving optimization purpose of the data center.

[0101] In a feasible implementation, the edge device directly communicates with controllable devices such as inter-row air conditioners and active floors, and sends the optimal control signal it calculates, thereby achieving energy-saving optimization control of the data center.

[0102] In summary, this embodiment provides a data center air conditioning energy-saving optimization control method, which obtains the operating parameters of the server equipment; based on the operating parameters of the server equipment, a preset prediction model is used to predict the working status and operating power of the server equipment to obtain the prediction results of the working status and operating power of the server equipment; based on the operating parameters of the server equipment and the prediction results of the working status and operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server and the power information of non-server equipment in the data center, the optimal control parameters of the air conditioning equipment are determined; thereby, the optimal operating parameters of the air conditioning can be given, and the energy-saving optimization and regulation of the data center can be effectively realized, thereby reducing the energy consumption of the air conditioning.

[0103] Second embodiment

[0104] This embodiment provides a data center air conditioning energy-saving optimization control device, which includes a data sensor and an edge control module; wherein the edge control module is communicatively connected with the data sensor;

[0105] The data sensor is used to collect the operating parameters of the server equipment and transmit the collected operating parameters of the server equipment to the edge control module; after receiving the data transmitted by the data sensor, the edge control module executes the data center air conditioning energy-saving optimization control method as described in the first embodiment above.

[0106] like Figure 5 As shown, sensors (including sensor 1 at the air outlet and sensor 2 at the air inlet) are installed in the server cabinet 4, and are installed in pairs at the air inlet and air outlet of each or important server equipment; the sensors communicate with the edge control module 3 by wired or wireless means; according to actual needs, sensors can be deployed at the air inlet and air outlet of the equipment rack that is closest to or farthest from the air conditioner and more important; the sensor at the air inlet has a temperature measurement function, and the sensor at the air outlet has a temperature and wind pressure measurement function. Depending on the distance from the edge control module 3, the sensor can be powered by wire or battery.

[0107] The edge control module 3 can communicate with the sensor by wire or wirelessly to obtain the server air inlet temperature, server air outlet temperature, and server air outlet wind speed parameter information collected by the sensor; the edge control module 3 is deployed on the server rack, connected to the sensor in the cabinet through the RS485 bus, and connected to the sensor at a longer distance through the Lora protocol. The edge control module 3 can operate independently and perform energy-saving optimization control, such as Figure 6 As shown; the edge control module can obtain the server operating power and server operating status without being directly connected to the server, accessing and using the network where the server and the data center are located, and reading and controlling the server's operating parameters and data; the edge control module can be connected to the precision air-conditioning equipment, and can directly control the operation of the precision air-conditioning or give recommended control parameters; the edge control module can display the measured server inlet temperature, server outlet temperature, server outlet wind speed and the calculated server equipment operating power, server equipment operating status, air conditioning supply temperature and air supply speed parameters to the user through the network; the user can collect and set in advance according to the building structure, cabinet layout, server equipment parameters, air conditioning parameters and lighting parameters of the data center, and store them in the edge control device.

[0108] Among them, it should be noted that the data center air conditioning energy-saving optimization control device of this embodiment corresponds to the data center air conditioning energy-saving optimization control method of the above-mentioned first embodiment; wherein, the functions realized by each functional module in the data center air conditioning energy-saving optimization control device of this embodiment correspond one-to-one to each process step in the data center air conditioning energy-saving optimization control method of the above-mentioned first embodiment; therefore, they will not be repeated here.

[0109] In addition, it should be noted that the present invention can be provided as a method, an apparatus or a computer program product. Therefore, the embodiment of the present invention can be in the form of a full or partial hardware embodiment, a full or partial software embodiment or an embodiment combining software and hardware. Moreover, when implemented using software, the embodiment of the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in 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 devices. 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 one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). 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 or data center containing one or more available media sets. 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. The semiconductor medium may be a solid state hard disk.

[0110] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0112] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements. In addition, the term "and / or" is only an association relationship describing the associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone, wherein A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding. "At least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can be represented by: a, b, c, ab, ac, bc or abc, where a, b, c can be single or plural.

[0113] In addition, it can be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0114] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0115] In several embodiments provided by the present invention, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of functional modules / units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0116] If the method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0117] Finally, it should be noted that the above is only a preferred embodiment of the present invention. It should be pointed out that although the preferred embodiment of the present invention has been described, for ordinary technicians in this technical field, once the basic creative concept of the present invention is known, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the protection scope of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A data center air conditioning energy-saving optimization control method, wherein the cooling method of the data center is air cooling, and the data center includes a server device to be cooled and an air conditioning device for cooling, characterized in that: The method comprises: Obtain the operating parameters of the server device; Based on the operating parameters of the server device, a preset prediction model is used to predict the working state and operating power of the server device to obtain the prediction results of the working state and operating power of the server device; Based on the operating parameters of the server equipment and the predicted results of the working status and operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server and the power information of the non-server equipment in the data center, the optimal control parameters of the air conditioning equipment are determined; The optimal control parameters are sent to the air conditioning equipment to achieve energy-saving optimization control of the data center air conditioning.

2. The data center air conditioning energy-saving optimization control method according to claim 1, characterized in that: The operating parameters include: the air inlet temperature of the server, the air outlet temperature of the server, and the air outlet speed of the server.

3. The data center air conditioning energy-saving optimization control method according to claim 1, characterized in that: The prediction model is a gated recurrent unit neural network model; the input of the prediction model is the operating parameters of the server device, and the output of the prediction model is the prediction result of the working state and operating power of the server device.

4. The data center air conditioning energy-saving optimization control method according to claim 1, characterized in that: The method of determining the optimal control parameters of the air conditioning equipment based on the operating parameters of the server equipment and the prediction results of the working status and operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server and the power information of the non-server equipment in the data center, includes: Based on the prediction results of the operating power of the server equipment, combined with the spatial structure of the data center, the layout location information of the server and the power information of the non-server equipment in the data center, the minimum total cooling capacity required for the data center is determined; Calculate the energy saving of data center cooling based on the minimum total cooling capacity required by the data center; Based on the operating parameters of the server equipment, calculate the stability of the server temperature in time and space; Based on the energy saving degree of data center refrigeration and the stability of server temperature in time and space, combined with the spatial structure of the data center and the layout location information of the servers, the optimal control parameters of the air-conditioning equipment are determined.

5. The data center air conditioning energy-saving optimization control method according to claim 4, characterized in that: The minimum total cooling capacity P required for the data center cool_min The calculation formula is: P cool_min =ωP IT +P other ; Among them, P IT represents the predicted result of the operating power of the server equipment; P other Represents the power information of non-server equipment in the data center; ω is the cooling capacity compensation variable, whose value is set by the user based on experience, the spatial structure of the data center and the layout location information of the server.

6. The data center air conditioning energy-saving optimization control method according to claim 4, characterized in that: The energy saving degree of the data center refrigeration is the ratio of the actual refrigeration capacity of the data center to the minimum total refrigeration capacity required by the data center.

7. The data center air conditioning energy-saving optimization control method according to claim 4, characterized in that: The calculation formula of the stability of the server temperature in time and space SI is: Among them, α, β, and γ are adjustment parameters and need to be calibrated based on experience; T i represents the current temperature of the i-th server device; m represents the total number of server devices in the data center; StdDev(T i ) represents the standard deviation of the current temperature of all server devices in the data center; T ij represents the temperature of the i-th server device at the j-th time step; StdDev(T ij ) represents the standard deviation of the temperature of the i-th server device within a preset time period.

8. The data center air conditioning energy-saving optimization control method according to claim 4, characterized in that: Based on the energy saving degree of data center cooling and the stability of server temperature in time and space, combined with the spatial structure of the data center and the layout location information of the servers, the optimal control parameters of the air conditioning equipment are determined, including: Based on the spatial structure of the data center and the layout location information of the servers, a fluid simulation model of the data center is constructed; wherein the fluid simulation model of the data center takes the supply air temperature and supply air speed of the air conditioning equipment as input, and takes the outlet air temperature of the server equipment and the operating power of the server equipment as output; A multi-objective optimization problem is constructed, and based on the fluid simulation model of the data center, the control parameters of the air conditioning equipment are optimized by a non-dominated genetic optimization algorithm; wherein the multi-objective optimization problem is expressed as: Among them, SI represents the stability of server temperature in time and space; PI represents the energy saving degree of data center cooling; t as Indicates the air supply temperature of the air conditioning equipment; s a Indicates the air supply speed of the air conditioning equipment. The optimal compromise solutions of multiple groups of supply air temperatures and supply air temperatures are obtained through a non-dominated genetic optimization algorithm, and the optimal compromise solutions of multiple groups of supply air temperatures and supply air temperatures are sorted according to the stability of server temperatures in time and space and the energy-saving degree of data center refrigeration. Then, according to the working status of the server equipment, the optimal control parameters of the air-conditioning equipment are screened out from the optimal compromise solutions of multiple groups of supply air temperatures and supply air temperatures.

9. The data center air conditioning energy-saving optimization control method according to claim 8, characterized in that: The working status of the server device includes: high load operation status, medium load operation status, low load operation status, abnormal heat dissipation status and shutdown status; The method of selecting the optimal control parameters of the air conditioning equipment from multiple groups of supply air temperatures and optimal compromise solutions of the supply air temperatures according to the working state of the server equipment includes: When the working state of the server equipment is a high-load operation state or a medium-load operation state, a solution with a lower degree of stability of the corresponding server temperature in time and space is selected as the optimal control parameter of the air conditioning equipment; When the server equipment is in a low-load operation state, a solution with a lower energy saving degree of the corresponding data center cooling is selected as the optimal control parameter of the air conditioning equipment; When the working state of the server equipment is an abnormal heat dissipation state, the solution with the largest corresponding cooling capacity is selected as the optimal control parameter of the air-conditioning equipment.

10. A data center air conditioning energy-saving optimization control device, wherein the cooling method of the data center is air cooling, and the data center includes a server device to be cooled and an air conditioning device for cooling, characterized in that: The device comprises a data sensor and an edge control module; wherein the edge control module is communicatively connected with the data sensor; The data sensor is used to collect the operating parameters of the server equipment and transmit the collected operating parameters of the server equipment to the edge control module; after receiving the data transmitted by the data sensor, the edge control module executes the data center air conditioning energy-saving optimization control method as described in any one of claims 1 to 9.

Images