Cloud computing energy consumption optimization method and device, equipment, medium and program product

Abstract

The invention relates to the technical field of cloud computing, and discloses a cloud computing energy consumption optimization method and device, equipment, a medium and a program product, and the cloud computing energy consumption optimization method comprises the steps: obtaining physical resource information in a plurality of physical machines in a cloud computing scene; according to the physical resource information and the physical machine energy consumption information, generating energy consumption correlation curves respectively corresponding to various physical resources in the plurality of physical machines; superposing the resource use information of the calculation task and the physical resource information of the plurality of physical machines to obtain target physical resource information; predicting the energy consumption of the plurality of physical machines according to the target physical resource information and the energy consumption correlation curve to obtain a plurality of energy consumption predicted values; and selecting a minimum value from the plurality of energy consumption predicted values as a target energy consumption predicted value, and distributing the calculation task to a physical machine corresponding to the target energy consumption predicted value. According to the method, the computing task is allocated to the physical machine with the minimum energy consumption, so that the cloud computing energy consumption is optimized.

Description

Technical Field

[0001] The present invention relates to the field of cloud computing technology, and in particular to a method, device, equipment, medium and program product for optimizing cloud computing energy consumption. Background Art

[0002] With the continuous development of cloud computing, hybrid deployment of cloud resources has become more and more popular. Hybrid deployment of cloud resources refers to combining different types of cloud computing resources (including resources from public clouds, private clouds, and local data centers) in various ways to build a more flexible and efficient computing environment that can meet complex business needs. In the hybrid deployment of cloud resources, cloud computing generates more energy consumption, and minimizing energy consumption becomes a key issue.

[0003] At present, the method to reduce the energy consumption of cloud computing is to dynamically allocate computing tasks according to the load conditions. When the load of a server or virtual machine is too high, some computing tasks are automatically migrated to servers or virtual machines with lower loads to reduce the energy consumption caused by excessive use of servers or virtual machines. However, this method will cause performance loss in the process of migrating computing tasks. Therefore, the effect of optimizing cloud computing energy consumption based on this method is poor. Summary of the invention

[0004] In view of this, the present invention provides a method, device, equipment, medium and program product for optimizing cloud computing energy consumption to solve the problem of poor effect of optimizing cloud computing energy consumption.

[0005] In a first aspect, the present invention provides a method for optimizing cloud computing energy consumption, including: obtaining physical resource information in multiple physical machines in a cloud computing scenario, the physical resource information being used to characterize the usage of multiple physical resources in the physical machines; generating energy consumption correlation curves corresponding to multiple physical resources in multiple physical machines according to the physical resource information and the physical machine energy consumption information; the physical machine energy consumption information being used to characterize the energy consumption generated during the process of load increase of multiple physical resources in multiple physical machines; superimposing the resource usage information of the computing task with the physical resource information of multiple physical machines to obtain target physical resource information; the resource usage information being used to characterize the usage of the physical resources of the physical machine to be assigned by the computing task; predicting the energy consumption of multiple physical machines according to the target physical resource information and the energy consumption correlation curve to obtain multiple energy consumption prediction values; selecting the minimum value among the multiple energy consumption prediction values ​​as the target energy consumption prediction value, and assigning the computing task to the physical machine corresponding to the target energy consumption prediction value.

[0006] The present invention obtains physical resource information for characterizing the usage of various physical resources in multiple physical machines in a cloud computing scenario, and generates energy consumption correlation curves corresponding to various physical resources in the multiple physical machines according to the physical machine energy consumption information and the physical resource information. The present invention analyzes the correlation between the physical resource information and the physical machine energy consumption information to obtain the energy consumption correlation curve, and associates the usage of various physical resources in the multiple physical machines with the energy consumption generated during the load increase of the various physical resources in the multiple physical machines to obtain a correlation, which is convenient for subsequent prediction of energy consumption. The present invention superimposes the resource usage information of the computing task with the physical resource information of multiple physical machines to obtain the target physical resource information, and uses the energy consumption correlation curve to predict the energy consumption of multiple physical machines according to the target physical resource information to obtain multiple energy consumption prediction values, and selects the minimum value from the multiple energy consumption prediction values ​​as the target energy consumption prediction value, and allocates the computing task to the physical machine corresponding to the target energy consumption prediction value. The present invention uses the energy consumption correlation curve to predict the energy consumption generated after the computing task is allocated to multiple physical machines, and selects the physical machine corresponding to the minimum energy consumption from all the energy consumptions to allocate the computing task, indicating that the computing task is allocated to the physical machine that generates the minimum energy consumption, thereby achieving energy consumption minimization. Compared with the related art, the present invention selects the physical machine that generates the minimum energy consumption from the beginning of allocating computing tasks, thereby achieving better energy consumption optimization effect.

[0007] In an optional embodiment, energy consumption correlation curves corresponding to multiple physical resources in multiple physical machines are generated based on physical resource information and physical machine energy consumption information, including: inputting the physical resource information and the physical machine energy consumption information into a correlation curve generation model to obtain an energy consumption correlation curve, the input of the correlation curve generation model is the physical resource information and the physical machine energy consumption information, and the output of the correlation curve generation model is the energy consumption correlation curve.

[0008] The correlation curve generation model of the present invention is obtained by training based on a large amount of historical data. Therefore, the physical resource information and the physical machine energy consumption information are input into the correlation curve generation model to obtain the energy consumption correlation curve. The obtained energy consumption correlation curve is more accurate, so that the subsequent energy consumption prediction value obtained based on the energy consumption correlation curve is also more accurate.

[0009] In an optional implementation, the resource usage information of the computing task is superimposed with the physical resource information of multiple physical machines to obtain target physical resource information, including: obtaining a first usage of multiple physical resources in the resource usage information and a second usage of multiple physical resources in the physical resource information; adding the first usage and the second usage corresponding to the same type of physical resources to obtain the target physical resource information.

[0010] The present invention superimposes the used resource amounts corresponding to the same type of physical resources and the resource amounts required for computing tasks to obtain the total resource usage on the physical machine after the computing tasks are assigned to the physical machine, so as to facilitate subsequent prediction of energy consumption.

[0011] In an optional implementation, the energy consumption of multiple physical machines is predicted based on the target physical resource information and the energy consumption correlation curve to obtain multiple energy consumption prediction values, including: determining the correlation relationship between the physical resource information and the physical machine energy consumption information based on the energy consumption correlation curve; substituting the target physical resource information into the correlation relationship to obtain multiple energy consumption prediction values.

[0012] In an optional embodiment, the method for optimizing cloud computing energy consumption also includes a process of training a correlation curve generation model; the training process of the correlation curve generation model includes: collecting multiple physical resource usage information of multiple physical machines according to a first preset time period, and collecting energy consumption information corresponding to the multiple physical resource usage information according to the first preset time period; judging whether the physical resources have reached the maximum usage based on the multiple physical resource usage information, if the physical resources have reached the maximum usage, performing correlation analysis on the multiple physical resource usage information and energy consumption information to obtain a correlation curve to train the correlation curve generation model.

[0013] In an optional implementation, the method for optimizing cloud computing energy consumption further includes: if the physical resources have not reached maximum usage, adjusting the sampling intensity, and collecting a variety of physical resource usage information and energy consumption information according to the new sampling intensity until the physical resources reach maximum usage.

[0014] In the process of training the correlation curve generation model, the present invention performs sampling according to a first preset time to determine whether the physical resources have reached the maximum usage. If the physical resources have reached the maximum usage, a correlation curve is generated. If the physical resources have not reached the maximum usage, the sampling intensity is adjusted, and a variety of physical resource usage information and energy consumption information are collected according to the new sampling intensity until the physical resources reach the maximum usage, thereby ensuring the accuracy of the correlation curve generation model obtained through training.

[0015] In a second aspect, the present invention provides an optimization device for cloud computing energy consumption, including: a physical resource information acquisition module, used to acquire physical resource information in multiple physical machines in a cloud computing scenario, the physical resource information being used to characterize the usage of multiple physical resources in the physical machines; an energy consumption correlation curve generation module, used to generate energy consumption correlation curves corresponding to multiple physical resources in multiple physical machines according to the physical resource information and the physical machine energy consumption information; the physical machine energy consumption information is used to characterize the energy consumption generated during the load increase of multiple physical resources in multiple physical machines; a target physical resource information determination module, used to superimpose the resource usage information of a computing task with the physical resource information of multiple physical machines to obtain the target physical resource information; the resource usage information is used to characterize the usage of the physical resources of the physical machine to be assigned by the computing task; an energy consumption prediction module, used to predict the energy consumption of multiple physical machines according to the target physical resource information and the energy consumption correlation curve, and obtain multiple energy consumption prediction values; a computing task allocation module, used to select the minimum value among multiple energy consumption prediction values ​​as the target energy consumption prediction value, and assign the computing task to the physical machine corresponding to the target energy consumption prediction value.

[0016] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for optimizing cloud computing energy consumption of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for optimizing cloud computing energy consumption of the above-mentioned first aspect or any corresponding embodiment thereof.

[0018] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for optimizing cloud computing energy consumption according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 is a flow chart of a method for optimizing cloud computing energy consumption according to an embodiment of the present invention;

[0021] Figure 2 is a flow chart of another method for optimizing cloud computing energy consumption according to an embodiment of the present invention;

[0022] Figure 3 is a flowchart of a training method for a correlation curve generation model according to an embodiment of the present invention;

[0023] Figure 4 It is a flow chart of a method for collecting a CPU occupancy rate and CPU energy consumption correlation curve according to an embodiment of the present invention;

[0024] Figure 5 is a flow chart of another method for optimizing cloud computing energy consumption according to an embodiment of the present invention;

[0025] Figure 6 is a structural block diagram of a device for optimizing cloud computing energy consumption according to an embodiment of the present invention;

[0026] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0028] With the continuous development of cloud computing, hybrid deployment of cloud resources has become more and more popular. Energy consumption has become one of the main operating expenses of cloud computing vendors. In the hybrid deployment of cloud resources, how to minimize energy consumption has become an issue that cloud computing vendors are exploring.

[0029] In hybrid cloud scenarios, there are currently many energy consumption measurement methods and energy consumption optimization models for cloud computing scenarios, but there is a lack of energy consumption optimization solutions for computing task allocation under hybrid deployment of cloud resources.

[0030] According to an embodiment of the present invention, an embodiment of a method for optimizing cloud computing energy consumption is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] In this embodiment, a method for optimizing cloud computing energy consumption is provided, which can be used for computer equipment. Figure 1is a flow chart of a method for optimizing cloud computing energy consumption according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0032] Step S101, obtaining physical resource information of multiple physical machines in a cloud computing scenario, where the physical resource information is used to characterize the usage of multiple physical resources in the physical machines.

[0033] Among them, each physical machine includes multiple physical resources, such as a central processing unit (CPU), memory, disk and other hardware resources. Therefore, the physical resource information of each physical machine includes at least one or more of CPU occupancy, memory occupancy and disk read and write rate; the cloud computing energy consumption involved in this embodiment specifically refers to the energy consumption of cloud computing resources, which may include but is not limited to one or more of the energy consumption of public clouds, private clouds and the energy consumption of resources in local data centers.

[0034] In some optional implementations, the multiple physical machines in the cloud computing scenario involved in this embodiment may specifically be all physical machines in the target cloud platform or physical machines in use.

[0035] In some optional implementations, the method for obtaining physical resource information may be obtaining the physical resource information in a task manager or resource manager in a physical machine, or sending a command to the physical machine to obtain the physical resource information, or using third-party monitoring software to obtain the physical resource information.

[0036] Step S102, generating energy consumption correlation curves corresponding to multiple physical resources in multiple physical machines according to physical resource information and physical machine energy consumption information; the physical machine energy consumption information is used to characterize the energy consumption generated during the load increase of multiple physical resources in multiple physical machines.

[0037] Among them, the energy consumption information of the physical machine can be obtained by installing energy consumption monitoring software on the physical machine, or it can be directly measured by connecting an external power meter to the physical machine; the energy consumption correlation curve involved in this embodiment specifically refers to the relationship curve between the physical resource usage and the corresponding energy consumption.

[0038] In some optional embodiments, energy consumption correlation curves corresponding to multiple physical resources in multiple physical machines are generated based on physical resource information and physical machine energy consumption information, including: inputting the physical resource information and the physical machine energy consumption information into a correlation curve generation model to obtain an energy consumption correlation curve, the input of the correlation curve generation model is the physical resource information and the physical machine energy consumption information, and the output of the correlation curve generation model is the energy consumption correlation curve.

[0039] Among them, the number of energy consumption correlation curves of each physical machine output by the correlation curve generation model is related to the number of physical resource types in the physical resource information. The number of energy consumption correlation curves of each physical machine can be multiple or one. For example, if the physical resource information includes CPU occupancy, memory occupancy and disk read and write rate, the energy consumption correlation curve output by the correlation curve generation model is a first energy consumption correlation curve between CPU occupancy and CPU energy consumption, a second energy consumption correlation curve between memory occupancy and memory energy consumption, and a third energy consumption correlation curve between disk read and write rate and disk energy consumption; if the physical resource information includes CPU occupancy, the energy consumption correlation curve output by the correlation curve generation model is an energy consumption correlation curve between CPU occupancy and CPU energy consumption.

[0040] In some optional implementations, when the physical resource information includes CPU occupancy, memory occupancy, and disk read / write rate, the relational expression of the correlation curve generation model is:

[0041]

[0042] Among them, E total represents the total energy consumption, n is the nth physical machine, k is the total number of physical machines, R cpun is the CPU usage of the nth physical machine, R memn is the memory usage of the nth physical machine, R ion is the disk read and write rate of the nth physical machine, E base is the basic energy consumption of the physical machine, f1() represents the first correlation function between CPU occupancy and CPU energy consumption, f2() represents the second correlation function between memory occupancy and memory energy consumption, and f3() represents the third correlation function between disk read and write rate and disk energy consumption.

[0043] Step S103, superimposing the resource usage information of the computing task with the physical resource information of multiple physical machines to obtain target physical resource information; the resource usage information is used to characterize the usage of the physical resources of the physical machine to be allocated by the computing task.

[0044] Among them, computing tasks are various work units or operation sets performed in a cloud computing environment using the computing resources of a cloud computing system. Resource usage information is the physical resource information required to perform computing tasks. The target physical resource information includes the superposition information of multiple physical resources of multiple physical machines.

[0045] In some optional implementations, the resource usage information of the computing task is superimposed with the physical resource information of multiple physical machines to obtain target physical resource information, including: obtaining a first usage of multiple physical resources in the resource usage information and a second usage of multiple physical resources in the physical resource information; adding the first usage and the second usage corresponding to the same type of physical resources to obtain the target physical resource information.

[0046] Exemplarily, the resource usage information of the computing task includes CPU occupancy and memory occupancy. The CPU occupancy in the physical resource information of each physical machine and the CPU occupancy in the resource usage information are added to obtain the overall CPU usage information in the target physical resource information. The memory occupancy in the physical resource information of each physical machine and the memory occupancy in the resource usage information are added to obtain the overall memory usage of each physical machine in the target physical resource information.

[0047] Step S104: predicting the energy consumption of multiple physical machines according to the target physical resource information and the energy consumption correlation curve to obtain multiple energy consumption prediction values.

[0048] In some optional embodiments, the energy consumption of multiple physical machines is predicted based on the target physical resource information and the energy consumption correlation curve to obtain multiple energy consumption prediction values, including: determining the correlation relationship between the physical resource information and the physical machine energy consumption information based on the energy consumption correlation curve; substituting the target physical resource information into the correlation relationship to obtain multiple energy consumption prediction values.

[0049] Among them, the nature of the energy consumption correlation curve is determined by the correlation between the physical resource information and the physical machine energy consumption information, which can be a linear relationship or a nonlinear relationship. For example, if the energy consumption correlation curve is a linear correlation curve, the correlation relationship equation can be y=ax+b. If the energy consumption correlation curve is a nonlinear correlation curve, the correlation relationship equation can be a quadratic function, exponential function, logarithmic function and other nonlinear relationships.

[0050] In some optional embodiments, the target physical resource information is substituted into a correlation formula to obtain multiple energy consumption prediction values, including: substituting the target resource usage corresponding to multiple physical resources in the target physical resource information of each physical machine into the correlation formula to obtain energy consumption values ​​corresponding to the multiple physical resources, and superimposing the multiple energy consumption values ​​to obtain the energy consumption prediction value corresponding to each physical machine.

[0051] Step S105 , selecting a minimum value from a plurality of energy consumption prediction values ​​as a target energy consumption prediction value, and allocating the computing task to a physical machine corresponding to the target energy consumption prediction value.

[0052] Among them, the multiple energy consumption prediction values ​​are the overall energy consumption prediction values ​​corresponding to the multiple physical machines respectively, and the minimum value among the multiple energy consumption prediction values ​​is the energy consumption prediction value corresponding to the physical machine with the minimum energy consumption after the computing tasks are allocated to the physical machines.

[0053] Exemplarily, if a computing task can be assigned to three physical machines A, B, and C, based on the current resource usage of the three physical machines, the CPU, memory, and disk read and write data after the computing task is placed can be predicted. Based on the energy consumption correlation curve, according to the CPU, memory, and disk read and write data after the computing task is placed, the energy consumption prediction values ​​of the three physical machines after receiving the computing task are obtained. The energy consumption prediction values ​​of the three physical machines after receiving the computing task are compared respectively, and the physical machine computing task allocation point corresponding to the smallest energy consumption prediction value is taken.

[0054] The method for optimizing cloud computing energy consumption provided in this embodiment obtains physical resource information for characterizing the usage of multiple physical resources in multiple physical machines in a cloud computing scenario, and generates energy consumption correlation curves corresponding to multiple physical resources in the multiple physical machines according to the physical machine energy consumption information and the physical resource information. The present invention analyzes the correlation between the physical resource information and the physical machine energy consumption information to obtain the energy consumption correlation curve, and associates the usage of multiple physical resources in the multiple physical machines with the energy consumption generated during the load increase of the multiple physical resources in the multiple physical machines to obtain a correlation, which is convenient for subsequent prediction of energy consumption. The present invention superimposes the resource usage information of the computing task with the physical resource information of multiple physical machines to obtain the target physical resource information, and uses the energy consumption correlation curve to predict the energy consumption of multiple physical machines according to the target physical resource information to obtain multiple energy consumption prediction values, and selects the minimum value from the multiple energy consumption prediction values ​​as the target energy consumption prediction value, and allocates the computing task to the physical machine corresponding to the target energy consumption prediction value. The present invention uses the energy consumption correlation curve to predict the energy consumption generated after the computing task is allocated to multiple physical machines, and selects the physical machine corresponding to the minimum energy consumption from all the energy consumptions to allocate the computing task, indicating that the computing task is allocated to the physical machine that generates the minimum energy consumption, thereby achieving energy consumption minimization. Compared with the related art, the present invention selects the physical machine that generates the minimum energy consumption from the beginning of allocating computing tasks, thereby achieving better energy consumption optimization effect.

[0055] In this embodiment, a method for optimizing cloud computing energy consumption is provided, which can be used for computer equipment. Figure 2 is a flow chart of another method for optimizing cloud computing energy consumption according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0056] Step S201, obtaining physical resource information of multiple physical machines in a cloud computing scenario, where the physical resource information is used to characterize the usage of multiple physical resources in the physical machines. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0057] Step S202, generating energy consumption correlation curves corresponding to multiple physical resources in multiple physical machines according to physical resource information and physical machine energy consumption information; the physical machine energy consumption information is used to characterize the energy consumption generated during the load increase of multiple physical resources in multiple physical machines.

[0058] Specifically, the above step S202 includes:

[0059] Step S2021, input the physical resource information and the physical machine energy consumption information into the correlation curve generation model to obtain the energy consumption correlation curve, the input of the correlation curve generation model is the physical resource information and the physical machine energy consumption information, and the output of the correlation curve generation model is the energy consumption correlation curve.

[0060] Step S203, superimposing the resource usage information of the computing task with the physical resource information of multiple physical machines to obtain target physical resource information; the resource usage information is used to characterize the usage of the physical resources of the physical machine to be allocated by the computing task.

[0061] Specifically, the above step S203 includes:

[0062] Step S2031: Obtain first usage amounts of multiple physical resources in the resource usage information and second usage amounts of multiple physical resources in the physical resource information.

[0063] Step S2032: Add the first usage amount and the second usage amount corresponding to the same type of physical resources to obtain target physical resource information.

[0064] Step S204: predicting the energy consumption of multiple physical machines according to the target physical resource information and the energy consumption correlation curve to obtain multiple energy consumption prediction values.

[0065] Specifically, the above step S204 includes:

[0066] Step S2041: Determine a correlation relationship between the physical resource information and the physical machine energy consumption information according to the energy consumption correlation curve.

[0067] Step S2042, substituting the target physical resource information into the correlation equation to obtain a plurality of energy consumption prediction values.

[0068] Step S205: Select the minimum value from the multiple energy consumption prediction values ​​as the target energy consumption prediction value, and assign the computing task to the physical machine corresponding to the target energy consumption prediction value. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0069] In the method for optimizing cloud computing energy consumption provided in this embodiment, the correlation curve generation model is obtained by training based on a large amount of historical data. Therefore, the physical resource information and the physical machine energy consumption information are input into the correlation curve generation model to obtain the energy consumption correlation curve. The obtained energy consumption correlation curve is more accurate, so that the energy consumption prediction value obtained later based on the energy consumption correlation curve is also more accurate. The used resource amount corresponding to the same type of physical resources and the resource amount required for the computing task are superimposed to obtain the total resource usage on the physical machine after the computing task is assigned to the physical machine, so as to facilitate the subsequent prediction of energy consumption.

[0070] In this embodiment, a method for optimizing cloud computing energy consumption is provided, which can be used for computer equipment. The method for optimizing cloud computing energy consumption also includes a process of training a correlation curve generation model. Figure 3 is a flowchart of a training method for a correlation curve generation model according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0071] Step S301: collect various physical resource usage information of a plurality of physical machines according to a first preset time period, and collect energy consumption information corresponding to the various physical resource usage information according to the first preset time period.

[0072] The first preset time period may be customized according to actual conditions. For example, the first preset time period may be 5 seconds.

[0073] In some optional implementations, a physical machine is run to perform an energy consumption test, and various physical resource usage information and energy consumption information corresponding to the various physical resource usage information are collected every 5 seconds.

[0074] Step S302: determining whether the physical resource has reached the maximum usage according to the various physical resource usage information.

[0075] Exemplarily, for the CPU, it is determined whether the CPU occupancy rate reaches 100%.

[0076] Step S303: If the physical resource reaches the maximum usage, a correlation analysis is performed on the usage information and energy consumption information of various physical resources to obtain a correlation curve to train a correlation curve generation model.

[0077] Step S304: if the physical resources have not reached the maximum usage, the sampling intensity is adjusted, and the usage information and energy consumption information of various physical resources are collected according to the new sampling intensity until the physical resources reach the maximum usage.

[0078] The adjustment of the sampling intensity may be adjusting the sampling interval time and the like.

[0079] For example, Figure 4 As shown, it is a flow chart of the method for collecting the correlation curve of CPU occupancy and CPU energy consumption. Figure 4 In the process, the CPU energy consumption test task is run, the CPU occupancy rate is gradually adjusted from 0% to 100%, the CPU occupancy rate and the physical machine energy consumption corresponding to each sampled CPU occupancy rate are sampled multiple times within 5 seconds, the sampling data is obtained, and the sampling data is stored, and it is continuously judged whether the CPU occupancy rate reaches 100%. If it reaches 100%, the sampling is ended, the sampling data is summarized, and the correlation analysis is performed on the sampling data to obtain the correlation curve between the CPU occupancy rate and the energy consumption, and the energy consumption test task is ended; if the CPU occupancy rate does not reach 100%, the test task intensity is adjusted, the CPU occupancy rate and the physical machine energy consumption corresponding to each sampled CPU occupancy rate are collected again, until the CPU occupancy rate reaches 100%, and then the correlation analysis is performed on the sampling data to obtain the correlation curve between the CPU occupancy rate and the energy consumption, and the energy consumption test task is ended.

[0080] In this embodiment, a method for optimizing cloud computing energy consumption is provided, which can be used for computer equipment. Figure 5 is a flow chart of another method for optimizing cloud computing energy consumption according to an embodiment of the present invention. Figure 5 As shown, the process includes:

[0081] Step S501, training the correlation curve generation model.

[0082] The training process of the correlation curve generation model is shown in Figure 3 and Figure 4 The steps of the illustrated embodiment will not be repeated here.

[0083] Step S502: predicting the energy consumption of multiple physical machines using a correlation curve generation model.

[0084] In some optional implementations, target physical resource information of multiple physical machines is input into an energy consumption model, and energy consumption of the multiple physical machines is predicted to obtain multiple prediction results.

[0085] Step S503: selecting a physical machine to allocate computing tasks according to the prediction result.

[0086] In some optional implementations, a minimum value is selected from multiple prediction results, and the computing task is allocated to the physical machine corresponding to the minimum value.

[0087] In this embodiment, a device for optimizing cloud computing energy consumption is also provided, which is used to implement the above embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0088] This embodiment provides a device for optimizing cloud computing energy consumption, such as Figure 6 As shown, including:

[0089] The physical resource information acquisition module 601 is used to acquire physical resource information in multiple physical machines in a cloud computing scenario. The physical resource information is used to characterize the usage of multiple physical resources in the physical machines.

[0090] The energy consumption correlation curve generation module 602 is used to generate energy consumption correlation curves corresponding to multiple physical resources in multiple physical machines based on physical resource information and physical machine energy consumption information; the physical machine energy consumption information is used to characterize the energy consumption generated during the load increase of multiple physical resources in multiple physical machines.

[0091] The target physical resource information determination module 603 is used to superimpose the resource usage information of the computing task with the physical resource information of multiple physical machines to obtain the target physical resource information; the resource usage information is used to characterize the usage of the physical resources of the physical machine to be allocated by the computing task.

[0092] The energy consumption prediction module 604 is used to predict the energy consumption of multiple physical machines according to the target physical resource information and the energy consumption correlation curve to obtain multiple energy consumption prediction values.

[0093] The computing task allocation module 605 is used to select the minimum value from multiple energy consumption prediction values ​​as the target energy consumption prediction value, and allocate the computing task to the physical machine corresponding to the target energy consumption prediction value.

[0094] In some optional implementations, the energy consumption correlation curve generating module 602 includes:

[0095] The correlation curve generation model operation unit is used to input physical resource information and physical machine energy consumption information into the correlation curve generation model to obtain an energy consumption correlation curve. The input of the correlation curve generation model is the physical resource information and physical machine energy consumption information, and the output of the correlation curve generation model is the energy consumption correlation curve.

[0096] In some optional implementations, the target physical resource information determination module 603 includes:

[0097] The usage amount acquisition unit is used to acquire the first usage amounts of multiple physical resources in the resource usage information and the second usage amounts of multiple physical resources in the physical resource information.

[0098] The superposition unit is used to add the first usage amount and the second usage amount corresponding to the same type of physical resources to obtain target physical resource information.

[0099] In some optional implementations, the energy consumption prediction module 604 includes:

[0100] The correlation relationship determination unit is used to determine the correlation relationship between the physical resource information and the physical machine energy consumption information according to the energy consumption correlation curve.

[0101] The energy consumption prediction unit is used to substitute the target physical resource information into the correlation relationship to obtain multiple energy consumption prediction values.

[0102] In some optional implementations, the cloud computing energy consumption optimization device further includes:

[0103] The information collection module is used to collect various physical resource usage information of multiple physical machines according to a first preset time period, and to collect energy consumption information corresponding to the various physical resource usage information according to the first preset time period.

[0104] The correlation curve generation model training module is used to determine whether the physical resources have reached the maximum usage based on the physical resource usage information. According to whether the physical resources have reached the maximum usage, the correlation analysis is performed on the physical resource usage information and energy consumption information to obtain the correlation curve so as to train the correlation curve generation model.

[0105] The correlation curve generation model training module is also used to adjust the sampling intensity according to the fact that the physical resources have not reached the maximum usage, and collect various physical resource usage information and energy consumption information according to the new sampling intensity until the physical resources reach the maximum usage.

[0106] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0107] The cloud computing energy consumption optimization device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0108] The embodiment of the present invention also provides a computer device having the above Figure 7 An apparatus for optimizing energy consumption of cloud computing is shown.

[0109] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0110] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0111] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0112] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0113] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0114] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0115] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0116] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0117] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for optimizing cloud computing energy consumption, characterized in that: The method comprises: Acquire physical resource information in multiple physical machines in a cloud computing scenario, where the physical resource information is used to characterize usage of multiple physical resources in the physical machines; Generate energy consumption correlation curves corresponding to the multiple physical resources in the multiple physical machines respectively according to the physical resource information and the physical machine energy consumption information; the physical machine energy consumption information is used to characterize the energy consumption conditions generated during the process of load increase of the multiple physical resources in the multiple physical machines; The resource usage information of the computing task is superimposed with the physical resource information of the multiple physical machines to obtain target physical resource information; the resource usage information is used to characterize the usage of the physical resources of the physical machine to be allocated by the computing task; Predicting the energy consumption of the multiple physical machines according to the target physical resource information and the energy consumption correlation curve to obtain multiple energy consumption prediction values; A minimum value is selected from the multiple energy consumption prediction values ​​as a target energy consumption prediction value, and the computing task is allocated to a physical machine corresponding to the target energy consumption prediction value.

2. The method according to claim 1, characterized in that The step of generating energy consumption correlation curves respectively corresponding to the multiple physical resources in the multiple physical machines according to the physical resource information and the physical machine energy consumption information includes: The physical resource information and the physical machine energy consumption information are input into a correlation curve generation model to obtain the energy consumption correlation curve. The input of the correlation curve generation model is the physical resource information and the physical machine energy consumption information, and the output of the correlation curve generation model is the energy consumption correlation curve.

3. The method according to claim 1 or 2, characterized in that: The superimposing the resource usage information of the computing task with the physical resource information of the multiple physical machines to obtain target physical resource information includes: Acquire first usage amounts of multiple physical resources in the resource usage information and second usage amounts of the multiple physical resources in the physical resource information; The first usage amount and the second usage amount corresponding to the same type of physical resources are added together to obtain the target physical resource information.

4. The method according to claim 1 or 2, characterized in that: The step of predicting the energy consumption of the multiple physical machines according to the target physical resource information and the energy consumption correlation curve to obtain multiple energy consumption prediction values ​​includes: Determining a correlation relationship between the physical resource information and the physical machine energy consumption information according to the energy consumption correlation curve; Substitute the target physical resource information into the correlation relationship to obtain the multiple energy consumption prediction values.

5. The method according to claim 2, characterized in that: The method also includes a process of training a correlation curve generation model; The training process of the correlation curve generation model includes: Collecting multiple physical resource usage information of the multiple physical machines according to a first preset time period, and collecting energy consumption information corresponding to the multiple physical resource usage information according to the first preset time period; Whether the physical resource has reached the maximum usage is determined based on the multiple physical resource usage information. If the physical resource has reached the maximum usage, a correlation analysis is performed on the multiple physical resource usage information and the energy consumption information to obtain a correlation curve to train the correlation curve generation model.

6. The method according to claim 5, characterized in that The method further comprises: If the physical resource has not reached the maximum usage, the sampling intensity is adjusted, and the multiple physical resource usage information and the energy consumption information are collected according to the new sampling intensity until the physical resource reaches the maximum usage.

7. A device for optimizing cloud computing energy consumption, characterized in that: The device comprises: A physical resource information acquisition module, used to acquire physical resource information in multiple physical machines in a cloud computing scenario, wherein the physical resource information is used to characterize the usage of multiple physical resources in the physical machines; An energy consumption correlation curve generating module, used to generate energy consumption correlation curves corresponding to the multiple physical resources in the multiple physical machines respectively according to the physical resource information and the physical machine energy consumption information; the physical machine energy consumption information is used to characterize the energy consumption conditions generated during the process of load increase of the multiple physical resources in the multiple physical machines; a target physical resource information determination module, configured to superimpose the resource usage information of the computing task with the physical resource information of the multiple physical machines to obtain target physical resource information; the resource usage information is used to characterize the usage of the physical resources of the physical machine to be allocated by the computing task; An energy consumption prediction module, used to predict the energy consumption of the multiple physical machines according to the target physical resource information and the energy consumption correlation curve, and obtain multiple energy consumption prediction values; The computing task allocation module is used to select a minimum value from the multiple energy consumption prediction values ​​as a target energy consumption prediction value, and allocate the computing task to a physical machine corresponding to the target energy consumption prediction value.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for optimizing cloud computing energy consumption according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for optimizing cloud computing energy consumption according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to cause a computer to execute the method for optimizing cloud computing energy consumption according to any one of claims 1 to 6.

Images