Server surplus value evaluation method, device, equipment, medium and program product

Abstract

The invention relates to the technical field of computers, and particularly provides a server surplus value evaluation method, device and equipment, a medium and a program product, and the method comprises the steps: obtaining a first computing power parameter value of a reference server in a target unit time, and a second computing power parameter value of a to-be-evaluated target server in the target unit time; determining a target computing power ratio of the reference server to the target server in the target unit time based on the first computing power parameter value and the second computing power parameter value; based on the target computing power ratio, the first life period of the reference server, the second life period of the target server, the service duration of the target server in the target unit time and a surplus value evaluation model, obtaining the surplus value of the target server relative to the reference server in the target unit time; according to the method and the device, the accuracy of the determined server surplus value can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a server residual value evaluation method, device, equipment, medium and program product. Background Art

[0002] With the continuous development of digital technology, data centers, as the supporting foundation of digital technology, can meet the needs of large-scale data processing and storage; however, as the number of years of server equipment in the network increases, a reasonable assessment of the residual value of massive servers in the data center is of great significance to the asset management, decision-making and sustainable development of data center managers. It can help enterprises optimize resource utilization, control costs, and better adapt to technological development and changes.

[0003] In related technologies, the residual value of a server can usually be evaluated by considering market prices, or the cost and service life of the server; or, an appraiser can conduct a manual evaluation based on the server's hardware condition, configuration and performance, service life, maintenance and servicing records, brand and reliability, technology status, remaining warranty period, etc.

[0004] However, the evaluation schemes for the residual value of servers provided in related technologies usually mainly consider the market value and equipment status of the server, resulting in inaccurate evaluation results for the residual value of the server; at the same time, manual evaluation is more dependent on the professionalism of the evaluators, resulting in large differences in the evaluation results for the residual value of the server. Summary of the invention

[0005] In view of the above problems, the present application is proposed. The present application provides a server residual value evaluation method, device, equipment, medium and program product, which can improve the accuracy of the determined server residual value.

[0006] According to one aspect of the present application, a method for evaluating residual value of a server is provided, comprising:

[0007] Obtaining a first computing power parameter value of a reference server in a target unit time, and a second computing power parameter value of a target server to be evaluated in a target unit time, wherein an initial service time of the target server is earlier than an initial service time of the reference server;

[0008] Determine a target computing power ratio between the reference server and the target server in a target unit time based on the first computing power parameter value and the second computing power parameter value;

[0009] Based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in the target unit time, and the residual value evaluation model, the residual value of the target server relative to the reference server in the target unit time is obtained, wherein the residual value evaluation model is determined based on the same relationship between the usage cost ratio and the computing power ratio between the reference server and the target server under the same computing power requirements.

[0010] According to another aspect of the present application, a server residual value evaluation device is provided, comprising:

[0011] An acquisition module is configured to acquire a first computing power parameter value of a reference server in a target unit time, and a second computing power parameter value of a target server to be evaluated in a target unit time, wherein an initial service time of the target server is earlier than an initial service time of the reference server;

[0012] A determination module, configured to determine a target computing power ratio between the reference server and the target server in a target unit time based on the first computing power parameter value and the second computing power parameter value;

[0013] The evaluation module is configured to obtain the residual value of the target server relative to the reference server in a target unit time based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in a target unit time, and a residual value evaluation model, wherein the residual value evaluation model is determined based on the same relationship between the usage cost ratio and the computing power ratio between the reference server and the target server under the same computing power requirements.

[0014] According to another aspect of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-mentioned server residual value evaluation method.

[0015] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned server residual value evaluation method is implemented.

[0016] According to another aspect of the present application, a computer program product is provided, including a computer program, which implements the above-mentioned server residual value evaluation method when executed by a processor.

[0017] The present application provides a server residual value evaluation method, apparatus, equipment, medium and program product. On the one hand, based on the principle that the usage cost ratio and computing power ratio between a reference server with a later service time and a target server to be evaluated are the same under the same computing power requirements, a residual value evaluation model of the target server relative to the reference server is constructed to determine the residual value of the target server, thereby realizing the evaluation of the residual value of the server from the basic capability dimension of providing computing power services by the server, and improving the scientificity and reliability of the residual value of the determined target server to be evaluated; on the other hand, in the process of determining the target server to be evaluated, the life span of the target server and the reference server, as well as the service time of the target server to be evaluated in the target unit time are comprehensively considered, which can further improve the scientificity and accuracy of the determined residual value of the target server to be evaluated.

[0018] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0020] Figure 1 It is a flowchart illustrating a method for evaluating the residual value of a server according to an embodiment of the present application.

[0021] Figure 2 It is a schematic diagram illustrating the usage cost of the reference server in the first year according to an embodiment of the present application.

[0022] Figure 3 It is a schematic diagram illustrating the usage cost of the target server of an embodiment of the present application after it has been in service for a certain period of time.

[0023] Figure 4 It is a schematic diagram illustrating a process of determining model parameter values ​​according to an embodiment of the present application.

[0024] Figure 5 It is a schematic block diagram illustrating the functional modules of the server residual value evaluation device according to an embodiment of the present application.

[0025] Figure 6 is a schematic diagram illustrating a computer program product according to an embodiment of the present application.

[0026] Figure 7It is a hardware block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present application more obvious, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0028] In the related art, for servers in service, in order to better understand the residual value of the servers, the residual value of the server to be evaluated can be determined by referring to the market price of second-hand servers with similar configurations and usage conditions as the server to be evaluated; or, based on the purchase cost and service life of the server to be evaluated, a certain depreciation rate is used to calculate the residual value of the server to be evaluated, among which common depreciation methods include straight-line depreciation method or double declining balance method; or, ask a professional evaluation agency or technician to conduct a detailed evaluation of the server to be evaluated, and determine the residual value of the server to be evaluated based on their experience and market knowledge.

[0029] However, the residual value evaluation schemes of these servers provided in the related arts all have certain limitations. Among them, when evaluating the residual value of the server through market price, the configuration of the second-hand servers found in the second-hand market is difficult to be completely or basically consistent with the server to be evaluated, resulting in low credibility of the determined residual value of the server to be evaluated; at the same time, when the number of reference second-hand servers that can be found in the second-hand server market is small, the credibility of the residual value of the server to be evaluated determined through the reference servers is even lower.

[0030] When calculating the residual value of the server to be evaluated through the depreciation rate, the reference information mainly includes the purchase cost and the service life. The reference information has fewer dimensions and does not take into account the fluctuation of market prices, resulting in the unreliable residual value of the server to be evaluated.

[0031] In addition, in the process of manually evaluating the residual value of the server to be evaluated, the evaluation result mainly depends on the professionalism of the evaluator and his ability to understand the information of various dimensions, which leads to large differences in the evaluation results determined by different people and low reference value.

[0032] In order to solve the above problems, the present application provides a server residual value evaluation method, which can be applied to terminal devices, which can be electronic devices with data processing capabilities such as computers, notebooks, mobile phones, tablet computers or servers. Figure 1 As shown, Figure 1A flow chart of a server residual value evaluation method provided in an embodiment of the present application is shown, including:

[0033] Step S101, obtaining a first computing power parameter value of a reference server in a target unit time, and a second computing power parameter value of a target server to be evaluated in a target unit time;

[0034] Wherein, the initial service time of the target server is earlier than the initial service time of the reference server;

[0035] Step S102, determining a target computing power ratio between the reference server and the target server in a target unit time based on the first computing power parameter value and the second computing power parameter value;

[0036] Step S103, based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in the target unit time, and the residual value evaluation model, obtain the residual value of the target server relative to the reference server in the target unit time;

[0037] Among them, the residual value evaluation model is determined based on the same relationship between the usage cost ratio and the computing power ratio between the reference server and the target server under the same computing power requirements.

[0038] To summarize, the server residual value evaluation method provided in the embodiment of the present application, on the one hand, constructs a residual value evaluation model of the target server relative to the reference server based on the principle that the usage cost ratio and computing power ratio between a reference server with a later service time and the target server to be evaluated are the same under the same computing power requirements, determines the residual value of the target server, and realizes the evaluation of the residual value of the server from the basic capability dimension of providing computing power services by the server, thereby improving the scientificity and reliability of the residual value of the determined target server to be evaluated; on the other hand, in the process of determining the target server to be evaluated, comprehensively considers the life span of the target server and the reference server, as well as the service time of the target server to be evaluated in the target unit time, which can further improve the scientificity and accuracy of the determined residual value of the target server to be evaluated.

[0039] The following Figure 1 The specific implementation methods of each step in the embodiment shown are described in detail:

[0040] In step S101, the terminal device obtains a first computing power parameter value of a reference server in a target unit time, and a second computing power parameter value of a target server to be evaluated in the target unit time.

[0041] In an embodiment of the present application, the initial service time of the target server is earlier than the initial service time of the reference server; the target unit time is the time required for residual value evaluation, and the target unit time can be determined based on actual needs, which is not limited in the embodiment of the present application. For example, the target unit time can be a certain year, a certain month in a certain year, or a certain day in a certain month in a certain year, etc.; the computing power parameter value is used to characterize the computing power of the server, wherein the computing power parameter value can be the value of the computing power parameter, and the computing power parameter can be determined based on actual needs, which is not limited in the embodiment of the present application. For example, the computing power parameter can include at least one of the number of cores of the server's central processing unit (CPU), the main frequency of a single core, and the floating-point calculation value of a single CPU cycle.

[0042] In an optional embodiment, the process of a terminal device obtaining a first computing power parameter value of a reference server at a target unit time and a second computing power parameter value of a target server to be evaluated at a target unit time may include: in response to detecting a server residual value evaluation operation, the terminal device obtains the target server identifier and the reference server identifier, as well as the target unit time in a first server residual value evaluation instruction generated based on the server residual value evaluation operation, and reads the first computing power parameter value of the reference server at the target unit time and the second computing power parameter value of the target server to be evaluated at the target unit time in a computing power parameter value information table based on the target server identifier and the reference server identifier, as well as the target unit time.

[0043] It is understandable that the computing power parameter value information table can store computing power parameter information of multiple servers at different times, wherein the multiple servers include a target server and a reference server.

[0044] In an optional embodiment, the process of a terminal device obtaining a first computing power parameter value of a reference server at a target unit time and a second computing power parameter value of a target server to be evaluated at a target unit time may include: the terminal device obtains the target unit time in the second server residual value evaluation instruction, the first computing power parameter value of the reference server at the target unit time, and the second computing power parameter value of the target server to be evaluated at the target unit time in response to receiving a second server residual value evaluation instruction sent by the serviceable device.

[0045] Among them, the serviceable device is a terminal device of the service demander that is allowed to provide server residual value evaluation service through the terminal device.

[0046] In step S102, the terminal device determines a target computing power ratio between the reference server and the target server in a target unit time based on the first computing power parameter value and the second computing power parameter value.

[0047] In an embodiment of the present application, the target computing power ratio is used to characterize the difference in computing power between the reference server and the target server in a target unit time; it can be understood that since the computing power of a new server is usually better than that of an old server, when the initial service time of the target server is earlier than the initial service time of the reference server, the larger the target computing power ratio is, the more target servers are required under the same computing power requirements.

[0048] In an optional implementation, the first computing power parameter value includes multiple computing power parameter values, the second computing power parameter value includes multiple computing power parameter values, and the process of the terminal device determining the target computing power ratio of the reference server to the target server in the target unit time based on the first computing power parameter value and the second computing power parameter value may include: determining the product of multiple first computing power parameter values ​​to obtain the first computing power value of the reference server in the target unit time; then, determining the product of multiple second computing power parameter values ​​to obtain the second computing power value of the target server in the target unit time; further, determining the ratio of the first computing power value to the second computing power value as the target computing power ratio of the reference server to the target server in the target unit time. The computing power values ​​of the reference server and the target server can be determined by the product of the values ​​of multiple computing power parameters to improve the accuracy of the determined computing power values ​​of the reference server and the target server, and further improve the accuracy of the determined target computing power ratio of the reference server to the target server in the target unit time.

[0049] In an optional embodiment, when the computing power parameters include the number of CPU cores, the main frequency of a single core and the floating-point calculation value of a single CPU cycle of the server, the terminal device determines the product of multiple first computing power parameter values ​​to obtain the first computing power value of the reference server in the target unit time. The process includes: determining the product of the number of CPU cores, the main frequency of a single core and the floating-point calculation value of a single CPU cycle of the reference server in the target unit time as the first computing power value of the reference server in the target unit time; the first computing power value of the reference server in the target unit time can be determined by computing power parameters in three dimensions: the number of CPU cores, the main frequency of a single core and the floating-point calculation value of a single CPU cycle, thereby further improving the accuracy and reliability of the first computing power value of the reference server in the target unit time.

[0050] It can be understood that, when the computing power parameters include the number of CPU cores, the main frequency of a single core and the floating-point calculation value of a single CPU cycle of the server, the terminal device determines the product of multiple second computing power parameter values, and the process of obtaining the second computing power value of the target server in the target unit time includes: determining the product of the number of CPU cores, the main frequency of a single core and the floating-point calculation value of a single CPU cycle of the target server in the target unit time as the second computing power value of the reference server in the target unit time.

[0051] For example, when the computing power parameters include the number of CPU cores, the main frequency of a single core, and the floating-point calculation value of a single CPU cycle of the server, the first computing power value of the reference server per unit time is:

[0052] F ni =cor ni *hz ni f ni ; (Formula 1)

[0053] In Formula 1, F ni represents the first computing power value of reference server n at unit time i, cor ni Indicates the number of CPU cores of reference server n per unit time i, hz ni represents the single-core main frequency of reference server n per unit time i, and f ni Indicates the CPU single cycle floating point calculation value of reference server n in unit time i.

[0054] The second computing power value of the target server per unit time is:

[0055] F oi =cor oi *hz oi *f oi ; (Formula 2)

[0056] In Formula 2, F oi represents the second computing power value of the target server o in unit time i, cor oi Indicates the number of CPU cores of the target server o per unit time i, hz oi represents the single core frequency of the target server o in unit time i, and f oi Indicates the CPU single cycle floating point calculation value of the target server o in unit time i.

[0057] The computing power ratio is:

[0058]

[0059] Formula 3 indicates that under the same computing power requirements, the computing power of x target servers is the same as that of a reference server per unit time.

[0060] In an optional embodiment, the first computing power parameter value includes a computing power parameter value, the second computing power parameter value includes a computing power parameter value, and the terminal device determines the target computing power ratio between the reference server and the target server in the target unit time based on the first computing power parameter value and the second computing power parameter value. The process may include: determining the ratio of the first computing power parameter value and the second computing power parameter value as the target computing power ratio between the reference server and the target server in the target unit time, so as to quickly obtain the target computing power ratio between the reference server and the target server in the target unit time.

[0061] In step S103, the terminal device obtains the residual value of the target server relative to the reference server in the target unit time based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in the target unit time, and the residual value evaluation model.

[0062] In the embodiment of the present application, according to Moore's Law, the computing power of the server chip increases exponentially over time, so it can be determined that the value of the server's computing power decreases over time. Therefore, an exponentially decreasing model of the server's unit computing power value and time can be constructed to characterize the changing relationship between the server's computing power value and time.

[0063] Wherein, the exponential decline model is:

[0064]

[0065] In Formula 4, θ(t) is the unit computing power value of the t-th unit time, X(t) is the server value of the t-th unit time, F(t) is the server computing power of the t-th unit time, and α, β, and μ are model parameters of the exponentially decreasing model.

[0066] It should be noted that in the embodiment of the present application, under the same computing power requirements, the usage costs of the reference server and the target server are the same, that is, under the same computing power requirements, the usage cost ratio and computing power ratio between the reference server and the target server are the same in any unit time. Based on this principle, an original residual value evaluation model of the target server relative to the reference server can be constructed, wherein the usage cost of the server in a certain unit time is: the product of the unit time and the unit computing power value of the unit time (the unit computing power value is determined by the exponential decreasing model of the unit computing power value and time), and the usage cost of the server in the unit time can also be represented as the difference between the residual value of the server in the unit time and the residual value of the server in the next unit time; therefore, for reference server n, the usage cost of the reference server in unit time i is:

[0067]

[0068] In Formula 5, X n (i) represents the residual value of reference server n in unit time i, X (i+1)n represents the residual value of reference server n at unit time i+1, LCn represents the first lifetime of the reference server n, It is the first computing power value ratio.

[0069] For example, Figure 2 As shown, Figure 2 A schematic diagram showing the usage cost of the reference server in the first year is shown, wherein the residual value of the reference server n in the first year can be represented by the sum of the usage costs of the reference server each year after it starts to be put into service. At the same time, the remaining value of reference server n in the second year can be represented by the sum of the annual usage costs of the reference server after the second year, so the remaining value of reference server n in the second year is Among them, S is the usage cost, Figure 2 The shaded portion S0 is the usage cost of the reference server n in the first year.

[0070] For the target server o, the usage cost of the target server per unit time i is:

[0071]

[0072] In Formula 6, Q io represents the residual value of the target server o after the service time, Q (i+1)o It represents the remaining value of the target server o in the next unit time i+1 after the service time. LCo represents the second life span of the target server o, TO Indicates the service time of the target server o in the target unit time; It is the second computing power value ratio.

[0073] For example, Figure 3 As shown, Figure 3 A schematic diagram showing the use cost of the target server after the service time, wherein the remaining value of the target server o after the service time can be represented by the sum of the use cost of the target server each year after the service time, then the remaining value of the target server o after the service time At the same time, the remaining value of the target server o in the next unit time after the service time can be represented by the sum of the annual usage cost of the target server after the next unit time after the service time. Then the remaining value of the target server o in the next unit time after the service time is Figure 3 Middle shaded area S To is the usage cost of the target server o after it has been in service for a certain period of time.

[0074] Among them, under the same computing power requirements, the computing power requirements of the reference server and the target server in any unit time are equal, which can be expressed as:

[0075]

[0076] It can be seen from Formula 5, Formula 6 and Formula 7 that under the same computing power requirements, the usage cost ratio and computing power ratio between the reference server and the target server are the same. Then, by transforming Formula 7, the original residual value evaluation model of the target server relative to the reference server can be obtained as follows:

[0077]

[0078] It can be understood that the original residual value evaluation model is related to the model parameters of the exponentially decreasing model in which the unit computing power value of the server changes over time.

[0079] It should be noted that, since the computing power value of different servers varies with time, but the configuration and performance of the reference server and the target server are basically the same, the terminal device can construct a computing power value model to characterize the changes in the unit computing power value of the reference server and the target server over time. The computing power value model is an exponentially decreasing model of the unit computing power value of the reference server and the target server and time; at the same time, the model parameters of the computing power value model established based on the device parameter set for different time periods are different. Therefore, the terminal device can periodically update the computing power value model to make the relationship between the unit computing power value of the reference server and the target server and time represented by the computing power value model more in line with the actual situation at the time. Among them, the update cycle of the model can be determined based on actual needs, and the embodiment of the present application does not limit this, for example, every one year, every six months, or every month, etc.

[0080] In an optional embodiment, the terminal device obtains the residual value of the target server relative to the reference server in a target unit time based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in a target unit time, and the residual value evaluation model. The process includes: updating the original residual value evaluation model according to the model parameter values ​​of the computing power value model constructed in the current modeling cycle to obtain the target residual value evaluation model; then, inputting the target unit time, the first life span of the reference server, the service time of the target server in the target unit time, and the second life span into the target residual value evaluation model to obtain the residual value of the target server relative to the reference server in the target unit time; wherein, the target residual value evaluation model is used to evaluate the residual value of the target server relative to the reference server in the target unit time. The residual value of the target server relative to the reference server in the target unit time can be quickly determined by combining the changes in the unit computing power value and time of the first target server and the reference server, the lifespan of the reference server and the target server, the service time of the target server in the target unit time, and the residual value evaluation model used to characterize the target server relative to the reference server.

[0081] The target residual value evaluation model may include: determining a first computing power value ratio of the reference server based on a model parameter value of a computing power value model, the target unit time, and the first life span of the reference server; and determining a second computing power value ratio of the target server based on a model parameter value of a computing power value model, the target unit time, and the first life span of the reference server; and then determining the second computing power value ratio of the target server based on the model parameter value of the computing power value model, the service time of the target server in the target unit time, and the second life span; The product of the first computing power value ratio and the target computing power ratio is used to obtain an updated value of the second computing power value ratio; further, the ratio between the first computing power value ratio and the updated value of the second computing power value ratio is determined as the residual value of the target server relative to the reference server in the target unit time; wherein, the first computing power value ratio is the ratio of the unit computing power value of the reference server at the target unit time, and the total unit computing power value in the remaining life cycle from the target unit time to the first life period; the second computing power value ratio is the ratio of the unit computing power value of the target server after the service time, and the total unit computing power value from the service time to the second life period.

[0082] In an optional implementation, the process of establishing a computing power value model by a terminal device includes: obtaining a first device parameter set of a reference server and a second device parameter set of a target server to be evaluated; then, based on the first sample computing power parameter value of each historical unit time, determining the first sample computing power value of the reference server at each historical unit time, and, based on the second sample computing power parameter value of each historical unit time, determining the second sample computing power value of the target server at each historical unit time; further, determining the ratio of the first sample computing power value to the first sample value index value of each historical unit time, obtaining the first sample unit computing power value of the reference server at each historical unit time, and determining the second sample computing power value of each historical unit time. The second sample unit computing power value of the target server in each historical unit time is obtained by calculating the ratio of the second sample computing power value and the second sample value index value of the target server in each historical unit time; finally, based on the first sample unit computing power value and the second sample unit computing power value of each historical unit time, a parameter prediction model is trained to obtain the first target model parameter value, and the target model parameter value is introduced into the exponential decrease model to construct the computing power value model; wherein, the first device parameter set includes the first sample computing power parameter value and the first sample value index value of the reference server in multiple historical unit times, and the second device parameter set includes the second sample computing power parameter value and the second sample value index value of the target server in multiple historical unit times. The parameter prediction model can be trained through the sample computing power parameter values ​​and sample value index values ​​of the target server and the reference server in multiple historical unit times to obtain the model parameters of the exponential decrease model of the unit computing power value and time of the reference server and the target server, so as to combine the information of the historical unit time to obtain a more accurate exponential decrease model that characterizes the unit computing power value and time of the reference server and the target server, and further improve the accuracy of the evaluation result of the residual value of the determined target server.

[0083] It should be noted that the number of multiple historical unit times can be determined based on actual needs, and the embodiments of the present application do not limit this. The process of the terminal device determining the first sample computing power value of the reference server at each historical unit time based on the first sample computing power parameter value of each historical unit time can refer to the process of determining the first computing power value in the above embodiment, and the process of determining the second sample computing power value of the target server at each historical unit time based on the second sample computing power parameter value of each historical unit time can refer to the process of determining the second computing power value in the above embodiment, and the embodiments of the present application do not limit this.

[0084] The first sample value index value of the reference server at each historical unit time can be used to estimate the computing power value of the reference server at each historical unit time, and the second sample value index value of the target server at each historical unit time can be used to estimate the computing power value of the target server at each unit time.

[0085] In an optional embodiment, the terminal device trains a parameter prediction model based on the first sample unit computing power value and the second sample unit computing power value of each historical unit time to obtain a target model parameter value. The process includes: determining the first sample unit computing power value and the second sample unit computing power value of each historical unit time as sample unit computing power values, respectively, to obtain a sample unit computing power value set; then, for each sample unit computing power value in the sample unit computing power value set, inputting the sample unit computing power value into the parameter prediction model to be trained to obtain a prediction model parameter value; and determining the sample unit computing power prediction value based on the prediction model parameter value and the exponential decrease model; further, inputting the sample unit computing power value and the sample unit computing power prediction value into a loss function to obtain a loss function value; if the loss function value is less than or equal to the loss function threshold, determining the prediction model parameter value as the target model parameter value. In each round of iterative training, after obtaining the prediction model parameter values, the sample unit computing power prediction value can be determined in combination with the exponential decrease model. The sample unit computing power prediction value and the sample unit computing power value can be processed in combination with the loss function to determine whether the model converges, so as to improve the accuracy of the determined model parameters.

[0086] It can be understood that in the embodiment of the present application, the loss function threshold can be determined based on actual needs, and the embodiment of the present application does not limit this; if the loss function value is greater than the loss function threshold, the parameters of the parameter prediction model are updated, and a new round of iterative training is continued until the model converges.

[0087] For example, Figure 4 As shown, Figure 4 The schematic diagram of the model parameter value determination process provided by the embodiment of the present application is shown, wherein the parameter prediction model includes an input layer 401, a hidden layer 402 and an output layer 403, and the terminal device can provide the sample unit computing power value of n historical unit time to the input layer, and output the prediction model parameter values ​​α′, β t′ After θ′ and μ′ are obtained, they can be input into the exponentially decreasing model to determine the predicted value of unit computing power θ′(t), and the model parameters can be updated in combination with the loss function.

[0088] In an optional embodiment, the terminal device can also: obtain the first updated device parameter set of the reference server and the second updated device parameter set of the target server according to the preset update cycle within the next modeling cycle; further, determine the updated computing power value model based on the first updated device parameter set and the second updated device parameter set; the computing power value model and the computing power value model can be updated according to the preset modeling cycle, so that the change of the unit computing power value of the reference server represented by the computing power value model over time is more in line with the current actual situation, and the change of the unit computing power value of the target server represented by the computing power value model over time is more in line with the current actual situation, thereby further improving the residual value evaluation result of the determined target server to be evaluated.

[0089] It should be noted that the process by which the terminal device determines the updated computing power value model based on the first updated device parameter set and the second updated device parameter set can refer to the process by which the terminal device determines the computing power value model based on the first device parameter set and the second device parameter set, and this embodiment of the present application will not go into details.

[0090] An exemplary embodiment of the present application provides a server residual value evaluation device, which may be a server or a chip applied to a server. Figure 5 FIG. 1 shows a schematic block diagram of functional modules of a server residual value evaluation device according to an exemplary embodiment of the present application. Figure 5 As shown, the server residual value evaluation device 500 includes:

[0091] The acquisition module 501 is configured to acquire a first computing power parameter value of a reference server in a target unit time, and a second computing power parameter value of a target server to be evaluated in a target unit time, wherein an initial service time of the target server is earlier than an initial service time of the reference server;

[0092] A determination module 502 is configured to determine a target computing power ratio between the reference server and the target server in a target unit time based on the first computing power parameter value and the second computing power parameter value;

[0093] The evaluation module 503 is configured to obtain the residual value of the target server relative to the reference server in the target unit time based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in the target unit time, and the residual value evaluation model, wherein the residual value evaluation model is determined based on the same relationship between the usage cost ratio and the computing power ratio between the reference server and the target server under the same computing power requirements.

[0094] Optionally, the evaluation module 503 is configured to:

[0095] According to the model parameter values ​​of the computing power value model constructed in the current modeling cycle, the original residual value evaluation model is updated to obtain the target residual value evaluation model, wherein the computing power value model is an exponentially decreasing model of the unit computing power value of the reference server and the target server and time;

[0096] The target unit time, the first life span of the reference server, the service time of the target server in the target unit time and the second life span are input into the target residual value evaluation model to obtain the residual value of the target server relative to the reference server in the target unit time.

[0097] Optional, such as Figure 5 As shown, the server residual value evaluation device 500 further includes a construction module 504 configured to:

[0098] Obtain a first device parameter set of a reference server and a second device parameter set of a target server to be evaluated, wherein the first device parameter set includes a first sample computing power parameter value and a first sample value index value of the reference server in multiple historical unit times, and the second device parameter set includes a second sample computing power parameter value and a second sample value index value of the target server in multiple historical unit times;

[0099] Based on the first sample computing power parameter value of each historical unit time, determine the first sample computing power value of the reference server at each historical unit time, and based on the second sample computing power parameter value of each historical unit time, determine the second sample computing power value of the target server at each historical unit time;

[0100] Determine the ratio of the first sample computing power value and the first sample value index value for each historical unit time, and obtain the first sample unit computing power value of the reference server for each historical unit time; and determine the ratio of the second sample computing power value and the second sample value index value for each historical unit time, and obtain the second sample unit computing power value of the target server for each historical unit time;

[0101] Based on the first sample unit computing power and the second sample unit computing power value of each historical unit time, a parameter prediction model is trained to obtain a target model parameter value, and the target model parameter value is introduced into an exponentially decreasing model to construct the computing power value model.

[0102] Optionally, the construction module 504 is configured to:

[0103] The first sample unit computing power value and the second sample unit computing power value of each historical unit time are respectively determined as the sample unit computing power value, and a sample unit computing power value set is obtained;

[0104] For each sample unit computing power value in the sample unit computing power value set, input the sample unit computing power value into the parameter prediction model to be trained to obtain a prediction model parameter value;

[0105] Determine the predicted value of sample unit computing power based on the prediction model parameter value and the exponential decline model;

[0106] Input the sample unit computing power value and the sample unit computing power predicted value into the loss function to obtain the loss function value;

[0107] If the loss function value is less than or equal to the loss function threshold, the prediction model parameter value is determined as the target model parameter value.

[0108] Optional, such as Figure 5 As shown, the server residual value evaluation device 500 further includes an updating module 505 configured to:

[0109] In the next modeling cycle, obtaining a first updated device parameter set of the reference server and a second updated device parameter set of the target server;

[0110] Based on the first updated device parameter set and the second updated device parameter set, an updated computing power value model is determined.

[0111] Optionally, the first computing power parameter value includes values ​​of multiple computing power parameters, the second computing power parameter value includes values ​​of multiple computing power parameters, and the determining module 502 is configured to:

[0112] Determine the product of multiple first computing power parameter values ​​to obtain a first computing power value of the reference server in a target unit time;

[0113] Determine the product of multiple second computing power parameter values ​​to obtain the second computing power value of the target server in the target unit time;

[0114] The ratio of the first computing power value to the second computing power value is determined as a target computing power ratio between the reference server and the target server in a target unit time.

[0115] Optionally, the determining module 502 is configured to:

[0116] The product of the number of CPU cores, the main frequency of a single core, and the floating-point calculation value of a single CPU cycle of the reference server in the target unit time is determined as the first computing power value of the reference server in the target unit time.

[0117] The exemplary embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program that can be executed by the at least one processor, and the computer program is used to cause the electronic device to perform the method according to the embodiment of the present application when executed by the at least one processor.

[0118] The exemplary embodiment of the present application further provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform a method according to an embodiment of the present application.

[0119] like Figure 6 As shown, the exemplary embodiment of the present application further provides a computer program product 600, including a computer program 601, wherein when the computer program is executed by a processor of a computer, it is used to enable the computer to execute the method according to the embodiment of the present application.

[0120] refer to Figure 7 , the structural block diagram of the electronic device 700 that can be used as the terminal device of the present application will now be described, which is an example of the hardware device that can be applied to various aspects of the present application. The electronic device is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only used as examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0121] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0122] A plurality of components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 may be any type of device capable of inputting information to the electronic device 700, and the input unit 706 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 707 may be any type of device capable of presenting information, and may include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 708 may include but is not limited to a disk, an optical disk. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0123] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above. For example, in some embodiments, the method of the embodiment of the present application may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 709. In some embodiments, the computing unit 701 may be configured to perform the method of the embodiment of the present application by any other appropriate means (e.g., by means of firmware).

[0124] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0125] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0126] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0127] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0128] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0129] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present application is executed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user device or other programmable device. The computer program or instruction may 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 program or instruction may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, for example, a floppy disk, a hard disk, or a tape; it may also be an optical medium, for example, a digital video disc (DVD); it may also be a semiconductor medium, for example, a solid state drive (SSD).

[0130] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for evaluating the residual value of a server, characterized in that: include: Obtaining a first computing power parameter value of a reference server in a target unit time, and a second computing power parameter value of a target server to be evaluated in a target unit time, wherein an initial service time of the target server is earlier than an initial service time of the reference server; Determine a target computing power ratio between the reference server and the target server in a target unit time based on the first computing power parameter value and the second computing power parameter value; Based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in the target unit time, and the residual value evaluation model, the residual value of the target server relative to the reference server in the target unit time is obtained, wherein the residual value evaluation model is determined based on the same relationship between the usage cost ratio and the computing power ratio between the reference server and the target server under the same computing power requirements.

2. The server residual value evaluation method according to claim 1, characterized in that: The method of obtaining the residual value of the target server relative to the reference server in the target unit time based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in the target unit time, and the residual value evaluation model includes: According to the model parameter values ​​of the computing power value model constructed in the current modeling cycle, the original residual value evaluation model is updated to obtain the target residual value evaluation model, wherein the computing power value model is an exponentially decreasing model of the unit computing power value of the reference server and the target server and time; The target unit time, the first life span of the reference server, the service time of the target server in the target unit time and the second life span are input into the target residual value evaluation model to obtain the residual value of the target server relative to the reference server in the target unit time.

3. The server residual value evaluation method according to claim 2, characterized in that: The method further comprises: Obtain a first device parameter set of a reference server and a second device parameter set of a target server to be evaluated, wherein the first device parameter set includes a first sample computing power parameter value and a first sample value index value of the reference server in multiple historical unit times, and the second device parameter set includes a second sample computing power parameter value and a second sample value index value of the target server in multiple historical unit times; Based on the first sample computing power parameter value of each historical unit time, determine the first sample computing power value of the reference server at each historical unit time, and based on the second sample computing power parameter value of each historical unit time, determine the second sample computing power value of the target server at each historical unit time; Determine the ratio of the first sample computing power value and the first sample value index value for each historical unit time, and obtain the first sample unit computing power value of the reference server for each historical unit time; and determine the ratio of the second sample computing power value and the second sample value index value for each historical unit time, and obtain the second sample unit computing power value of the target server for each historical unit time; Based on the first sample unit computing power value and the second sample unit computing power value of each historical unit time, a parameter prediction model is trained to obtain a target model parameter value, and the target model parameter value is introduced into an exponentially decreasing model to construct the computing power value model.

4. The server residual value evaluation method according to claim 3, characterized in that: The training of the parameter prediction model based on the first sample unit computing power value and the second sample unit computing power value of each historical unit time to obtain the target model parameter value includes: The first sample unit computing power value and the second sample unit computing power value of each historical unit time are respectively determined as the sample unit computing power value, and a sample unit computing power value set is obtained; For each sample unit computing power value in the sample unit computing power value set, input the sample unit computing power value into the parameter prediction model to be trained to obtain a prediction model parameter value; Determine the predicted value of sample unit computing power based on the prediction model parameter value and the exponential decline model; Input the sample unit computing power value and the sample unit computing power predicted value into the loss function to obtain the loss function value; If the loss function value is less than or equal to the loss function threshold, the prediction model parameter value is determined as the target model parameter value.

5. The server residual value evaluation method according to claim 3, characterized in that: The method further comprises: In the next modeling cycle, obtaining a first updated device parameter set of the reference server and a second updated device parameter set of the target server; Based on the first updated device parameter set and the second updated device parameter set, an updated computing power value model is determined.

6. The server residual value evaluation method according to claim 1, characterized in that: The first computing power parameter value includes values ​​of multiple computing power parameters, the second computing power parameter value includes values ​​of multiple computing power parameters, and determining a target computing power ratio of the reference server to the target server in a target unit time based on the first computing power parameter value and the second computing power parameter value includes: Determine the product of multiple first computing power parameter values ​​to obtain a first computing power value of the reference server in a target unit time; Determine the product of multiple second computing power parameter values ​​to obtain the second computing power value of the target server in the target unit time; The ratio of the first computing power value to the second computing power value is determined as a target computing power ratio between the reference server and the target server in a target unit time.

7. The server residual value evaluation method according to claim 5, characterized in that: The determining the product of the plurality of first computing power parameter values ​​to obtain the first computing power value of the reference server in the target unit time includes: The product of the number of CPU cores, the main frequency of a single core, and the floating-point calculation value of a single CPU cycle of the reference server in the target unit time is determined as the first computing power value of the reference server in the target unit time.

8. A server residual value evaluation device, characterized in that: include: An acquisition module is configured to acquire a first computing power parameter value of a reference server in a target unit time, and a second computing power parameter value of a target server to be evaluated in a target unit time, wherein an initial service time of the target server is earlier than an initial service time of the reference server; A determination module, configured to determine a target computing power ratio between the reference server and the target server in a target unit time based on the first computing power parameter value and the second computing power parameter value; The evaluation module is configured to obtain the residual value of the target server relative to the reference server in the target unit time based on the target computing power ratio, the first life span of the reference server, the second life span of the target server, the service time of the target server in the target unit time, and a residual value evaluation model, wherein the residual value evaluation model is determined based on the same relationship between the usage cost ratio and the computing power ratio between the reference server and the target server under the same computing power requirements.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the server residual value evaluation method described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the server residual value evaluation method described in any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the server residual value evaluation method described in any one of claims 1 to 7 is implemented.

Images