Topportunity recommendation for server deactivation

Abstract

The present disclosure provides methods and apparatus for providing opportunity recommendations for server deactivation in a cloud service platform. Multi-modal data associated with a deactivation decision made to a target server in the cloud service platform may be obtained. A maintenance cost curve for the target server and at least one of a server added value curve for the target server and a replacement server cost line for a replacement server may be generated based on the multi-modal data. A deactivation opportunity recommendation for the target server may be determined based on the maintenance cost curve and at least one of the server added value curve and the replacement server cost line.

Description

Background Art

[0001] The cloud service platform can provide users with various cloud services. Generally, the cloud service platform includes multiple data centers, and each data center includes a large number of servers. The servers in the cloud service platform provide various resources for cloud services, such as storage resources, computing resources, etc. In order to ensure the stability of cloud services, it is necessary to manage the servers in the cloud service platform in a systematic and intelligent manner. Summary of the invention

[0002] This Summary is provided to introduce a group of concepts that will be further described in the following Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

[0003] Embodiments of the present disclosure propose methods and apparatus for providing a recommendation for a timing of server decommissioning in a cloud service platform. Multimodal data associated with a decommissioning decision made for a target server in the cloud service platform may be obtained. A maintenance cost curve for the target server and at least one of the following items: a server value-added curve for the target server and a replacement server cost line for a replacement server may be generated based on the multimodal data. A recommendation for a decommissioning timing of the target server may be determined based on the maintenance cost curve and at least one of the server value-added curve and the replacement server cost line.

[0004] It should be noted that one or more of the above aspects include the features specifically pointed out in the following detailed description and claims. The following description and drawings set forth in detail certain illustrative features of the one or more aspects. These features are merely indicative of the various ways in which the principles of various aspects may be implemented, and the present disclosure is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] The disclosed aspects will be described below in conjunction with the accompanying drawings, which are provided to illustrate rather than limit the disclosed aspects.

[0006] Figure 1 An exemplary process for providing timing recommendations for server deactivation in a cloud service platform according to an embodiment is shown.

[0007] Figure 2 An exemplary server value-added curve, an exemplary maintenance cost curve, and an exemplary replacement server cost line are shown, according to an embodiment.

[0008] Figure 3 An exemplary deactivation opportunity decision mechanism according to an embodiment is shown.

[0009] Figure 4 An exemplary deactivation opportunity decision mechanism according to an embodiment is shown.

[0010] Figure 5 An exemplary deactivation opportunity decision mechanism according to an embodiment is shown.

[0011] Figure 6 An exemplary deactivation opportunity decision mechanism according to an embodiment is shown.

[0012] Figure 7 A flow chart of an exemplary method for providing timing recommendations for server deactivation in a cloud service platform according to an embodiment is shown.

[0013] Figure 8 An exemplary apparatus for providing a recommendation for timing of server deactivation in a cloud service platform according to an embodiment is shown.

[0014] Fig. 9 An exemplary apparatus for providing a recommendation for timing of server deactivation in a cloud service platform according to an embodiment is shown. DETAILED DESCRIPTION

[0015] The present disclosure will now be discussed with reference to several exemplary embodiments. It should be understood that these embodiments are merely discussed to enable those skilled in the art to better understand and thereby implement examples of the present disclosure, and do not imply any limitation on the scope of the present disclosure.

[0016] In order to ensure the normal function and performance of servers in the cloud service platform, existing server management relies on the predefined life of the server. The predefined life of the server may refer to a period of time during which the function and performance of the server can be kept in good condition by various means. For example, the predetermined life of the server may be a warranty period, during which the provider of the server can replace components in the server free of charge to ensure the normal function and performance of the server. Typically, once the predefined life of the server expires, the server will be decommissioned. However, the server may still be healthy at the end of the predefined life, for example, the server is still able to provide normal storage resources, computing resources, etc. In this case, decommissioning the server at the end of the predefined life will result in waste from a cost-effectiveness perspective or from a data center sustainability perspective.

[0017] In view of the above-mentioned server deactivation problem, the existing solution is to find a suitable time period for server deactivation based on the capital expenditure cost curve and the maintenance cost curve. The capital expenditure cost curve represents the dynamic value of the server in a certain time period, while the maintenance cost curve represents the dynamic cost that needs to be paid for the server in the time period. Both the capital expenditure cost curve and the maintenance cost curve are mathematically defined as continuous functions, and the appropriate time period for server deactivation is determined based on the analytical solutions of these two continuous functions. However, in practice, it is difficult to find or define such continuous functions for the capital expenditure cost curve and the maintenance cost curve. For example, due to uncertain factors such as server failures, the degree of server damage, and the operating environment of the server, it is difficult to find a continuous function for the maintenance cost curve. Accordingly, it is difficult to obtain the desired analytical solution from the capital expenditure cost curve and the maintenance cost curve, and thus it is difficult to find a correct and appropriate time period for server deactivation.

[0018] The embodiments of the present disclosure provide an effective way to help administrators of a cloud service platform make server decommissioning decisions. The embodiments of the present disclosure can provide effective and helpful server decommissioning timing recommendations in a cloud service platform. Compared with the above-mentioned existing methods, the embodiments of the present disclosure do not adopt the capital expenditure cost curve involved in the existing methods, but use a maintenance cost curve based on a discrete function instead of the maintenance cost curve based on a continuous function involved in the existing methods.

[0019] The embodiments of the present disclosure can find the appropriate time to deactivate a server by comparing the server added value, maintenance cost, and server replacement cost. For example, the embodiments of the present disclosure can use a server added value curve, a maintenance cost curve, a server replacement cost line, etc. to determine the appropriate deactivation time. The server added value function, the maintenance cost function, and the server replacement cost function are respectively defined to generate a server added value curve, a maintenance cost curve, and a server replacement cost line based on multimodal data. Multiple types or levels of deactivation timing can be recommended based on multiple types of deactivation timing decision mechanisms, so that different actions can be taken on the server at different times. The embodiments of the present disclosure can obtain numerical solutions from the server added value curve, the maintenance cost curve, and the server replacement cost line, which is more practical than seeking analytical solutions in existing methods.

[0020] Through the embodiments of the present disclosure, reasonable server deactivation timing recommendations can be provided, so that even if the server in the cloud service platform exceeds the predetermined life span, it can still be deployed for providing cloud services, and at the same time the function and performance of the server can still be in a healthy state. Accordingly, the cost of server deployment in the cloud service platform can be effectively and significantly reduced or saved.

[0021] Figure 1 An exemplary process 100 for providing a recommendation for a timing of server deactivation in a cloud service platform according to an embodiment is shown. Process 100 may be performed to provide a recommendation for a timing of server deactivation for a specific server or any one of multiple servers of the same type or configuration in the cloud service platform. Accordingly, the deactivation timing recommendation generated by process 100 may be used to decide whether to deactivate a specific server or multiple servers of the same type or configuration. In the following, a specific server or multiple servers of the same type or configuration may be referred to as a target server.

[0022] At 110, multimodal data associated with a deactivation decision made for a target server in the cloud service platform is obtained. The multimodal data may be obtained from various databases storing information related to the operation, management, maintenance, etc. of the server in the cloud service platform. Embodiments of the present disclosure are not limited to any specific method for obtaining multimodal data.

[0023] The multimodal data may include various types of data or information that may be used to decide whether to deactivate the target server.

[0024] The multimodal data may include target server capital expenditure information. The target server capital expenditure information indicates the capital expenditure of the target server paid once for acquiring the target server.

[0025] The multimodal data may include replacement server capital expenditure information. The target server capital expenditure information indicates the capital expenditure of the replacement server paid once to obtain the replacement server. Herein, the replacement server refers to a server used to replace the target server if the target server is deactivated.

[0026] The multimodal data may include parameter information of the target server and parameter information of the replacement server. The parameter information indicates the size of the server's parameter, where the parameter may be, for example, storage space size, computing power, etc. Taking the parameter as storage space size as an example, the parameter information of the target server refers to the storage space size provided by the target server, and the parameter information of the replacement server refers to the storage space size provided by the replacement server.

[0027] The multimodal data may include service life information and offline duration information. In one embodiment, the service life information and offline duration information may be obtained from the historical data of a reference server corresponding to the target server. The reference server may be of the same type or configuration as the target server, and therefore the historical data of these reference servers may be regarded as data associated with the target server and used to decide whether to deactivate the target server. Typically, due to routine inspections, fault recovery, component replacement, etc., a server may periodically or occasionally have offline events. The cloud service platform may record various types of information related to these offline events, such as service life information, offline duration information, etc. The service life information indicates the service life of the server when the offline event occurs, wherein the service life is calculated from the time the server is deployed to the cloud service platform for operation. The offline duration information indicates the length of time the offline event lasts, for example in hours.

[0028] The multimodal data may include hosting cost information. The hosting cost information indicates the cost per unit time, such as per hour, of hosting a server in a data center.

[0029] The multimodal data may include service life information, replacement component information, and component price information. In one embodiment, the service life information, replacement component information, and component price information may be obtained from historical data of a reference server corresponding to the target server. A server may experience a component replacement event, in which a poorly performing component in the server may be replaced with a new replacement component. The cloud service platform may record various types of information related to such component replacement events, such as service life information, replacement component information, component price information, etc. The service life information indicates the service life of the server when the component replacement event occurs. The replacement component information indicates what component is used to replace the original component in the replacement component information event, and the component price information indicates the price of the replacement component.

[0030] The multimodal data may include predefined lifespan information. The predefined lifespan information indicates a predefined lifespan set for the target server or its reference server.

[0031] It should be understood that the multimodal data obtained at 110 may include any one or more types of the exemplary information described above, and may also include any other types of information associated with a decommissioning decision made for a target server.

[0032] According to an embodiment of the present disclosure, the obtained multimodal data can be used to generate a server value-added curve of the target server, a maintenance cost curve of the target server, and a replacement server cost line of the replacement server. For example, a server value-added function, a maintenance cost function, and a replacement server cost function can be established based on the multimodal data, and used to generate a server value-added curve, a maintenance cost curve, and a replacement server cost line.

[0033] At 120, a server value-added function may be established. The server value-added function may characterize the added value due to the extended period of use of the target server. The server value-added calculated by the server value-added function may reflect how much cost may be saved. Here, the extended period of use is referred to as a reference time span. The server value-added function may be established using depreciation differences. Depreciation differences refer to the difference between the original depreciation calculated based on the useful life of the target server and the reference depreciation calculated based on the useful life and the reference time span. The target server capital expenditure information included in the multimodal data may be used to calculate the original depreciation and the reference depreciation. For example, the server value-added function may be defined as:

[0034]

[0035] Among them, f(x,n) is the server added value function, x represents the service life of the target server, n represents the reference time span, C1 represents the capital expenditure of the target server, represents the original depreciation of the target server at age x, and It represents the reference depreciation of the target server at the age of x+n. The defined server value-added function is a continuous function.

[0036] It should be understood that the above formula (1) is only an example for defining the server value-added function. The embodiments of the present disclosure may also use any other method to define the server value-added function. For example, the linear depreciation calculation method may not be used. and Instead of using the original depreciation and reference depreciation method, any other nonlinear depreciation calculation method may be used to calculate the original depreciation and reference depreciation. The embodiments of the present disclosure are not limited to any specific method for defining the server value-added function.

[0037] At 130, a server value-added curve may be generated according to the established server value-added function. For example, a server value-added curve may be drawn according to the server value-added function, wherein the X-axis represents the age of the target server and the Y-axis represents the added value of the target server.

[0038] At 140, a maintenance cost function may be established. The maintenance cost function may characterize the maintenance cost due to server maintenance events, such as offline events, component replacement events, etc. The maintenance cost may reflect how much money needs to be paid for the maintenance event. The maintenance cost function may be established using offline waste costs and / or component replacement costs calculated over a reference time span.

[0039] In one aspect, an offline waste cost function may be defined for calculating the offline waste cost within a reference time span. The offline waste cost function may calculate the offline waste cost within the reference time span based on at least the service life information, offline duration information, hosting cost information, etc. included in the multimodal data. For example, the offline waste cost function may be defined as:

[0040] w(x,n)=∑ n (hc*h(x)) Formula (2)

[0041] Wherein, w(x, n) is an offline waste cost function, x represents the service life of the server, n represents the reference time span, hc represents the hosting cost, and h(x) represents the offline duration at year x. By formula (2), the offline waste cost of each year from year x to year x+n is calculated respectively, and the offline waste cost is accumulated within the reference time span n, so as to obtain the total offline waste cost within the reference time span n. It should be understood that the above formula (2) is only an example for defining an offline waste cost function, and the embodiments of the present disclosure are not limited to any specific method for defining an offline waste cost function.

[0042] On the other hand, a component replacement cost function may be defined for calculating the component replacement cost within a reference time span. The component replacement cost function may calculate the component replacement cost within a reference time span based at least on the service life information, replacement component information, component price information, etc. in the multimodal data. For example, the component replacement cost function may be expressed as r(x, n, o, p), where x represents the service life of the server, n represents the reference time span, o represents the replacement component, and p represents the price of the replacement component. The component replacement cost function may calculate the total cost of all replacement components used within the reference time span. It should be understood that the embodiments of the present disclosure are not limited to any specific method for defining a component replacement cost function.

[0043] In one embodiment, the maintenance cost function may be defined as:

[0044]

[0045] Among them, m(x, n) is the maintenance cost function, w(x, n) is the offline waste cost function, r(x, n, o, p) is the component replacement cost function, and T represents the predefined life.

[0046] According to formula (3), when the service life x of the target server does not exceed the predefined life T, the maintenance cost function can be based on the offline waste cost function w(x, n). When the service life x of the target server exceeds the predefined life T, the maintenance cost function can be based on both the offline waste cost function w(x, n) and the component replacement cost function r(x, n, o, p). In some scenarios, the calculation methods of maintenance costs within the predefined life and outside the predefined life may be different from each other. Taking the predefined life as the warranty period as an example, if it is promised to replace components free of charge during the warranty period, the component replacement cost can only be considered after the warranty period ends, and the component replacement cost does not need to be considered during the warranty period, as shown in formula (3).

[0047] The defined maintenance cost function is a discrete function, and the maintenance cost is defined as a random variable that changes over time. The maintenance cost can be calculated using at least historical data of a reference server corresponding to the target server in the multimodal data, where the historical data can be regarded as a series of discrete data items. Therefore, the maintenance cost function can calculate multiple discrete maintenance costs based on discrete historical data.

[0048] It should be understood that the above formula (3) is only an example for defining a maintenance cost function. Embodiments of the present disclosure may cover various methods for defining a maintenance cost function. For example, in addition to the offline waste cost function and the component replacement cost function, a maintenance cost function may be further established based on any other factors that cause certain costs within a reference time span, such as the labor costs involved in maintenance, etc. For example, a maintenance cost function may be established without adopting a predetermined life span, and therefore the same calculation method may be applied to calculate the maintenance costs within and beyond the predetermined life span. For example, a maintenance cost function may also be defined using any one of the offline waste cost function and the component replacement cost function, without using both the offline waste cost function and the component replacement cost function to define the maintenance cost function.

[0049] At 150, a maintenance cost curve may be generated based on the established maintenance cost function. In one embodiment, the maintenance cost function may first be used to determine a plurality of discrete points, wherein the plurality of discrete points correspond to a plurality of discrete maintenance costs calculated by the maintenance cost function based on discrete historical data. Then, a fitting process may be performed on the plurality of discrete points to form a maintenance cost curve, wherein the x-axis represents the age of the server and the y-axis represents the maintenance cost.

[0050] At 160, a replacement server cost function may be established. The replacement server cost function may characterize the cost incurred by replacing the target server with the replacement server. The replacement server cost calculated by the replacement server cost function is an indicator of the cost that should be paid for the server replacement. The replacement server cost function may be established by at least performing parameter normalization on the capital expenditure of the replacement server. The replacement server cost may be calculated by the replacement server cost function based on at least the replacement server capital expenditure information, the parameter information of the target server, and the parameter information of the replacement server included in the multimodal data. For example, the replacement server cost function may be defined as:

[0051]

[0052] Among them, γ is the cost function of replacing the server, C2 represents the capital expenditure of replacing the server, S2 represents the parameter information of the replacement server, and S1 represents the parameter information of the target server. represents the cost per parameter unit to be paid for replacing the server, and The product of S2 and S1 represents the cost of replacing the server to achieve the target server's parameters, i.e., the replacement server cost. By introducing S2 and S1 into the replacement server cost function, the replacement server capital expenditure can be normalized, so that the replacement server cost obtained is more reasonable and comparable. Taking the parameter corresponding to the storage space size as an example, S2 represents the storage space size of the replacement server, and S1 represents the storage space size of the target server. represents the cost per storage unit to replace the server, and The product of S1 and S2 represents the cost of replacing the server to reach the storage space size of the target server. The defined replacement server cost function can generate a constant γ as the replacement server cost.

[0053] It should be understood that the above formula (4) is only an example for defining a replacement server cost function. Embodiments of the present disclosure are not limited to any specific method for defining a replacement server cost function.

[0054] At 170, a replacement server cost line may be generated based on the established replacement server cost function. For example, a replacement server cost line may be plotted based on a constant γ calculated by the replacement server cost function, where the X-axis represents the age of the target server and the Y-axis represents the replacement server cost of the replacement server.

[0055] At 180, a decommissioning timing decision mechanism may be applied based on the server value-added curve, the maintenance cost curve, and the replacement server cost line to determine a decommissioning timing recommendation 190 for the target server. The decommissioning timing decision mechanism may determine the decommissioning timing recommendation 190 by comparing the server value-added curve, the maintenance cost curve, and the replacement server cost line with the server value-added curve, the maintenance cost curve, and the replacement server cost line. The embodiments of the present disclosure propose various types of decommissioning timing decision mechanisms for determining different types or levels of decommissioning timings, which will be described later in conjunction with Figures 3 to 6 Discuss it further.

[0056] It should be understood that although the server value-added curve, the maintenance cost curve, and the replacement server cost line are all used to determine the decommissioning timing recommendation in process 100, depending on different decommissioning timing decision mechanisms, only two of them may be used, such as only using the server value-added curve and the maintenance cost curve, or only using the maintenance cost curve and the replacement server cost line to determine the decommissioning timing recommendation. Therefore, process 100 can be changed to include only those steps related to a specific timing decision mechanism.

[0057] In addition, it should be understood that the reference time span n involved in the server value-added function and the maintenance cost function can be effectively used to unify the server value-added calculated by the server value-added function and the maintenance cost calculated by the maintenance cost function into the same statistical area, thereby facilitating the comparison of the server value-added and the maintenance cost by using the server value-added curve and the maintenance cost curve. In addition, since at least the maintenance cost curve is based on a discrete function (i.e., the maintenance cost function), the process of determining the deactivation timing based on the maintenance cost curve and at least one of the server value-added curve and the replacement server cost line can be regarded as a process of finding a numerical solution that can correctly reflect the deactivation timing.

[0058] Figure 2 An exemplary server value-added curve, an exemplary maintenance cost curve, and an exemplary replacement server cost line are shown, according to an embodiment.

[0059] exist Figure 2 , an exemplary server added value curve 210, an exemplary maintenance cost curve 220, and an exemplary replacement server cost line 230 are placed in the same coordinate system, wherein the X-axis represents the useful life of the target server, and the Y-axis represents various types of value or cost. For example, for the server added value curve 210, the maintenance cost curve 220, and the replacement server cost line 230, the Y-axis may represent the added value of the target server, the maintenance cost, and the replacement server cost of the replacement server, respectively.

[0060] Server value-added curve 210 is a curve generated according to a continuous server value-added function. Maintenance cost curve 220 is a curve generated by fitting discrete points determined by a discrete maintenance cost function, such as points 221 to 226. Replacement server cost line 230 is a line with a constant value γ on the Y axis, where γ is calculated by the replacement server cost function.

[0061] like Figure 2 As shown, there is an intersection 202 between server added value curve 210 and maintenance cost curve 220, and there is an intersection 204 between maintenance cost curve 220 and replacement server cost line 230. Intersection 202 corresponds to time point T1 on the X-axis, and intersection 204 corresponds to time point T2 on the X-axis.

[0062] It should be understood that Figure 2 The server added value curve 210, the maintenance cost curve 220, and the replacement server cost curve 230 in FIG. 2 are merely exemplary, and they may have any other different visual shapes depending on various actual scenarios.

[0063] Figure 3 FIG. 3 shows an exemplary deactivation timing decision mechanism 300 according to an embodiment. Figure 1 An exemplary embodiment of the outage timing decision mechanism applied at 180 in FIG. The outage timing decision mechanism 300 takes the server value-added curve 302 and the maintenance cost curve 304 as input.

[0064] At 310, an intersection between the server value-added curve 302 and the maintenance cost curve 304 is identified. For example, the intersection between the server value-added curve 302 and the maintenance cost curve 304 may be identified at 310. Figure 2 The intersection point 202 in .

[0065] At 320, a first time interval is determined, wherein the first time interval is a time interval that does not exceed the time point corresponding to the intersection point. Figure 2 In the example, the first time interval determined at 320 may be a time interval that does not exceed the time point T1 corresponding to the intersection point 202. In the first time interval, the maintenance cost curve 304 is not higher than the server added value curve 302. For example, Figure 2 In the embodiment, the maintenance cost curve 220 is not higher than the server value-added curve 210 in the first time interval.

[0066] At 330, a second time interval is determined, wherein the second time interval is a time interval beyond the time point corresponding to the intersection point. Figure 1 In the example, the second time interval determined at 330 may be a time interval exceeding the time point T2 corresponding to the intersection point 202. In the second time interval, the maintenance cost curve 304 is higher than the server added value curve 302. For example, Figure 2 In the embodiment of the present invention, the maintenance cost curve 220 is higher than the server value-added curve 210 in the second time interval.

[0067] At 340, the first time interval determined at 320 may be recommended as an unnecessary time interval. The unnecessary time interval may refer to a time interval during which the server is unnecessarily deactivated. For example, during the unnecessary time interval, the maintenance cost is not higher than the server added value, and therefore, from the perspective of cost savings that the server added value can bring, it is unnecessary to deactivate the target server.

[0068] At 350, the second time interval determined at 330 may be recommended as a feasible time interval. The feasible time interval may refer to a time interval within which server deactivation is feasible. For example, within the feasible time interval, the maintenance cost is higher than the server added value, and thus the deactivation of the target server may be performed from the perspective that the server added value cannot bring cost savings.

[0069] It should be understood that all steps and their execution order in the deactivation timing decision mechanism 300 are exemplary, and embodiments of the present disclosure may cover various changes to the deactivation timing decision mechanism 300. In addition, the combination of steps 320, 540, and 330 may be viewed as a process of identifying a first time interval and a second time interval.

[0070] Figure 4 FIG. 4 shows an exemplary deactivation timing decision mechanism 400 according to an embodiment. Figure 1 An exemplary embodiment of the outage timing decision mechanism applied at 180 in FIG. The outage timing decision mechanism 400 takes a maintenance cost curve 402 and a replacement server cost line 404 as input.

[0071] At 410, the intersection between the maintenance cost curve 402 and the replacement server cost line 404 is identified. For example, the intersection between the maintenance cost curve 402 and the replacement server cost line 404 may be identified at 410. Figure 2 The intersection point 204 in .

[0072] At 420, a time interval is determined, wherein the determined time interval is a time interval exceeding the time point corresponding to the intersection point. Figure 2 In the example, the time interval determined at 420 may be a time interval exceeding the time point T2 corresponding to the intersection 204. During the determined time interval, the maintenance cost curve 402 is higher than the replacement server cost line 404. For example, Figure 2 In the embodiment, the maintenance cost curve 220 is higher than the server replacement cost line 230 during a certain time interval.

[0073] At 430, the time interval determined at 420 may be recommended as a necessary time interval. The necessary time interval may refer to a time interval within which server deactivation is necessary. For example, during the necessary time interval, the maintenance cost is higher than the server replacement cost, and therefore, deactivating the target server is necessary from the perspective of cost savings that can be brought about by replacing the server.

[0074] It should be understood that all steps and their execution order in the deactivation timing decision mechanism 400 are exemplary, and embodiments of the present disclosure may cover various changes to the deactivation timing decision mechanism 400. In addition, the combination of steps 410 and 420 may be viewed as a process of identifying a time interval.

[0075] Figure 5 FIG. 5 shows an exemplary deactivation timing decision mechanism 500 according to an embodiment. Figure 1 An exemplary embodiment of the outage timing decision mechanism applied at 180 in FIG. The outage timing decision mechanism 500 takes a server value-added curve 502 , a maintenance cost curve 504 , and a replacement server cost line 506 as inputs.

[0076] At 510, a first intersection between the server value-added curve 502 and the maintenance cost curve 504 is identified. For example, at 510, Figure 2 The intersection point 202 in .

[0077] At 520, a second intersection between the maintenance cost curve 504 and the replacement server cost line 506 is identified. For example, the second intersection between the maintenance cost curve 504 and the replacement server cost line 506 may be identified at 520. Figure 2 The intersection point 204 in .

[0078] At 530, a first time interval is determined, wherein the first time interval is a time interval that does not exceed a first time point corresponding to the first intersection point. Figure 2 In the example, the first time interval determined at 530 may be a time interval that does not exceed the time point T1 corresponding to the intersection point 202. In the first time interval, the maintenance cost curve 504 is not higher than the server added value curve 502. For example, Figure 2 In the first time interval, the maintenance cost curve 220 is not higher than the server added value curve 210.

[0079] At 540, a second time interval is determined, wherein the second time interval is a time interval that exceeds the first time point corresponding to the first intersection point but does not exceed the second time point corresponding to the second intersection point. Figure 2In the example, the second time interval determined at 540 may be a time interval that exceeds the time point T1 corresponding to the intersection point 202 but does not exceed the time point T2 corresponding to the intersection point 204. In the second time interval, the maintenance cost curve 504 is higher than the server added value curve 502 and is not higher than the replacement server cost line 506. For example, Figure 2 In the second time interval, the maintenance cost curve 220 is higher than the server added value curve 210 and is not higher than the server replacement cost line 230.

[0080] At 550, a third time interval is determined, wherein the third time interval is a time interval exceeding the second time point corresponding to the second intersection point. Figure 2 In the example, the third time interval determined at 550 may be a time interval exceeding the time point T2 corresponding to the intersection 204. During the third time interval, the maintenance cost curve 504 is higher than the replacement server cost line 506. For example, Figure 2 In the third time interval, the maintenance cost curve 220 is higher than the server replacement cost line 230.

[0081] At 560, the first time interval determined at 530 may be recommended as an unnecessary time interval in which server deactivation is unnecessary. For example, during the unnecessary time interval, the maintenance cost is not higher than the server added value, and therefore, deactivating the target server is unnecessary from the perspective of cost savings that can be brought about by the server added value.

[0082] At 570, the second time interval determined at 540 may be recommended as the operation time interval. The optional time interval may refer to a time interval within which server deactivation is optional. For example, within the optional time interval, on the one hand, the maintenance cost is higher than the server added value, and thus from the perspective that the server added value cannot bring cost savings, the target server may be deactivated; on the other hand, the maintenance cost is not higher than the server replacement cost, and thus from the perspective that server replacement may bring higher costs, the target server may not be deactivated.

[0083] At 580, the third time interval determined at 550 may be recommended as a necessary time interval during which server deactivation is necessary. For example, during the necessary time interval, the maintenance cost is higher than the server replacement cost, and therefore, deactivating the target server is necessary from the perspective of cost savings that can be brought about by replacing the server.

[0084] It should be understood that all steps in the deactivation timing decision mechanism 500 and their execution order are exemplary, and embodiments of the present disclosure may cover various changes to the deactivation timing decision mechanism 500. In addition, the combination of steps 510, 520, 530, 540, and 550 may be viewed as a process of identifying a first time interval, a second time interval, and a third time interval.

[0085] Figure 6 FIG. 6 is a diagram showing an exemplary deactivation timing decision mechanism 600 according to an embodiment. Figure 1 An exemplary embodiment of the outage timing decision mechanism applied at 180 in FIG. The outage timing decision mechanism 600 takes a server value-added curve 602 , a maintenance cost curve 604 , and a replacement server cost line 606 as inputs.

[0086] At 610, a first intersection between the server value-added curve 602 and the maintenance cost curve 604 is identified. For example, at 610, Figure 2 The intersection point 202 in .

[0087] At 620, a second intersection between the maintenance cost curve 604 and the replacement server cost line 606 is identified. For example, at 620, Figure 2 The intersection point 204 in .

[0088] At 630, a first time point corresponding to the first intersection point may be recommended as a starting time point for deactivating the server. Figure 2 In the example, the time point T1 corresponding to the intersection point 202 may be recommended as the starting time point for server deactivation. The starting time point may indicate that server deactivation is feasible after the starting time point.

[0089] At 640, a second time point corresponding to the second intersection point may be recommended as a mandatory time point for server deactivation. Figure 2 In the example, the time point T2 corresponding to the intersection point 204 may be recommended as a mandatory time point for server deactivation. The mandatory time point may indicate that server deactivation is necessary after the mandatory time point.

[0090] It should be understood that all steps and their execution order in the deactivation timing decision mechanism 600 are exemplary, and embodiments of the present disclosure may cover various changes to the deactivation timing decision mechanism 600. For example, although both the starting time point of server deactivation and the mandatory time point of server deactivation are recommended in the deactivation timing decision mechanism 600, only one of the starting time point and the mandatory time point may be recommended, and accordingly, the deactivation timing decision mechanism 600 may be changed to include only those steps related to the recommended time point.

[0091] Combination of the above Figures 3 to 6 The various types of exemplary deactivation timing decision mechanisms discussed may be combined in any manner, and thus, embodiments of the present disclosure may provide a method for determining the deactivation timing of a Figures 3 to 6 In addition, embodiments of the present disclosure may include any other types of outage timing decision mechanisms that are used to determine outage timing recommendations based on any two or more of the server value-added curve, the maintenance cost curve, and the server replacement cost line.

[0092] Figure 7 A flow chart of an exemplary method 700 for providing server deactivation timing recommendations in a cloud service platform according to an embodiment is shown.

[0093] At 710 , multimodal data associated with a decommissioning decision made for a target server in a cloud service platform can be obtained.

[0094] At 720 , a maintenance cost curve of the target server and at least one of a server added value curve of the target server and a replacement server cost line of the replacement server may be generated based on the multimodal data.

[0095] At 730 , a deactivation timing recommendation of the target server may be determined according to the maintenance cost curve and at least one of the server value-added curve and the server replacement cost line.

[0096] In one embodiment, determining a deactivation timing recommendation may include: identifying a first time interval within which a maintenance cost curve is not higher than a server value-added curve and a second time interval within which the maintenance cost curve is higher than the server value-added curve; recommending the identified first time interval as an unnecessary time interval within which server deactivation is unnecessary; and recommending the identified second time interval as a feasible time interval within which server deactivation is feasible.

[0097] Identifying the first time interval and the second time interval may include: identifying the intersection between the server value-added curve and the maintenance cost curve; determining a time interval that does not exceed the time point corresponding to the intersection as the identified first time interval; and determining a time interval that exceeds the time point as the identified second time interval.

[0098] In one embodiment, determining the deactivation timing recommendation may include: identifying a time interval within which a maintenance cost curve is higher than a server replacement cost line; and recommending the identified time interval as a necessary time interval within which server deactivation is necessary.

[0099] Identifying the time interval may include: identifying an intersection point between the maintenance cost curve and the server replacement cost line; and determining a time interval exceeding a time point corresponding to the intersection point as the identified time interval.

[0100] In one embodiment, determining a deactivation timing recommendation may include: identifying a first time interval within which a maintenance cost curve is not higher than a server value-added curve, a second time interval within which a maintenance cost curve is higher than the server value-added curve and not higher than a server replacement cost line, and a third time interval within which a maintenance cost curve is higher than a server replacement cost line; recommending the identified first time interval as an unnecessary time interval within which server deactivation is unnecessary; recommending the identified second time interval as an optional time interval within which server deactivation is optional; and recommending the identified third time interval as a necessary time interval within which server deactivation is necessary.

[0101] Identifying a first time interval, a second time interval, and a third time interval may include: identifying a first intersection between a server value-added curve and a maintenance cost curve; identifying a second intersection between the maintenance cost curve and a server replacement cost line; determining a time interval that does not exceed a first time point corresponding to the first intersection as the identified first time interval; determining a time interval that exceeds the first time point but does not exceed a second time point corresponding to the second intersection as the identified second time interval; and determining a time interval that exceeds the second time point as the identified third time interval.

[0102] In one embodiment, determining a deactivation timing recommendation may include at least one of the following: identifying a first intersection point between a server value-added curve and a maintenance cost curve, and recommending a first time point corresponding to the first intersection point as a starting time point for server deactivation; and identifying a second intersection point between the maintenance cost curve and a replacement server cost line, and recommending a second time point corresponding to the second intersection point as a mandatory time point for server deactivation.

[0103] In one embodiment, generating a maintenance cost curve and at least one of a server value-added curve and a server replacement cost line may include: generating a server value-added curve based on a server value-added function; generating a maintenance cost curve based on a maintenance cost function; and generating a server replacement cost line based on a server replacement cost function.

[0104] The server value-added function may be established using the depreciation difference between the original depreciation calculated based on the useful life of the target server and the reference depreciation calculated based on the useful life and the reference time span.

[0105] The original depreciation and the reference depreciation may be further calculated based on the target server capital expenditure information included in the multimodal data.

[0106] A maintenance cost function may be established using offline waste costs and / or component replacement costs calculated over a reference time span.

[0107] In the case where the service life of the target server does not exceed the predefined life, the maintenance cost function may be based on the offline waste cost function. In the case where the service life of the target server exceeds the predefined life, the maintenance cost function may be based on both the offline waste cost function and the component replacement cost function.

[0108] The offline waste cost function may calculate the offline waste cost within a reference time span based at least on the service life information, offline duration information, and hosting cost information included in the multimodal data. The component replacement cost function may calculate the component replacement cost within a reference time span based at least on the service life information, replacement component information, and component price information included in the multimodal data.

[0109] The server added value function may be a continuous function. The maintenance cost function may be a discrete function. A maintenance cost curve may be generated by fitting discrete points determined by the maintenance cost function.

[0110] A replacement server cost function may be established by performing at least a parameter normalization on the capital expenditure of the replacement server.

[0111] The replacement server cost function may calculate the replacement server cost based on at least replacement server capital expenditure information included in the multimodal data, parameter information of the target server, and parameter information of the replacement server.

[0112] In one implementation, the multimodal data may include at least historical data of a reference server corresponding to the target server.

[0113] In addition, method 700 may also include any steps / operations for providing a recommendation for timing of server deactivation in a cloud service platform according to the above-described embodiments of the present disclosure.

[0114] Figure 8 An exemplary apparatus 800 for providing timing recommendations for server deactivation in a cloud service platform according to an embodiment is shown.

[0115] The device 800 may include: a multimodal data acquisition module 810, used to obtain multimodal data associated with a decommissioning decision made for a target server in a cloud service platform; a generation module 820, used to generate a maintenance cost curve of the target server and at least one of a server value-added curve of the target server and a replacement server cost line of a replacement server based on the multimodal data; and a recommendation determination module 830, used to determine a decommissioning timing recommendation for the target server based on the maintenance cost curve and at least one of the server value-added curve and the replacement server cost line.

[0116] In addition, the apparatus 800 may further include any other modules for executing any steps / operations in the method for providing a recommendation for timing of server deactivation in a cloud service platform according to the above-described embodiments of the present disclosure.

[0117] Fig. 9 An exemplary apparatus 900 for providing timing recommendations for server deactivation in a cloud service platform according to an embodiment is shown.

[0118] The apparatus 900 includes at least one processor 910. The apparatus 900 also includes a memory 920 connected to the at least one processor 910. The memory 920 stores computer executable instructions, which, when executed, cause the at least one processor 910 to perform any operation in the method for providing a recommendation for timing of server deactivation in a cloud service platform according to the above-mentioned embodiment of the present disclosure.

[0119] An embodiment of the present disclosure provides a computer program product for providing a recommendation for the timing of server deactivation in a cloud service platform. The computer program product may include a computer program, which is executed by at least one processor to perform any steps / operations in the method for providing a recommendation for the timing of server deactivation in a cloud service platform according to the above embodiment of the present disclosure.

[0120] Embodiments of the present disclosure may be embodied in a non-transitory computer-readable medium. The non-transitory computer-readable medium may include instructions that, when executed, cause one or more processors to perform any step / operation in the method for providing a recommendation for timing of server deactivation in a cloud service platform according to the above-mentioned embodiments of the present disclosure.

[0121] It should be understood that all operations in the method described above are merely exemplary, and the present disclosure is not limited to any operation in the method or the order of these operations, but should cover all other equivalent transformations under the same or similar concept.

[0122] In addition, the articles "a" and "an" as used in this specification and the appended claims should generally be construed to mean "one" or "one or more" unless specified otherwise or clear from context to be directed to a singular form.

[0123] It should also be understood that all modules in the above described device can be implemented in various ways. These modules can be implemented as hardware, software, or a combination thereof. In addition, any module in these modules can be further divided into submodules or combined together functionally.

[0124] Processors have been described in conjunction with various devices and methods. These processors can be implemented using electronic hardware, computer software or any combination thereof. Whether these processors are implemented as hardware or software will depend on specific application and the overall design constraints imposed on the system. As an example, the processor provided in this disclosure, any part of the processor or any combination of processors can be implemented as microprocessors, microcontrollers, digital signal processors (DSPs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable processing components configured to perform the various functions described in this disclosure. The function of the processor provided in this disclosure, any part of the processor or any combination of processors can be implemented as software executed by microprocessors, microcontrollers, DSPs or other suitable platforms.

[0125] Software should be broadly considered to mean instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, running threads, processes, functions, etc. Software can reside in a computer-readable medium. A computer-readable medium can include, for example, a memory, which can be, for example, a magnetic storage device (e.g., a hard disk, a floppy disk, a magnetic stripe), an optical disk, a smart card, a flash memory device, a random access memory (RAM), a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a register, or a removable disk. Although the memory is shown as being separate from the processor in the various aspects provided in the present disclosure, the memory can also be located inside the processor (e.g., a cache or a register).

[0126] The above description is provided so that any person skilled in the art can implement the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not intended to be limited to the aspects shown herein. All structural and functional equivalents of the elements of the various aspects described in this disclosure that are known or to be known to those skilled in the art will be covered by the claims.

Claims

1. A method for providing a recommendation on a timing of server deactivation in a cloud service platform, comprising: Obtaining multimodal data associated with a deactivation decision made for a target server in the cloud service platform; generating, based on the multimodal data, a maintenance cost curve of the target server and at least one of a server added value curve of the target server and a replacement server cost line of a replacement server; as well as A deactivation timing recommendation for the target server is determined according to the maintenance cost curve and at least one of the server added value curve and the replacement server cost line.

2. The method according to claim 1, wherein: The determination of the deactivation timing recommendation includes: Identifying a first time interval and a second time interval, wherein the maintenance cost curve is not higher than the server value-added curve within the first time interval, and the maintenance cost curve is higher than the server value-added curve within the second time interval; recommending the identified first time interval as an unnecessary time interval within which server deactivation is unnecessary; and The identified second time interval is recommended as a feasible time interval within which server deactivation is feasible.

3. The method according to claim 2, wherein: The identifying the first time interval and the second time interval includes: identifying an intersection point between the server value-added curve and the maintenance cost curve; determining a time interval not exceeding the time point corresponding to the intersection point as the identified first time interval; and A time interval exceeding the time point is determined as the identified second time interval.

4. The method according to claim 1, wherein: The determination of the deactivation timing recommendation includes: identifying a time interval within which the maintenance cost curve is above the replacement server cost line; and The identified time interval is recommended as a necessary time interval within which server deactivation is necessary.

5. The method according to claim 4, wherein: The identification time interval includes: identifying an intersection between the maintenance cost curve and the replacement server cost line; and A time interval exceeding the time point corresponding to the intersection point is determined as the identified time interval.

6. The method according to claim 1, wherein: The determination of the deactivation timing recommendation includes: Identifying a first time interval, a second time interval, and a third time interval, wherein the maintenance cost curve is not higher than the server value-added curve within the first time interval, the maintenance cost curve is higher than the server value-added curve and not higher than the replacement server cost line within the second time interval, and the maintenance cost curve is higher than the replacement server cost line within the third time interval; recommending the identified first time interval as an unnecessary time interval during which server deactivation is unnecessary; recommending the identified second time interval as an optional time interval within which server deactivation is optional; and The identified third time interval is recommended as a necessary time interval within which server deactivation is necessary.

7. The method according to claim 6, wherein: The identifying the first time interval, the second time interval, and the third time interval includes: identifying a first intersection point between the server value-added curve and the maintenance cost curve; identifying a second intersection point between the maintenance cost curve and the replacement server cost line; determining a time interval not exceeding a first time point corresponding to the first intersection point as an identified first time interval; determining a time interval that exceeds the first time point but does not exceed a second time point corresponding to the second intersection point as an identified second time interval; and A time interval exceeding the second time point is determined as the identified third time interval.

8. The method according to claim 1, wherein: The determining of the deactivation timing recommendation includes at least one of the following: identifying a first intersection point between the server added value curve and the maintenance cost curve, and recommending a first time point corresponding to the first intersection point as a starting time point for deactivating the server; as well as A second intersection point between the maintenance cost curve and the replacement server cost line is identified, and a second time point corresponding to the second intersection point is recommended as a mandatory time point for server deactivation.

9. The method according to claim 1, wherein: Generating at least one of the maintenance cost curve, the server added value curve, and the server replacement cost curve comprises: generating the server added value curve according to the server added value function; generating the maintenance cost curve according to a maintenance cost function; and The replacement server cost line is generated according to a replacement server cost function.

10. The method according to claim 9, wherein: The server value-added function is established using the depreciation difference between the original depreciation calculated based on the useful life of the target server and the reference depreciation calculated based on the useful life and a reference time span.

11. The method according to claim 10, wherein: The original depreciation and the reference depreciation are further calculated based on target server capital expenditure information included in the multimodal data.

12. The method according to claim 9, wherein: The maintenance cost function is established using offline waste costs and / or component replacement costs calculated over a reference time span.

13. The method according to claim 12, wherein: In the case where the service life of the target server does not exceed a predefined lifespan, the maintenance cost function is based on an offline waste cost function, and In a case where the useful life of the target server exceeds the predefined life span, the maintenance cost function is based on both the offline waste cost function and a component replacement cost function.

14. The method according to claim 13, wherein: The offline waste cost function calculates the offline waste cost within the reference time span based on at least the usage age information, offline duration information and hosting cost information included in the multimodal data, and The component replacement cost function calculates the component replacement cost within the reference time span based on at least the service life information, replacement component information and component price information included in the multimodal data.

15. The method according to claim 9, wherein: The server added value function is a continuous function, The maintenance cost function is a discrete function, and The maintenance cost curve is generated by fitting discrete points determined by the maintenance cost function.

16. The method according to claim 9, wherein: The replacement server cost function is established by performing at least a parameter normalization on a capital expenditure of the replacement server.

17. The method according to claim 16, wherein: The replacement server cost function calculates a replacement server cost based on at least replacement server capital expenditure information included in the multimodal data, parameter information of the target server, and parameter information of the replacement server.

18. The method according to claim 1, wherein: The multimodal data includes at least historical data of a reference server corresponding to the target server.

19. A device for providing a recommendation for a time to deactivate a server in a cloud service platform, comprising: at least one processor, and A memory storing computer executable instructions, which, when executed, cause the at least one processor to perform the operations of the method according to any one of claims 1-18.

20. A computer program product for providing a recommendation on timing of server deactivation in a cloud service platform, comprising a computer program, wherein the computer program is executed by at least one processor to perform the operations in the method according to any one of claims 1 to 18.

Images