Device scheduling optimization strategy determination method, apparatus, device, and storage medium

Abstract

The application provides a device scheduling optimization strategy determination method and device, equipment and storage medium, and the method comprises the following steps: obtaining historical maintenance data of at least one target component in each machine room device in a device management system; determining a device health index of the machine room device based on each historical maintenance data; determining a health state of the machine room device based on the device health index; determining a health load index of the machine room device based on the health state and a load rate of the machine room device; determining a device scheduling optimization strategy based on the health load index of each type of all machine room devices, wherein the device scheduling optimization strategy is used to represent a schedulable machine room device in all the machine room devices. The application can improve the accuracy of the determined residual value of the machine room device, so that the scheduling result of the machine room device is more accurate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of device management, and particularly relates to a device scheduling optimization strategy determination method and device, apparatus and storage medium. BACKGROUND

[0002] With the continuous updating and iteration of communication technology, especially with the development of the 5th Generation Mobile Communication Technology (5G) network, a large number of 4G devices need to be updated, and the replaced 4G devices need to be evaluated for residual value, so as to determine whether to directly eliminate or schedule them to other suitable machine rooms for continued use based on the evaluation results.

[0003] In the prior art, the residual value is usually calculated based on the original cost of the machine room device minus the depreciation and estimated disposal fees, so as to evaluate the scheduling of the machine room device according to the calculated residual value.

[0004] However, in actual application, since the actual degree of wear and tear of the machine room device may differ from the depreciation calculated according to the straight-line method or other depreciation methods, the determined residual value may have certain errors, resulting in inaccurate scheduling results of the machine room device. SUMMARY

[0005] The present application provides a device scheduling optimization strategy determination method, device, apparatus and storage medium, to solve the defect that the residual value of the machine room device determined in the prior art has certain errors, resulting in inaccurate scheduling results of the machine room device, and to realize improving the accuracy of determining the residual value of the machine room device, so that the scheduling results of the machine room device are more accurate.

[0006] The present application provides a device scheduling optimization strategy determination method, comprising:

[0007] For each machine room device in the device management system, historical maintenance data of at least one target component in the machine room device is obtained;

[0008] Based on each of the historical maintenance data, a device health index of the machine room device is determined;

[0009] Based on the device health index, a health status of the machine room device is determined;

[0010] Based on the health status and a load rate of the machine room device, a health load index of the machine room device is determined;

[0011] determine a device scheduling optimization strategy for each type of all the equipment rooms based on the health load index of each type of all the equipment rooms, wherein the device scheduling optimization strategy is used to represent schedulable equipment rooms in all the equipment rooms.

[0012] According to the device scheduling optimization strategy determination method provided in the application, the historical maintenance data includes historical maintenance time and historical maintenance cost;

[0013] The method further includes the following steps:

[0014] For each target component in the equipment room, a first weighted relative distance corresponding to the target component is determined based on the maximum maintenance time, the highest maintenance cost, the historical maintenance time of the target component, and the historical maintenance cost of the target component, wherein the maximum maintenance time is the maximum value of the historical maintenance time of all target components of the equipment room, and the highest maintenance cost is the maximum value of the historical maintenance cost of all target components of the equipment room.

[0015] A second weighted relative distance corresponding to the target component is determined based on the minimum maintenance time, the lowest maintenance cost, the historical maintenance time of the target component, and the historical maintenance cost of the target component, wherein the minimum maintenance time is the minimum value of the historical maintenance time of all target components of the equipment room, and the lowest maintenance cost is the minimum value of the historical maintenance cost of all target components of the equipment room.

[0016] A maintenance score of the target component in the equipment room is determined based on the first weighted relative distance and the second weighted relative distance.

[0017] A device health index of the equipment room is determined based on the maintenance score of each target component in the equipment room.

[0018] According to the device scheduling optimization strategy determination method provided in the application, the historical maintenance data further includes historical maintenance times;

[0019] The method further includes the following steps:

[0020] For each target component in the equipment room, an importance weight of the target component is determined based on the maintenance score of the same target component in all equipment rooms of the same type as the equipment room.

[0021] A deterioration degree of the target component is determined based on the historical maintenance times of the target component, the historical maintenance cost, and the sales price of the target component.

[0022] determine a weighted degradation degree of the target component based on the degradation degree of the target component and an importance weight of the target component;

[0023] determine a maximum weighted degradation degree among the weighted degradation degrees of all the target components as a device health index of the machine room equipment.

[0024] According to the device scheduling optimization strategy determination method provided in the present application, the health status of the machine room equipment is determined based on the device health index, which comprises:

[0025] determine a device failure rate of the machine room equipment based on the device health index, a proportionality coefficient and a curvature coefficient, wherein the proportionality coefficient and the curvature coefficient are obtained by fitting based on a number of failed devices and a total number of devices, the number of failed devices is a number of devices that have failed among all machine room equipment of the same type as the machine room equipment within a preset time period, and the total number of devices is a number of all machine room equipment of the same type as the machine room equipment;

[0026] determine the health status of the machine room equipment based on the device failure rate of the machine room equipment.

[0027] According to the device scheduling optimization strategy determination method provided in the present application, the device scheduling optimization strategy is determined based on the health load index of each type of all machine room equipment, which comprises:

[0028] for each type of machine room equipment, construct a first objective function with a minimum health load index of each machine room equipment as a target based on the health load index of each machine room equipment of the type and a number of machine room equipment of the type, and determine schedulable machine room equipment among all machine room equipment of the type based on the first objective function;

[0029] determine the device scheduling optimization strategy based on each type of schedulable machine room equipment.

[0030] According to the device scheduling optimization strategy determination method provided in the present application, the device scheduling optimization strategy is determined based on each type of schedulable machine room equipment, which comprises:

[0031] construct a second objective function with a minimum health load index of all types of machine room equipment in the device management system as a target based on the health load index of each type of schedulable machine room equipment and a number of device types, and determine a target schedulable machine room equipment corresponding to the device management system from each type of schedulable machine room equipment based on the second objective function;

[0032] determine the device scheduling optimization strategy based on the target schedulable machine room equipment corresponding to the device management system.

[0033] The application further provides a device scheduling optimization strategy determination apparatus, comprising:

[0034] An acquisition module is configured to acquire historical maintenance data of at least one target component in each machine room device in a device management system;

[0035] A determination module is configured to determine a device health index of each machine room device based on the historical maintenance data of the machine room device;

[0036] The determination module is further configured to determine a health state of the machine room device based on the device health index;

[0037] The determination module is further configured to determine a health load index of the machine room device based on the health state and a load rate of the machine room device;

[0038] The determination module is further configured to determine a device scheduling optimization strategy based on the health load index of each type of machine room device, wherein the device scheduling optimization strategy is used to represent schedulable machine room devices in all the machine room devices.

[0039] The application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the device scheduling optimization strategy determination method according to any one of the above when executing the program.

[0040] The application further provides a non-transitory computer readable storage medium, which stores a computer program executable by a processor to implement the device scheduling optimization strategy determination method according to any one of the above.

[0041] The application further provides a computer program product, comprising a computer program executable by a processor to implement the device scheduling optimization strategy determination method according to any one of the above.

[0042] The device scheduling optimization strategy determination method, device, equipment and storage medium provided by the application are used for each machine room device in a device management system, historical maintenance data of at least one target component in the machine room device is acquired, the device health index of the machine room device is determined based on each historical maintenance data, the health state of the machine room device is determined based on the device health index, and then the health load index of the machine room device is determined based on the health state and the load rate of the machine room device, so as to determine the device scheduling optimization strategy based on the health load index of all machine room devices of each type, and the device scheduling optimization strategy is used to represent the schedulable machine room device in all machine room devices. Since the health index of the machine room device is determined based on the historical maintenance data of each target component of the machine room device instead of the whole machine room device, the determined health state is more accurate. Further, the health load index determined based on the health state and the load rate of the machine room device can reflect the utilization rate and residual value of the machine room device in real time, so that the estimation of the residual value of the machine room device is more accurate, and the accuracy of the device scheduling optimization strategy determined based on the health load index of all machine room devices of each type is higher. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 One of the flowcharts of the device scheduling optimization strategy determination method provided by the embodiments of the application.

[0045] Figure 2 The second flowchart of the device scheduling optimization strategy determination method provided by the embodiments of the application.

[0046] Figure 3 The structural schematic diagram of the device scheduling optimization strategy determination apparatus provided by the embodiments of the application.

[0047] Figure 4 The physical structure schematic diagram of an electronic device provided by the embodiments of the application. DETAILED DESCRIPTION

[0048] In order to make the purposes, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in conjunction with the accompanying drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0049] At present, if the residual value of the replaced machine room equipment is not estimated accurately, errors will occur in the expected service life of the machine room equipment. If the expected service life is longer than the actual service life, the machine room equipment will be discarded prematurely in the middle of use. If the expected service life is shorter than the actual service life, the machine room equipment can actually still be used but has been discarded. Therefore, how to accurately estimate the residual value of the machine room equipment, so as to evaluate the service life of the machine room equipment and schedule the machine room equipment based on the service life, is very important.

[0050] The existing method of calculating the residual value by deducting the depreciation and the estimated disposal fee from the original cost of the machine room equipment will lead to inaccurate residual value of the machine room equipment, because the actual degree of wear and tear of the machine room equipment may be different from the depreciation calculated according to the straight-line method or other depreciation methods, thereby causing the scheduling result to be not accurate when the residual value is used as a reference for scheduling the machine room equipment.

[0051] Embodiments of the present application consider the above problems and propose a device scheduling optimization strategy determination method. In the method, the historical maintenance data of each target component of each machine room equipment in a device management system can be combined to determine a device health index of each machine room equipment, and then the health state of the machine room equipment can be determined based on the device health index. According to the health state and the load rate of the machine room equipment, a health load index of the machine room equipment can be determined, so as to determine which machine room equipment in all machine room equipment of each type is a schedulable machine room equipment, i.e., which machine room equipment has a larger residual value. Since the health index of the machine room equipment is determined based on the historical maintenance data of each target component of the machine room equipment, rather than the machine room equipment as a whole, the determined health state is more accurate. Further, the health load index determined based on the health state and the load rate of the machine room equipment can reflect the utilization rate and the residual value of the machine room equipment in real time, so that the estimation of the residual value of the machine room equipment is more accurate, and the accuracy of the device scheduling optimization strategy determined based on the health load index of all machine room equipment of each type is higher.

[0052] The following will be described in conjunction with Figure 1 and Figure 2The device scheduling optimization strategy determination method provided by the embodiments of the present application is described. The embodiments of the present application can be applied to the scenario of scheduling devices in a device management system, and can be particularly applied to the scenario of scheduling devices based on the residual value of the replaced machine room equipment by evaluating the residual value of the replaced machine room equipment. The execution subject of the method can be a terminal device, a computer, a server, a server cluster, or a specially designed device scheduling optimization strategy determination device, etc. electronic device, or a device scheduling optimization strategy determination device provided in the electronic device. The device scheduling optimization strategy determination device can be realized by software, hardware, or a combination of both.

[0053] Figure 1 One of the flowcharts of the device scheduling optimization strategy determination method provided by the embodiments of the present application is shown in FIG. 1, which includes the following steps. Figure 1

[0054] Step 101: For each machine room equipment in the device management system, obtain the historical maintenance data of at least one target component in the machine room equipment.

[0055] In this step, the device management system includes a plurality of machine room equipment, which can be the same type of equipment or different types of equipment. The machine room equipment includes a remote radio unit (RRU), an active antenna unit (AAU), or a baseband processing unit (BBU).

[0056] For each machine room equipment, the historical maintenance data of each target component in the machine room equipment can be collected. The relevant data of the machine room equipment can be as shown in Table 1:

[0057] Table 1

[0058]

[0059] According to Table 1, the target component of machine room equipment A is a baseband processing unit (BBU), and the historical maintenance data of the BBU includes a maintenance time of 8 hours and a maintenance cost of 350 yuan.

[0060] The historical maintenance data can be the maintenance data of each target component since the machine room equipment is put into use.

[0061] Step 102: Determine the device health index of the machine room equipment based on the historical maintenance data.

[0062] ​In this step, the equipment health index of the machine room equipment can be evaluated based on the historical maintenance data of each target component of the machine room equipment. The equipment health index of the machine room equipment is determined by comprehensively considering the condition of each target component, and therefore the accuracy of the equipment health index is high.

[0063] Step 103: Determine the health status of the machine room equipment based on the equipment health index.

[0064] In this step, after determining the equipment health index of the machine room equipment, the equipment health index can be converted into a health status, which can be used as a factor for measuring the size of the residual value of the machine room equipment.

[0065] Step 104: Determine the health load index of the machine room equipment based on the health status and the load rate of the machine room equipment.

[0066] In this step, the utilization efficiency of the machine room equipment is no longer simply targeted at improving the equipment load rate, but also considers the real-time health status of the machine room equipment. Therefore, in the embodiments of the present application, the health load index that reflects the utilization efficiency of the machine room equipment under the above requirements is constructed based on the health status of the machine room equipment and the load rate of the machine room equipment. The health load index can be represented by the following formula (1):

[0067] (1)

[0068] wherein, represents the health load index of the machine room equipment, represents the health status of the machine room equipment, and it should be noted that when there are multiple same type of equipment in the equipment management system, the health status needs to be normalized. represents the load rate of the machine room equipment, and the value range of the load rate needs to be mapped within the value range of the health status.

[0069] According to formula (1), it is known that the sum of two non-negative numbers is greater than or equal to the square root of the product of the two numbers, the value is greater than or equal to 1, and only when , the minimum value is 1.

[0070] It should be understood that, when the machine room equipment with a high health degree has a better load rate, is small, and when the machine room equipment with a low health degree has a lower load rate corresponding thereto, is also small. That is, when the The smaller the time, the better the matching of the health status of the machine room equipment and the load rate, so that the health status of the machine room equipment can be matched with the load rate The machine room equipment can be matched with the load rate according to the health degree thereof. The reasonable allocation of the load rate according to the actual health status of the machine room equipment can further optimize the use efficiency of the machine room equipment.

[0071] Step 105: determining a device scheduling optimization strategy based on the health load indexes of all machine room equipment of each type, the device scheduling optimization strategy being used to represent the schedulable machine room equipment in all machine room equipment.

[0072] In this step, the device scheduling optimization strategy is used to represent the residual value or utilization efficiency of all devices in the device management system, and based on the residual value or utilization efficiency of each device, the machine room equipment with high residual value or high utilization efficiency can be subsequently scheduled to other systems or other machine rooms for continuous use. Therefore, the device scheduling optimization strategy can provide effective data support for the retirement or scheduling of devices.

[0073] Since the health load index of each machine room equipment is determined by considering the health status and load rate of the machine room equipment, the residual value or utilization efficiency of the machine room equipment is evaluated from different dimensions when the health load index is used to evaluate the residual value or utilization efficiency of the machine room equipment, so that the residual value or utilization efficiency of the machine room equipment evaluated is more accurate. Thus, the accuracy of the device scheduling optimization strategy determined based on the health load index will be higher.

[0074] The device scheduling optimization strategy determination method provided by the embodiments of the present application is used for each machine room equipment in the device management system. The historical maintenance data of at least one target component in the machine room equipment is obtained, the device health index of the machine room equipment is determined based on each historical maintenance data, the health status of the machine room equipment is determined based on the device health index, and then the health load index of the machine room equipment is determined based on the health status and the load rate of the machine room equipment. Thus, the device scheduling optimization strategy is determined based on the health load indexes of all machine room equipment of each type, and the device scheduling optimization strategy is used to represent the schedulable machine room equipment in all machine room equipment. Since the health index of the machine room equipment is determined based on the historical maintenance data of each target component of the machine room equipment instead of the machine room equipment as a whole, the health status determined is more accurate. Further, the health load index determined based on the health status and the load rate of the machine room equipment can reflect the utilization rate and residual value of the machine room equipment in real time, so that the estimation of the residual value of the machine room equipment is more accurate, and thus the accuracy of the device scheduling optimization strategy determined based on the health load indexes of all machine room equipment of each type is higher.

[0075] Figure 2This is the second flowchart illustrating the method for determining equipment scheduling optimization strategies provided in this application embodiment. Figure 1 Based on the illustrated embodiment, this paper details the specific implementation process of determining the equipment health index of data center equipment based on historical maintenance data, including historical maintenance duration and historical maintenance costs. For example... Figure 2 As shown, the method includes:

[0076] Step 201: For each target component in the computer room equipment, determine the first weighted relative distance corresponding to the target component based on the maximum maintenance time, the highest maintenance cost, the historical maintenance time of the target component, and the historical maintenance cost of the target component.

[0077] Among them, the maximum repair time is the maximum value among the historical repair times of all target components of the data center equipment, and the maximum repair cost is the maximum value among the historical repair costs of all target components of the data center equipment.

[0078] Specifically, for each target component in each computer room, the historical maintenance time and historical maintenance cost of that target component can be pre-processed using standardization. For example, the historical maintenance time can be pre-processed using the following formula (2), and the historical maintenance cost can be pre-processed using the following formula (3):

[0079] (2)

[0080] (3)

[0081] in, This represents the standardized historical maintenance time of the i-th target component in the computer room equipment. This represents the historical maintenance duration of the i-th target component in the computer room equipment, and n represents the total number of target components in the computer room equipment. This represents the standardized historical maintenance cost of the i-th target component in the computer room equipment. This represents the historical maintenance cost of the i-th target component in the computer room equipment.

[0082] For each computer room device, based on the above formulas (2) and (3), the standardized historical maintenance time and standardized historical maintenance cost corresponding to each target component of the computer room device can be determined. From the standardized historical maintenance time and standardized historical maintenance cost corresponding to each of all target components, the largest historical maintenance time is selected as the maximum maintenance time, that is, the optimal solution for maintenance time. The largest historical maintenance cost is selected as the maximum maintenance cost, that is, the optimal solution for maintenance cost.

[0083] Further, the first weighted relative distance corresponding to the target component can be determined based on the following formula (4):

[0084] (4)

[0085] wherein, represents the first weighted relative distance corresponding to the i-th target component, which can also be understood as the first weighted relative distance between the target component and the optimal solution, represents the maximum maintenance time length, represents the highest maintenance cost.

[0086] Step 202: determining the second weighted relative distance corresponding to the target component based on the minimum maintenance time length, the lowest maintenance cost, the historical maintenance time length of the target component, and the historical maintenance cost of the target component.

[0087] wherein, the minimum maintenance time length is the minimum value among the historical maintenance time lengths corresponding to all target components of the machine room equipment, and the lowest maintenance cost is the minimum value among the historical maintenance costs corresponding to all target components of the machine room equipment.

[0088] Specifically, for each machine room equipment, after determining the standardized historical maintenance time length and the standardized historical maintenance cost corresponding to each target component of the machine room equipment based on the above formula (2) and formula (3), the shortest historical maintenance time length can be selected as the minimum maintenance time length, i.e., the worst solution of the maintenance time length, and the lowest historical maintenance cost can be selected as the lowest maintenance cost, i.e., the worst solution of the maintenance cost, from the standardized historical maintenance time lengths and the standardized historical maintenance costs corresponding to all target components.

[0089] Further, the second weighted relative distance corresponding to the target component can be determined based on the following formula (4):

[0090] (4)

[0091] wherein, represents the second weighted relative distance corresponding to the i-th target component, which can also be understood as the second weighted relative distance between the target component and the worst solution, min represents the minimum maintenance time length, represents the lowest maintenance cost.

[0092] Step 203: determining the maintenance score of the target component in the machine room equipment based on the first weighted relative distance and the second weighted relative distance.

[0093] In this step, the first weighted relative distance and the second weighted relative distance Then, the maintenance score of the ith target component in the equipment room can be determined based on the following formula (5) :

[0094] (5)

[0095] wherein, the value range of the maintenance score of the ith target component in the equipment room is 0-1.

[0096] Step 204: determining the equipment health index of the equipment room based on the maintenance scores of the target components in the equipment room.

[0097] In this step, the maintenance scores of each target component in the equipment room can be determined based on the above method, so that the equipment health index of the equipment room can be comprehensively evaluated according to the maintenance scores of the target components.

[0098] For example, in a possible implementation, the historical maintenance data further includes the historical maintenance times, and when the equipment health index of the equipment room is determined based on the maintenance scores of the target components in the equipment room, the following method can be used:

[0099] For each target component in the equipment room, the importance weight of the target component is determined based on the maintenance scores of the same target component in all equipment rooms of the same type as the equipment room, the degradation degree of the target component is determined based on the historical maintenance times, the historical maintenance cost of the target component and the sales price of the target component, the weighted degradation degree of the target component is determined based on the degradation degree of the target component and the importance weight of the target component, and the maximum weighted degradation degree among the weighted degradation degrees of all target components is determined as the equipment health index of the equipment room.

[0100] Specifically, the equipment management system can include multiple devices of the same type as the equipment room, and the target components included in these same type of equipment rooms are the same. It should be understood that based on the method described in the foregoing embodiments, the maintenance scores of each target component of each equipment room can be determined, for the ith target component, the quartile and the three-quarters quantile can be determined based on the maintenance scores of the ith target component contained in all same type of equipment rooms, and the average value of the remaining maintenance scores of the ith target component can be calculated by removing outliers through a box plot, for example, the first quarter of the maintenance scores and the last three-quarters of the maintenance scores can be removed , and the importance weight of the ith target component is determined based on the following formula (6) :

[0101] (6)

[0102] wherein, m represents the number of target components in the equipment room. ​

[0103] For example, if 100 machine room equipment of the same type are included in the machine room management equipment system, each of which includes 4 target components, after determining the maintenance scores of each target component of each machine room equipment, when determining the importance weight of the first target component, the maintenance scores of the first same target component in the 100 machine room equipment can be calculated for the quartile and the three-quarters, and the first 25 maintenance scores and the last 25 maintenance scores are removed, and after calculating the average of the remaining maintenance scores, based on the average, the importance weight of the first target component can be determined according to formula (6).

[0104] It should be understood that for the above 100 machine room equipment, the importance weight of the same target component is the same.

[0105] In addition, since the running state of the machine room equipment is mainly determined by the running state degradation degree of each target component and the importance weight of the target component, it is also necessary to determine the degradation degree of the running state of each target component of each machine room equipment. For example, the degradation degree of the i-th target component can be determined based on the following formula (7) :

[0106] (7)

[0107] wherein, represents the historical maintenance times of the i-th target component, represents the historical maintenance cost of the i-th target component at the k-th time, represents the sales price of the i-th target component.

[0108] The degradation degree of the target component and the importance weight of the target component are weighted to obtain the weighted degradation degree of the target component, and the maximum weighted degradation degree is determined from the weighted degradation degrees of all target components of the machine room equipment, so as to determine the equipment health index of the machine room equipment as the maximum weighted degradation degree.

[0109] Specifically, the equipment health index of the machine room equipment can be determined by the following formula (8) :

[0110] (8)

[0111] In this embodiment, when determining the equipment health index of the machine room equipment, the importance weight of each target component in the machine room equipment is also taken into account, so that the determined equipment health index of the machine room equipment is more focused on the degradation degree of the important target component, so that the determined equipment health index is more suitable for the actual application scenario, and the accuracy of the equipment health index is improved.

[0112] For example, based on the above embodiments, when determining the health state of the equipment room equipment based on the equipment health index, the following method can be used:

[0113] Based on the equipment health index, the proportion coefficient and the curvature coefficient, the equipment failure rate of the equipment room equipment is determined, the proportion coefficient and the curvature coefficient are fitted based on the number of failed equipment and the total number of equipment, the number of failed equipment is the number of equipment that fails in all equipment room equipment of the same type as the equipment room equipment in a preset time period, and the total number of equipment is the number of all equipment room equipment of the same type as the equipment room equipment; based on the equipment failure rate of the equipment room equipment, the health state of the equipment room equipment is determined.

[0114] Specifically, the health degree of the equipment room equipment and the equipment failure rate are complementary to each other, and the equipment failure rate and the equipment health index are usually in an exponential relationship, as shown in formula (9):

[0115] (9)

[0116] wherein, represents the equipment failure rate, represents the equipment health index of the equipment room equipment, and the value range is 1-10, represents the proportion coefficient, represents the curvature coefficient.

[0117] For the proportion coefficient and the curvature coefficient , the historical data of all equipment room equipment of the same type as the equipment room equipment can be used to determine, wherein the all equipment room equipment of the same type as the equipment room equipment includes the equipment room equipment. The historical data includes the number of failed equipment in all equipment room equipment in a preset time period and the number of all equipment room equipment of the same type as the equipment room equipment, and the failure rate in the preset time period is determined based on the number of failed equipment and the number of all equipment room equipment of the same type, and then the proportion coefficient and the curvature coefficient can be fitted based on the following formula (10):

[0118] (10)

[0119] wherein, N represents the number of all equipment room equipment of the same type, C is a preset constant, represents the equipment health index of the gth equipment room equipment.

[0120] For example, after fitting the equipment data of all equipment room equipment of the same type as the equipment room equipment, the proportion coefficient and the curvature coefficient can be obtained, and the proportion coefficient and the curvature coefficient Afterwards, the equipment failure rate of the equipment room equipment in various states can be obtained.

[0121] After the equipment failure rate of the equipment room equipment is determined, in the embodiment, the health status of the equipment room equipment can be determined by taking the complement of the equipment failure rate, for example, the health status of the equipment room equipment can be determined based on the following formula (11):

[0122] (11)

[0123] wherein, represents the health status of the equipment room equipment, represents the equipment failure rate of the equipment room equipment.

[0124] In the embodiment, since the equipment failure rate of the equipment room equipment can be determined based on the historical failure information of all equipment room equipment of the same type, instead of being determined based on the historical failure information of a single equipment room equipment, the result of the determined equipment failure rate is more accurate, so that after the health status of the equipment room equipment is determined based on the equipment failure rate, the accuracy of the health status of the equipment room equipment can be improved.

[0125] For example, on the basis of the above embodiments, when determining the equipment scheduling optimization strategy based on the health load index of all equipment room equipment of each type, for each type of equipment room equipment, a first objective function can be constructed based on the health load index of each equipment room equipment of the type and the number of equipment room equipment in the type, with the minimum health load index of each equipment room equipment as the target, the schedulable equipment room equipment in all equipment room equipment of the type is determined based on the first objective function, and the equipment scheduling optimization strategy is determined based on the schedulable equipment room equipment of each type.

[0126] Specifically, after the health load index of each equipment room equipment is determined, for the entire equipment management system, equipment room equipment of the same type is expected to have a similar index, since when the health load index of a certain equipment room equipment is smaller, the matching between the health status of the equipment room equipment and the equipment load rate is better, therefore, a first objective function can be constructed based on the health load index of each equipment room equipment of each type and the number of equipment room equipment in each type, with the minimum health load index of each equipment room equipment as the target, for example, the constructed first objective function is shown in formula (12):

[0127] (12)

[0128] wherein, d represents the dth type of equipment room equipment, j represents the jth equipment room equipment in the dth type of equipment room equipment with a non-zero load rate, n represents the number of equipment room equipment of the dth type with a non-zero load rate, This refers to the equipment in the d-th type of computer room in the equipment management system. The objective function, For health load index based on multiple different types of data center equipment A definite result This represents the health load index of the j-th data center device in the d-th data center. .

[0129] By solving the first objective function, we can identify the schedulable data center equipment with good health and a good match between load rate and health among all data center equipment of each type. Based on the schedulable data center equipment of each type, we can determine the equipment scheduling optimization strategy. The schedulable data center equipment can also be understood as the data center equipment with high residual value. The equipment scheduling optimization strategy includes scheduling the schedulable data center equipment in the equipment management system to other data centers, or scheduling other schedulable data center equipment to the equipment management system, etc.

[0130] In this embodiment, a first objective function can be constructed based on the health load index of each type of data center equipment and the number of data center equipment in each type, with the goal of minimizing the health load index of each data center equipment. By solving the first objective function, the schedulable data center equipment can be determined. This ensures that the determined schedulable equipment takes into account the matching relationship between health status and equipment load rate, minimizing the failure rate of the determined schedulable equipment and improving the accuracy of the final determined equipment scheduling optimization strategy.

[0131] For example, based on the above embodiments, when determining the equipment scheduling optimization strategy based on various types of schedulable data center equipment, a second objective function can be constructed based on the health load index of various types of schedulable data center equipment and the number of equipment types, with the goal of minimizing the health load index of all types of data center equipment in the equipment management system. Based on the second objective function, the schedulable data center equipment in the equipment management system is determined, and based on the schedulable data center equipment in the equipment management system, the equipment scheduling optimization strategy is determined.

[0132] Specifically, a second objective function can be constructed based on the health load index of each type of schedulable computer room equipment and the number of equipment types, with the goal of minimizing the health load index of all types of computer room equipment in the equipment management system. For example, the constructed second objective function is shown in formula (13):

[0133] (13)

[0134] Where k represents the number of equipment types in the computer room. a weight value of a dth type of machine room equipment, which is set based on a failure probability proportion of different types of machine room equipment, for example, a machine room equipment with a high failure probability is given a greater weight value, in actual application, The specific value of the weight value of the dth type of machine room equipment can also be corrected by comparison according to the expected result and the actual operation result.

[0135] By solving the second objective function, the schedulable machine room equipment in the equipment management system can be determined, and based on the schedulable machine room equipment in the equipment management system, the equipment scheduling optimization strategy can be determined.

[0136] In this embodiment, a second objective function can be constructed based on the health load index of each type of schedulable machine room equipment and the number of equipment types, with the minimum health load index of all types of machine room equipment in the equipment management system as the target. By solving the second objective function, the schedulable machine room equipment in the equipment management system can be determined, so that the schedulable equipment determined can ensure that the failure rate of the entire equipment management system is low after scheduling.

[0137] The device scheduling optimization strategy determination device provided in the present application will be described below. The device scheduling optimization strategy determination device described below can be referred to in conjunction with the device scheduling optimization strategy determination method described above.

[0138] Figure 3 The structure diagram of the device scheduling optimization strategy determination device provided in the embodiment of the present application is shown in Figure 3 As shown in the figure, the device scheduling optimization strategy determination device 300 comprises:

[0139] The acquisition module 11 is configured to acquire historical maintenance data of at least one target component in each machine room equipment in the equipment management system.

[0140] The determination module 12 is configured to determine an equipment health index of the machine room equipment based on the historical maintenance data.

[0141] The determination module 12 is further configured to determine a health state of the machine room equipment based on the equipment health index.

[0142] The determination module 12 is further configured to determine a health load index of the machine room equipment based on the health state and a load rate of the machine room equipment.

[0143] The determination module 12 is further configured to determine an equipment scheduling optimization strategy based on the health load index of each type of all machine room equipment, wherein the equipment scheduling optimization strategy is used to represent schedulable machine room equipment in all machine room equipment.

[0144] In an example embodiment, the historical maintenance data comprises historical maintenance time length and historical maintenance cost.

[0145] The determining module 12 is specifically configured to:

[0146] For each of the target components in the machine room equipment, a first weighted relative distance corresponding to the target component is determined based on the maximum maintenance time length, the highest maintenance cost, the historical maintenance time length of the target component, and the historical maintenance cost of the target component; the maximum maintenance time length is the maximum value in the historical maintenance time lengths corresponding to all target components of the machine room equipment, and the highest maintenance cost is the maximum value in the historical maintenance costs corresponding to all target components of the machine room equipment.

[0147] A second weighted relative distance corresponding to the target component is determined based on the minimum maintenance time length, the lowest maintenance cost, the historical maintenance time length of the target component, and the historical maintenance cost of the target component; the minimum maintenance time length is the minimum value in the historical maintenance time lengths corresponding to all target components of the machine room equipment, and the lowest maintenance cost is the minimum value in the historical maintenance costs corresponding to all target components of the machine room equipment.

[0148] A maintenance score of the target component in the machine room equipment is determined based on the first weighted relative distance and the second weighted relative distance.

[0149] A device health index of the machine room equipment is determined based on the maintenance scores of each of the target components in the machine room equipment.

[0150] In an example embodiment, the historical maintenance data further comprises historical maintenance frequency.

[0151] The determining module 12 is specifically configured to:

[0152] For each of the target components in the machine room equipment, an importance weight of the target component is determined based on the maintenance scores of the same target components in all machine room equipment of the same type as the machine room equipment.

[0153] A degradation degree of the target component is determined based on the historical maintenance frequency of the target component, the historical maintenance cost, and a sales price of the target component.

[0154] A weighted degradation degree of the target component is determined based on the degradation degree of the target component and the importance weight of the target component.

[0155] A maximum weighted degradation degree among the weighted degradation degrees of all the target components is determined as the device health index of the machine room equipment.

[0156] In an example embodiment, the determining module 12 is specifically configured to:

[0157] determine a device failure rate of the machine room device based on the device health index, a proportionality coefficient and a curvature coefficient, the proportionality coefficient and the curvature coefficient being fitted based on a number of failed devices and a total number of devices, the number of failed devices being a number of devices that have failed in all machine room devices of the same type as the machine room device within a preset time period, the total number of devices being a number of all machine room devices of the same type as the machine room device;

[0158] determine a health status of the machine room device based on the device failure rate of the machine room device.

[0159] In an example embodiment, the determining module 12 is specifically configured to:

[0160] for each type of machine room device, construct a first objective function based on a health load index of each machine room device of the type and a number of machine room devices in the type, with a minimum health load index of each machine room device of the type as an objective, and determine schedulable machine room devices in all machine room devices of the type based on the first objective function;

[0161] determine the device scheduling optimization strategy based on the schedulable machine room devices of each type.

[0162] In an example embodiment, the determining module 12 is specifically configured to:

[0163] construct a second objective function based on a health load index of each schedulable machine room device of each type and a number of device types, with a minimum health load index of all types of machine room devices in the device management system as an objective, and determine target schedulable machine room devices corresponding to the device management system from each schedulable machine room device of each type based on the second objective function;

[0164] determine the device scheduling optimization strategy based on the target schedulable machine room devices corresponding to the device management system.

[0165] The apparatus of the present embodiment can be used to execute the method of any one of the device scheduling optimization strategy determination method side embodiments, and has similar implementation processes and technical effects, and specific implementation processes can be referred to the detailed description of the device scheduling optimization strategy determination method side embodiments, which will not be described here.

[0166] Figure 4 An example electronic device entity structure diagram is provided for the present embodiment, as shown in Figure 4As shown, the electronic device can include a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 complete mutual communication through the communications bus 440. The processor 410 can invoke the logical instructions in the memory 430 to execute the device scheduling optimization strategy determination method, which includes: obtaining historical maintenance data of at least one target component in each machine room device in a device management system; determining a device health index of the machine room device based on each of the historical maintenance data; determining a health state of the machine room device based on the device health index; determining a health load index of the machine room device based on the health state and a load rate of the machine room device; and determining a device scheduling optimization strategy based on the health load index of each type of all machine room devices, wherein the device scheduling optimization strategy is used to represent schedulable machine room devices in all the machine room devices.

[0167] In addition, the logical instructions in the memory 430 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0168] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer readable storage medium, and the computer program is executable by a processor to cause a computer to perform the device scheduling optimization strategy determination method provided by the above-mentioned methods, which comprises: obtaining historical maintenance data of at least one target component in each machine room device in a device management system; determining a device health index of the machine room device based on each of the historical maintenance data; determining a health state of the machine room device based on the device health index; determining a health load index of the machine room device based on the health state and a load rate of the machine room device; and determining a device scheduling optimization strategy based on the health load index of all machine room devices of each type, wherein the device scheduling optimization strategy is used to represent schedulable machine room devices among all the machine room devices.

[0169] In another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, and the computer program is executable by a processor to implement the device scheduling optimization strategy determination method provided by the above-mentioned methods, which comprises: obtaining historical maintenance data of at least one target component in each machine room device in a device management system; determining a device health index of the machine room device based on each of the historical maintenance data; determining a health state of the machine room device based on the device health index; determining a health load index of the machine room device based on the health state and a load rate of the machine room device; and determining a device scheduling optimization strategy based on the health load index of all machine room devices of each type, wherein the device scheduling optimization strategy is used to represent schedulable machine room devices among all the machine room devices.

[0170] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0171] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and the necessary general hardware platform from the above description of the embodiments, and of course, the embodiments can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that contributes to the technical solutions can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the methods.

[0172] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining equipment scheduling optimization strategies, characterized in that, include: For each computer room device in the equipment management system, obtain historical maintenance data of at least one target component in the computer room device; The equipment health index of the computer room equipment is determined based on the historical maintenance data. The health status of the equipment in the computer room is determined based on the equipment health index. Based on the health status and the load rate of the data center equipment, the health load index of the data center equipment is determined; Based on the health load index of each type of data center equipment, a device scheduling optimization strategy is determined. The device scheduling optimization strategy is used to characterize the schedulable data center equipment among all the data center equipment. The historical maintenance data includes historical maintenance duration and historical maintenance costs. The process of determining the equipment health index of the computer room equipment based on the historical maintenance data includes: For each target component in the data center equipment, a first weighted relative distance is determined based on the maximum repair time, the maximum repair cost, the historical repair time of the target component, and the historical repair cost of the target component; the maximum repair time is the maximum value among the historical repair times of all target components of the data center equipment, and the maximum repair cost is the maximum value among the historical repair costs of all target components of the data center equipment. Based on the minimum repair time, the minimum repair cost, the historical repair time of the target component, and the historical repair cost of the target component, a second weighted relative distance corresponding to the target component is determined; the minimum repair time is the minimum value among the historical repair times corresponding to all target components of the data center equipment, and the minimum repair cost is the minimum value among the historical repair costs corresponding to all target components of the data center equipment; Based on the first weighted relative distance and the second weighted relative distance, the maintenance score of the target component in the computer room equipment is determined; Based on the maintenance scores of each target component in the computer room equipment, the equipment health index of the computer room equipment is determined.

2. The method for determining equipment scheduling optimization strategies according to claim 1, characterized in that, The historical maintenance data also includes the number of historical maintenance operations; The determination of the equipment health index of the data center equipment based on the maintenance scores of each target component in the data center equipment includes: For each target component in the computer room equipment, the importance weight of the target component is determined based on the maintenance score of the same target component in all computer room equipment of the same type as the computer room equipment. The degree of degradation of the target component is determined based on the historical number of repairs, the historical repair costs, and the sales price of the target component. The weighted degradation degree of the target component is determined based on the degradation degree of the target component and the importance weight of the target component; The maximum weighted degradation degree among all the target components is determined as the equipment health index of the data center equipment.

3. The method for determining equipment scheduling optimization strategies according to claim 1, characterized in that, Determining the health status of the data center equipment based on the equipment health index includes: Based on the equipment health index, proportional coefficient, and curvature coefficient, the equipment failure rate of the data center equipment is determined. The proportional coefficient and the curvature coefficient are obtained by fitting the number of faulty equipment and the total number of equipment. The number of faulty equipment is the number of equipment that has failed among all data center equipment of the same type as the data center equipment within a preset time period. The total number of equipment is the number of all data center equipment of the same type as the data center equipment. The health status of the equipment in the computer room is determined based on the equipment failure rate of the equipment in the computer room.

4. The method for determining equipment scheduling optimization strategies according to claim 1, characterized in that, The process of determining equipment scheduling optimization strategies based on the health load index of each type of equipment in all data center facilities includes: For each type of data center equipment, based on the health load index of each data center equipment of the type and the number of data center equipment in the type, a first objective function is constructed with the goal of minimizing the health load index of each data center equipment. Based on the first objective function, the schedulable data center equipment among all data center equipment of the type is determined. Based on the various types of schedulable data center equipment, the equipment scheduling optimization strategy is determined.

5. The method for determining equipment scheduling optimization strategies according to claim 4, characterized in that, The process of determining the equipment scheduling optimization strategy based on various types of schedulable data center equipment includes: Based on the health load index of each type of schedulable data center equipment and the number of equipment types, a second objective function is constructed with the goal of minimizing the health load index of all types of data center equipment in the equipment management system. Based on the second objective function, the target schedulable data center equipment corresponding to the equipment management system is determined from each type of schedulable data center equipment. Based on the target schedulable computer room equipment corresponding to the equipment management system, the equipment scheduling optimization strategy is determined.

6. A device for determining equipment scheduling optimization strategies, characterized in that, include: The acquisition module is used to acquire historical maintenance data of at least one target component of each computer room device in the equipment management system. The determination module is used to determine the equipment health index of the computer room equipment based on the historical maintenance data. The determining module is further configured to determine the health status of the computer room equipment based on the equipment health index; The determining module is further configured to determine the health load index of the data center equipment based on the health status and the load rate of the data center equipment; The determining module is further configured to determine a device scheduling optimization strategy based on the health load index of each type of all data center equipment, wherein the device scheduling optimization strategy is used to characterize the schedulable data center equipment among all the data center equipment. Historical maintenance data includes historical maintenance duration and historical maintenance costs. The determining module is specifically used to determine the equipment health index of the computer room equipment based on the historical maintenance data, including: For each target component in the data center equipment, a first weighted relative distance is determined based on the maximum repair time, the maximum repair cost, the historical repair time of the target component, and the historical repair cost of the target component; the maximum repair time is the maximum value among the historical repair times of all target components of the data center equipment, and the maximum repair cost is the maximum value among the historical repair costs of all target components of the data center equipment. Based on the minimum repair time, the minimum repair cost, the historical repair time of the target component, and the historical repair cost of the target component, a second weighted relative distance corresponding to the target component is determined; the minimum repair time is the minimum value among the historical repair times corresponding to all target components of the data center equipment, and the minimum repair cost is the minimum value among the historical repair costs corresponding to all target components of the data center equipment; Based on the first weighted relative distance and the second weighted relative distance, the maintenance score of the target component in the computer room equipment is determined; Based on the maintenance scores of each target component in the computer room equipment, the equipment health index of the computer room equipment is determined.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the device scheduling optimization strategy determination method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the device scheduling optimization strategy determination method as described in any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the device scheduling optimization strategy determination method as described in any one of claims 1 to 5.

Images