Site maintenance method, storage medium and program product

Abstract

The present application discloses a site maintenance method, storage medium and program product, which relate to the field of network operation and maintenance technology, including: determining multiple maintenance teams based on maintenance resources and computer room data of computer rooms to be maintained; clustering each of the computer rooms to be maintained to obtain multiple groups of computer rooms to be maintained, and determining the maintenance team corresponding to each group of the computer rooms to be maintained; for any target computer room group in each group of computer rooms to be maintained, determining the maintenance order of each target computer room in the target computer room group, wherein the target team maintains the target computer room group according to the maintenance order, and the target team is the maintenance team corresponding to the target computer room group. The present application groups computer rooms by clustering algorithm, and determines the maintenance order of computer rooms within the group, so as to generate flexible and efficient task allocation schemes and maintenance routes to adapt to the actual conditions of different computer rooms, thereby improving maintenance efficiency.

Description

Technical Field

[0001] The present application relates to the field of network operation and maintenance technology, and in particular to a site maintenance method, a storage medium, and a program product. Background Art

[0002] The communication site computer room is the infrastructure of the communication network, carrying the operation and maintenance of communication equipment. The computer room is usually equipped with base station equipment, transmission equipment, power supply system and other necessary auxiliary facilities, which together constitute the physical foundation of the communication network. The power supply of the communication site computer room is the key to ensuring its normal operation. Once the computer room loses power, the base station equipment will not work properly, and the communication signal will not be effectively covered, thus affecting the user's communication experience. In addition, power outages may also cause transmission equipment failures, making it impossible to transmit data normally, further affecting the stability and reliability of the communication network.

[0003] At present, when a communication site computer room fails, operation and maintenance tasks can be generated and assigned to maintenance personnel for the maintenance personnel to perform computer room operation and maintenance. The operation and maintenance tasks of the faulty communication site computer room are usually assigned in the following ways: one is to assign and schedule the operation and maintenance tasks of each faulty communication site computer room based on the geographical location and maintenance priority of each faulty communication site computer room, combined with manual experience, but this method has the disadvantages of low task allocation efficiency, unbalanced task allocation and easy errors, which affects the subsequent computer room operation and maintenance efficiency; the other is to assign and schedule the operation and maintenance tasks of each faulty communication site computer room according to preset rules and algorithms, and combined with automated tools based on fixed rules, but the preset rules and algorithms are too rigid to adapt to the complex and changeable actual situation, and the generated task allocation plan and maintenance route may not be optimized enough, resulting in low maintenance efficiency and lack of flexibility, which affects the subsequent computer room operation and maintenance efficiency. In summary, the current allocation of operation and maintenance tasks for the faulty site computer room is unreasonable, which affects the operation and maintenance efficiency of computer room operation and maintenance based on task allocation.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a site maintenance method, storage medium and program product, aiming to solve the technical problem that the current allocation of operation and maintenance tasks for the computer room of the faulty site is unreasonable, resulting in the operation and maintenance efficiency of the computer room based on task allocation being affected.

[0006] To achieve the above object, the present application proposes a site maintenance method, the method comprising:

[0007] Determine multiple maintenance teams based on maintenance resources and computer room data of computer rooms to be maintained;

[0008] Clustering the machine rooms to be maintained to obtain multiple groups of machine rooms to be maintained, and determining the maintenance team corresponding to each group of machine rooms to be maintained;

[0009] For any target computer room group in each group of computer rooms to be maintained, a maintenance order of each target computer room in the target computer room group is determined, wherein a target team maintains the target computer room group according to the maintenance order, and the target team is a maintenance team corresponding to the target computer room group.

[0010] In one embodiment, the step of clustering the machine rooms to be maintained to obtain multiple groups of machine rooms to be maintained includes:

[0011] According to the number of the maintenance teams, a plurality of initial cluster centroids are determined from each of the computer rooms to be maintained;

[0012] Traversing each of the machine rooms to be maintained, determining the cluster distance between the machine room to be maintained and each of the initial clustering centroids, and allocating the machine room to be maintained to the cluster cluster to which the initial clustering centroid with the smallest clustering distance belongs;

[0013] The cluster centers of the clusters are determined, and the cluster centers are iterated on each cluster until a preset clustering condition is met to obtain a plurality of target clusters, and each target cluster is determined as a group of computer rooms to be maintained.

[0014] In one embodiment, the step of determining the maintenance order of each target computer room in the target computer room group includes:

[0015] Based on the power-off status of each target computer room in the target computer room group, determining the estimated outage duration of each target computer room, and obtaining route information between each target computer room;

[0016] Based on the route information and the estimated deservice time, path planning is performed with the goal of minimizing the total expected deservice time of the target computer room group, and the maintenance order of each target computer room is obtained, wherein the total expected deservice time is the time interval between the target team completing maintenance of the target computer room group and the deservice of the target computer room group.

[0017] In one embodiment, before the step of performing path planning based on the route information and each of the estimated outage durations with the goal of minimizing the total expected outage duration of the target computer room group to obtain the maintenance sequence of each of the target computer rooms, the step further includes:

[0018] Determine a first number of each of the target computer rooms in the target computer room group;

[0019] The step of performing path planning based on the route information and each of the estimated out-of-service durations with the goal of minimizing the total expected out-of-service duration of the target computer room group to obtain the maintenance sequence of each of the target computer rooms comprises:

[0020] Based on the first quantity, the route information and the estimated outage durations, path planning is performed with the goal of minimizing the total expected outage duration of the target computer room group to obtain a maintenance order for each of the target computer rooms.

[0021] In one embodiment, the step of performing path planning based on the first quantity, the route information, and each of the estimated outage durations with the goal of minimizing the total expected outage duration of the target computer room group to obtain the maintenance order of each of the target computer rooms includes:

[0022] If the first number is less than or equal to a preset threshold, traverse each of the target computer rooms starting from the stationing location of the target team to obtain multiple theoretical routes;

[0023] For the target routes in each of the theoretical routes, based on the route information, each of the estimated decommissioning time, the theoretical maintenance time, and the traversal order of each of the target computer rooms, the expected decommissioning time of each of the target computer rooms is determined, wherein the expected decommissioning time of the computer room is the time interval between the target team completing maintenance of each of the target computer rooms and decommissioning each of the target computer rooms when the target team performs maintenance on the target computer room group according to the theoretical route;

[0024] Determine the total expected out-of-service duration corresponding to the target line based on the expected out-of-service duration of each target computer room;

[0025] The theoretical line with the smallest total expected out-of-service time among the theoretical lines is determined as the maintenance line, and the maintenance order of each of the target computer rooms is determined based on the maintenance line.

[0026] In one embodiment, the step of performing path planning based on the first quantity, the route information, and each of the estimated outage durations with the goal of minimizing the total expected outage duration of the target computer room group to obtain the maintenance order of each of the target computer rooms includes:

[0027] If the first number is greater than the preset threshold, each of the target computer rooms is added to the first computer room list, and based on the route information, the estimated service withdrawal time and the theoretical maintenance time, the local expected service withdrawal time of each first computer room in the first computer room list is determined, wherein the local expected service withdrawal time is the time interval between the target team completing the maintenance of the first computer room and the service withdrawal of the first computer room;

[0028] Move the first computer room with the shortest local expected out-of-service time in the first computer room list to the second computer room list, return to the step of determining the local expected out-of-service time of each first computer room in the first computer room list based on the route information, the estimated out-of-service time and the theoretical maintenance time, until the number of the first computer rooms reaches the preset threshold, and determine the order in which the second computer rooms are moved to the second computer room list as the maintenance order of each second computer room;

[0029] A traversal route is determined based on each of the first computer rooms, and a route with the shortest total expected out-of-service time among the traversal routes is determined as a local route, and a maintenance order of each of the first computer rooms is determined based on the local route.

[0030] In one embodiment, the step of determining multiple maintenance teams based on maintenance resources and computer room data of computer rooms to be maintained includes:

[0031] Based on the computer room data of the computer rooms to be maintained, determine the straight-line distance between any two of the computer rooms to be maintained, determine the median of each of the straight-line distances as the target distance, and determine the first value based on the target distance and the second number of each of the computer rooms to be maintained;

[0032] Determine the number of vehicles, the number of maintenance personnel, and the number of oil engines based on the maintenance resources of the machine room, and determine the minimum value among the number of vehicles, the number of maintenance personnel, and the number of oil engines as a second value;

[0033] The minimum value among the first value, the second value and the second number is determined as the third value, and the maximum value between the third value and the preset number is determined as the team number, and multiple maintenance teams are determined according to the team number.

[0034] In one embodiment, before the step of determining multiple maintenance teams based on the maintenance resources and the computer room data of the computer room to be maintained, the method further includes:

[0035] Acquire dynamic ring alarm data, and determine AC power outage information and DC power outage information from the dynamic ring alarm data;

[0036] The computer room corresponding to the AC power outage information and the DC power outage information is determined as the computer room to be maintained.

[0037] In addition, to achieve the above objectives, the present application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the site maintenance method described above are implemented.

[0038] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, wherein the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the site maintenance method described above are implemented.

[0039] In this application, multiple maintenance teams are determined based on maintenance resources and the data of the computer room to be maintained. Based on maintenance resources and the data of the computer room to be maintained, multiple maintenance teams are intelligently determined, which can fully consider the resource status of maintenance resources such as the number of maintenance personnel, skill level, vehicles and equipment, ensure the feasibility and efficiency of subsequent task allocation, and avoid maintenance task delays or poor execution due to insufficient or improper resource allocation.

[0040] Clustering the machine rooms to be maintained to obtain multiple groups of machine rooms to be maintained, and determining the maintenance team corresponding to each group of machine rooms to be maintained. The clustering algorithm can group machine rooms with similar geographical locations or maintenance requirements together to form a machine room to be maintained group, which can reduce the moving distance of the maintenance team between machine rooms, thereby improving maintenance efficiency. Allocating a maintenance team to each machine room group to be maintained can ensure balanced distribution of tasks and avoid the situation where some teams have too heavy tasks while other teams have too light tasks.

[0041] For any target computer room group in each group of computer rooms to be maintained, a maintenance order of each target computer room in the target computer room group is determined, wherein the target team performs maintenance on the target computer room group according to the maintenance order, and the target team is the maintenance team corresponding to the target computer room group. By determining the maintenance order for each group of computer rooms, it is possible to ensure that the maintenance team completes as much maintenance work as possible within a limited time, thereby improving maintenance efficiency.

[0042] In summary, the present application groups computer rooms through a clustering algorithm and determines the maintenance order of the computer rooms within the group, which can generate flexible and efficient task allocation plans and maintenance routes to adapt to the actual conditions of different computer rooms, thereby improving maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1A flowchart of the first embodiment of the site maintenance method of the present application is provided;

[0046] Figure 2 A flowchart of the second embodiment of the site maintenance method of the present application is provided;

[0047] Figure 3 A brief flowchart of a site maintenance method provided in an embodiment of the present application;

[0048] Figure 4 This is a schematic diagram of the module structure of the site maintenance device according to an embodiment of the present application;

[0049] Figure 5 Schematic diagram of the equipment structure of the hardware operating environment involved in the site maintenance method in the embodiment of the present application.

[0050] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of the embodiment of the present application is: determine multiple maintenance teams based on maintenance resources and computer room data of the computer room to be maintained; cluster each of the computer rooms to be maintained to obtain multiple groups of computer rooms to be maintained, and determine the maintenance team corresponding to each group of the computer room groups to be maintained; for any target computer room group in each group of the computer room groups to be maintained, determine the maintenance order of each target computer room in the target computer room group, wherein the target team maintains the target computer room group according to the maintenance order, and the target team is the maintenance team corresponding to the target computer room group.

[0054] In this embodiment, for ease of description, the following description is made with the site operation and maintenance equipment as the execution entity.

[0055] In the field of power outage maintenance in the computer room of a communication site, the existing technology usually uses the following methods to allocate maintenance tasks for the power outage room: Solution 1: Manual allocation and scheduling. The maintenance team usually relies on manual experience to allocate and schedule tasks. According to the geographical location and maintenance priority of each computer room, the team leader manually formulates the maintenance route and task allocation plan. The specific method adopted is: the team leader manually determines the maintenance order and priority according to the location and maintenance level of the computer room, and manually allocates specific maintenance tasks according to the number and skill level of the maintenance personnel. The maintenance personnel perform maintenance on the power outage room one by one according to the assigned tasks and routes. This solution has the problems of low efficiency, reliance on manual experience, time-consuming allocation process, unbalanced task allocation, which may cause individual maintenance personnel to be overloaded and prone to errors, and human factors affect the accuracy and rationality of task allocation. Solution 2: Automated tools based on fixed rules. Introduce automated tools based on fixed rules to allocate and plan routes for power outage maintenance tasks through preset rules and algorithms. The specific method used is: pre-set task allocation and route planning rules and algorithms, such as importing the information of the computer room and maintenance personnel into the tool according to factors such as geographical distance and maintenance level, automatically generating task allocation plans and maintenance routes. Maintenance personnel perform maintenance tasks according to the plans generated by the tool. The disadvantages of this solution are: the rules and algorithms are too rigid and cannot adapt to the complex and changing actual situation. The generated task allocation plans and maintenance routes may not be optimized enough, resulting in low maintenance efficiency, lack of flexibility, and difficulty in responding to emergencies or special needs in a timely manner.

[0056] In summary, the existing technologies have the following major shortcomings in the allocation of maintenance tasks and route optimization for power outages in the computer room of communication sites: 1) Unbalanced task allocation. Manual allocation and tools based on fixed rules make it difficult to achieve balanced task allocation, resulting in some maintenance personnel having too heavy tasks and other personnel having too light tasks. 2) Unreasonable route planning. Existing solutions mostly use distance as the only basis for route planning, ignoring the importance of the site and the maintenance level, which may lead to unreasonable maintenance sequences. 3) Low intelligence. The lack of the application of intelligent algorithms makes it difficult to dynamically adjust task allocation and route planning according to actual conditions, affecting maintenance efficiency and response speed. 4) High maintenance costs. Due to unreasonable task allocation and route planning, the work efficiency of maintenance personnel is low, which increases operation and maintenance costs.

[0057] Compared with manual allocation and tools based on fixed rules, it is difficult to achieve balanced distribution of tasks. This application determines multiple maintenance teams based on the data of maintenance resources and the computer room to be maintained, which can ensure that there are enough teams to deal with maintenance tasks. The clustering algorithm and data-driven allocation method are more objective and accurate, and can reduce the problems of unbalanced task allocation and inefficiency caused by human factors. Compared with route planning based on distance as the only basis, this application considers the similarity and geographical clustering between computer rooms through a clustering algorithm, thereby generating a more reasonable computer room group and further improving operation and maintenance efficiency. Compared with the prior art, it is difficult to dynamically adjust task allocation and route planning according to actual conditions. In this application, the clustering algorithm and subsequent maintenance order determination are based on the real-time data of maintenance resources and computer rooms to be maintained. When the maintenance needs or maintenance resources of the computer room change, clustering and maintenance order determination can be re-performed, thereby realizing dynamic allocation of tasks and dynamic adjustment of routes. By introducing intelligent algorithms for task allocation and route planning, the operation and maintenance task allocation can better adapt to the complex and changeable actual conditions. Therefore, this application can generate more reasonable and optimized task allocation plans and route planning plans through clustering algorithms and intelligent allocation methods, and can generate flexible and efficient task allocation plans and maintenance routes to adapt to the actual conditions of different computer rooms, thereby improving maintenance efficiency.

[0058] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a site operation and maintenance device, etc. The following takes the site operation and maintenance device as an example to illustrate this embodiment and the following embodiments.

[0059] Based on this, the present application embodiment provides a site maintenance method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the site maintenance method of the present application.

[0060] In this embodiment, the site maintenance method includes steps S10 to S30:

[0061] Step S10, determining multiple maintenance teams based on maintenance resources and computer room data of the computer room to be maintained;

[0062] It should be noted that the computer room to be maintained refers to the computer room of a communication site that needs maintenance due to power outages and other faults. The computer room data includes computer room location information representing the location of the computer room to be maintained and computer room fault information representing the computer room fault, including but not limited to the geographical location of the computer room, power outage level, historical maintenance data, etc. In this embodiment, before determining multiple maintenance teams based on maintenance resources and computer room data of the computer room to be maintained, the computer room to be maintained is first determined from the computer rooms of each site. Specifically, it can be a computer room to be maintained based on the input received by the engineer on the human-computer interaction interface, or it can be extracted based on alarm data. The specific method is not limited here.

[0063] Maintenance resources refer to all resources that can be used to perform maintenance work in the power outage maintenance task of the communication site room, including but not limited to maintenance personnel, maintenance vehicles, maintenance tools and equipment, etc. A maintenance team refers to a team composed of a certain number of maintenance personnel, responsible for performing specific maintenance tasks. Each maintenance team has a certain number of maintenance resources to perform maintenance tasks. The resources of different maintenance teams can be the same or different, and the maintenance tasks performed by different maintenance teams can be the same or different, and there is no restriction here.

[0064] The method of determining the maintenance team is not limited here. For example, in one feasible implementation, the maintenance team to be dispatched can be set up by an engineer based on the actual situation of the team's current personnel, vehicles and other resources based on the human-computer interaction interface; in another feasible implementation, the maintenance team can be determined based on a preset algorithm, which is not limited here.

[0065] Step S20, clustering the machine rooms to be maintained to obtain multiple groups of machine rooms to be maintained, and determining the maintenance team corresponding to each group of machine rooms to be maintained;

[0066] The K-means clustering algorithm is used to cluster the computer rooms to be maintained, and the computer rooms are divided into several categories equal to the number of maintenance teams to obtain multiple groups of computer rooms to be maintained. Specifically, the clustering can be based on indicators such as geographical location and computer room priority, which are not restricted here. The specific clustering process can be set according to actual needs.

[0067] According to the clustering results, each group of computer rooms is assigned to a maintenance team to ensure that the workload of each team is relatively balanced. There is no restriction on the way of task allocation. Each group of computer rooms to be maintained is assigned a maintenance team.

[0068] Step S30, for any target computer room group in each group of computer room groups to be maintained, determine the maintenance order of each target computer room in the target computer room group, wherein the target team maintains the target computer room group according to the maintenance order, and the target team is the maintenance team corresponding to the target computer room group.

[0069] For any target computer room group in each group of computer rooms to be maintained, each computer room in the target computer room group is called a target computer room, and the maintenance team corresponding to the target computer room group is called a target team. In this embodiment, the maintenance order of each target computer room is determined to ensure that the maintenance team can go to each computer room in turn to perform maintenance work in the most efficient and reasonable way. It should be noted that the method of determining the maintenance order is not limited here. For example, in one feasible implementation, the maintenance order can be determined according to the priority of each target computer room. The higher the priority, the higher the maintenance order; in another feasible implementation, it can also be based on the computer room data of each target computer room. Path planning is performed, and the path that meets the preset planning conditions (such as the minimum total distance cost, the shortest total time, etc.) is used as the optimal maintenance path, and the order of each path point in the path is used as the maintenance order of each target computer room. After determining the maintenance order of each target computer room, the target team maintains the target computer room group according to the maintenance order.

[0070] In a feasible implementation manner, the step S10: the step of determining multiple maintenance teams based on maintenance resources and computer room data of the computer room to be maintained, comprises:

[0071] Step S101, based on the computer room data of the computer rooms to be maintained, determining the straight-line distance between any two of the computer rooms to be maintained, determining the median of each of the straight-line distances as the target distance, and determining a first value based on the target distance and the second number of each of the computer rooms to be maintained;

[0072] In this implementation, the number of maintenance teams is automatically determined based on the computer room data and maintenance resources, and maintenance teams are created according to the number. Compared with manually determining the number of teams and creating teams, this implementation can improve the efficiency of creating maintenance teams, thereby improving the efficiency of computer room maintenance.

[0073] It should be noted that the computer room location information is extracted from the computer room data of the computer room to be maintained, and the straight-line distance between any two computer rooms to be maintained is determined based on the computer room location information. The straight-line distance refers to the shortest distance between two computer rooms to be maintained, without considering actual geographical conditions such as terrain and obstacles, and is calculated as the shortest path length between two points on a plane. By calculating the straight-line distance between computer rooms to be maintained, it can be used to evaluate the time cost and resource consumption cost of the maintenance team moving between different computer rooms. These straight-line distances are sorted, and the median of the straight-line distances is determined as the target distance. The target distance can reflect the central trend of the straight-line distances between computer rooms to be maintained.

[0074] A first value is determined based on the target distance and the second number of computer rooms to be maintained (i.e., the total number of computer rooms to be maintained). In one feasible implementation, the first value = ceiling(d / 3*N / 5), where ceiling represents a rounding function, N is the second number, and d is the target distance.

[0075] Step S102, determining the number of vehicles, the number of maintenance personnel and the number of oil engines based on the maintenance resources of the machine room, and determining the minimum value among the number of vehicles, the number of maintenance personnel and the number of oil engines as a second value;

[0076] The number of vehicles refers to the total number of vehicles that can be used to perform maintenance tasks, the number of maintenance personnel refers to the total number of personnel that can be used to perform maintenance tasks, and the number of oil engines refers to the total number of oil engines (generators) that can be used to provide temporary power supply for the communication site computer room. The number of vehicles, the number of maintenance personnel, and the number of oil engines are determined based on the computer room maintenance resources, and then the minimum value is determined from the number of vehicles, the number of maintenance personnel, and the number of oil engines as the second value. The second value represents the value corresponding to the resource type with the least number of currently available resources, which is a key factor in limiting the number of maintenance teams. By considering multiple resources such as vehicles, maintenance personnel, and oil engines, it can ensure that the composition of the maintenance team is more reasonable and avoid the inability to complete tasks due to insufficient resources.

[0077] Step S103, determining the minimum value among the first value, the second value and the second number as the third value, and determining the maximum value between the third value and the preset number as the team number, and determining multiple maintenance teams according to the team number.

[0078] The third value is determined as the minimum value among the first value, the second value, and the second number of computer rooms to be maintained. The maximum value between the third value and the preset number is determined as the number of teams, and multiple maintenance teams are determined according to the number of teams. It can be understood that by comprehensively considering multiple factors to determine the number of maintenance teams, the rationality and balance of task allocation can be ensured, and the maintenance efficiency can be improved. By forming maintenance teams according to the determined number of teams, it can be ensured that each team has sufficient resources and capabilities to complete the assigned tasks, thereby improving the overall maintenance effect.

[0079] In a feasible implementation manner, before the step S10: determining multiple maintenance teams based on maintenance resources and the computer room data of the computer room to be maintained, the step further includes:

[0080] Step S01, obtaining dynamic ring alarm data, and determining AC power outage information and DC power outage information from the dynamic ring alarm data;

[0081] An AC power outage refers to a situation where the AC power supply (usually the mains) in the computer room is interrupted. The AC power supply is one of the main power sources for various devices in the computer room. Once the AC power supply is interrupted, the equipment in the computer room will not work properly, and may even cause equipment damage or data loss. The causes of the AC power outage may include power grid failure, line aging, equipment failure, etc. A DC power outage refers to a situation where the DC power supply (usually a battery or a DC power supply device) in the computer room is interrupted. The DC power supply is usually used as a backup power supply in the computer room. When the AC power supply is interrupted, the DC power supply will take over the power supply task to ensure that the key equipment in the computer room can continue to operate for a period of time. The causes of the DC power outage may include battery aging, DC power supply device failure, etc.

[0082] Dynamic environment alarm data is the alarm information recorded by the power environment monitoring system (referred to as dynamic environment system) in the computer room of the communication site. The dynamic environment system is usually responsible for monitoring various equipment in the computer room (such as power supply, air conditioning, fire protection, etc.) and environmental parameters (such as temperature, humidity, smoke, etc.). Once these equipment or parameters are abnormal, the dynamic environment system will generate alarm information to remind the operation and maintenance personnel to deal with it in time. Dynamic environment alarm data contains key information such as alarm type, alarm level, alarm time, alarm location (computer room ID or location information), alarm description, etc.

[0083] During the maintenance of the computer room, by analyzing the AC power outage information and DC power outage information in the dynamic environment alarm data, the operation and maintenance personnel can determine which computer rooms need emergency maintenance. First, the real-time or historical dynamic environment alarm data is obtained through the interface or database of the dynamic environment system, and the obtained alarm data is screened to find out the alarm information related to AC power outage and DC power outage. Specifically, it can be achieved by matching the alarm types, for example, using specific alarm codes or keywords to identify alarms related to AC power outages (such as city power outage, AC power failure and other warning words) and DC power outages (such as "DC power failure", "battery exhaustion" and other warning words).

[0084] Step S02: determining the computer room corresponding to the AC power outage information and the DC power outage information as the computer room to be maintained.

[0085] The computer room corresponding to the AC power outage information and the DC power outage information is determined as the computer room to be maintained. It can be understood that by obtaining the dynamic environment alarm data, the operation and maintenance personnel can quickly locate the computer room related to the AC and DC power outages in the computer room, providing an accurate basis for subsequent maintenance tasks. Through the automated or semi-automated data screening and sorting process, the time for manual judgment is reduced and the execution efficiency of maintenance tasks is improved.

[0086] In this embodiment, multiple maintenance teams are determined based on maintenance resources and the room data of the room to be maintained. Based on the maintenance resources and the room data of the room to be maintained, multiple maintenance teams are intelligently determined, which can fully consider the number of maintenance personnel, skill level, vehicle and equipment and other maintenance resources. The resource status ensures the feasibility and efficiency of subsequent task allocation, and avoids the delay or poor execution of maintenance tasks caused by insufficient resources or improper allocation. Clustering is performed on each of the rooms to be maintained to obtain multiple groups of rooms to be maintained, and the maintenance teams corresponding to each group of rooms to be maintained are determined. Through the clustering algorithm, rooms with similar geographical locations or similar maintenance requirements can be combined to form a room to be maintained group, which can reduce the moving distance of the maintenance team between the rooms, thereby improving the maintenance efficiency. A maintenance team is assigned to each room to be maintained group, which can ensure the balanced distribution of tasks and avoid the situation where some teams have too heavy tasks and other teams have too light tasks. For any target computer room group in each group of computer rooms to be maintained, a maintenance order of each target computer room in the target computer room group is determined, wherein the target team performs maintenance on the target computer room group according to the maintenance order, and the target team is the maintenance team corresponding to the target computer room group. By determining the maintenance order for each group of computer rooms, it is possible to ensure that the maintenance team completes as much maintenance work as possible within a limited time, thereby improving maintenance efficiency.

[0087] In summary, this embodiment uses a clustering algorithm to group computer rooms and determine the maintenance order of computer rooms within the group, which can generate flexible and efficient task allocation plans and maintenance routes to adapt to the actual conditions of different computer rooms, thereby improving maintenance efficiency.

[0088] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 The step S20: clustering the machine rooms to be maintained to obtain multiple groups of machine rooms to be maintained, comprises:

[0089] Step S201, determining a plurality of initial cluster centroids from each of the computer rooms to be maintained according to the number of the maintenance teams;

[0090] According to the number of maintenance teams, a computer room with the same number of maintenance teams is randomly selected from the set of computer rooms to be maintained as the initial clustering centroid. Specifically, the initial clustering execution can be obtained randomly or determined based on a preset strategy (such as the geographical location and importance of the computer room), which is not limited here.

[0091] Step S202, traversing each of the machine rooms to be maintained, determining the cluster distance between the machine room to be maintained and each of the initial clustering centroids, and allocating the machine room to be maintained to the cluster cluster to which the initial clustering centroid with the smallest clustering distance belongs;

[0092] For each machine room to be maintained, the distance between it and all the initial clustering centroids is calculated. The distance may be Euclidean distance, Manhattan distance, etc., depending on the characteristics of the data and the requirements of clustering, which is not limited here. In a feasible implementation, the step of determining the clustering distance between the machine room to be maintained and each of the initial clustering centroids may include: traversing each of the initial clustering centroids, determining the first longitude and latitude of the machine room to be maintained, and determining the second longitude and latitude of the initial clustering execution; determining the longitude and latitude distance between the first longitude and longitude and the second longitude and longitude, and determining the longitude and latitude distance as the clustering distance.

[0093] Each computer room to be maintained is assigned to the cluster to which the initial cluster centroid with the smallest distance belongs, so that similar computer rooms will be assigned to the same cluster. It can be understood that by calculating the distance and assigning the computer rooms, it can be ensured that the computer rooms in each cluster are similar, making the maintenance task more centralized and efficient, and reducing unnecessary duplication of work.

[0094] Step S203, determining the cluster center of each cluster, iterating each cluster based on each cluster center until a preset clustering condition is met, obtaining multiple target clusters, and determining each target cluster as a computer room group to be maintained.

[0095] For each cluster, determine the cluster center of each cluster, which can be specifically calculated as the average position of all computer rooms in the cluster or other statistics as the new cluster center, which is not limited here. Based on the new cluster center, recalculate the distance between each computer room to be maintained and all cluster centers, and assign it to the cluster with the smallest distance, repeat the above steps of updating the cluster center and reallocating the computer room until the preset clustering condition is met (such as the change of the cluster center is less than a certain threshold, the number of iterations reaches the upper limit, etc.), stop the iteration, and use the obtained cluster as the target cluster, that is, the computer room group to be maintained.

[0096] In a feasible implementation manner, the step S30: determining the maintenance order of each target computer room in the target computer room group includes:

[0097] Step S301, based on the power off status of each target computer room in the target computer room group, determining the estimated outage duration of each target computer room, and obtaining route information between each target computer room;

[0098] The power-off state is used to indicate that the equipment room is in an AC power outage and / or a DC power outage. The estimated out-of-service duration refers to the theoretical out-of-service duration of the equipment room after the power outage. If the power outage status is AC power outage, it means that the computer room has a power outage. If the power outage status is DC power outage, it means that the battery is exhausted and the computer room is out of service. Different power outage statuses correspond to different estimated out-of-service durations. Specifically, if the power outage status of the computer room is both AC power outage and DC power outage, or the power outage status is DC power outage, the estimated out-of-service duration is 0, and the base stations in the computer room have been out of service. If the power outage status is AC power outage, the estimated out-of-service duration is max(0, computer room power storage duration - (current time - AC power outage alarm time)), where the computer room power storage duration is an estimated value of the battery power supply duration. If the computer room power storage duration - (current time - AC power outage alarm time) is negative, it indicates that the computer room battery may be exhausted at any time. If the AC power outage alarm is eliminated, it means that the AC power outage has been restored, and the computer room is removed from the maintenance task.

[0099] Route information refers to the path information of the maintenance team from the starting point (such as the station) to each machine room, which usually includes the distance, traffic conditions, road type, etc. It can be understood that by comprehensively considering the route information, the optimal maintenance route can be formulated to reduce the time the maintenance team spends on the road and improve maintenance efficiency.

[0100] Step S302, based on the route information and each of the estimated deservice times, path planning is performed with the goal of minimizing the total expected deservice time of the target computer room group, to obtain the maintenance order of each of the target computer rooms, wherein the total expected deservice time is the time interval between the target team completing maintenance of the target computer room group and the deservice of the target computer room group.

[0101] The target team may complete maintenance before the target computer room is decommissioned, or may not be able to complete maintenance before the target computer room is decommissioned. If the target team cannot complete maintenance before the target computer room is decommissioned, the target computer room will be decommissioned. The total expected decommissioning time is the time interval between the target team completing maintenance on the target computer room group and the target computer room group decommissioning.

[0102] In this embodiment, the goal is to minimize the total expected outage time of the target computer room group, and based on the route information and each estimated outage time, a preset path planning algorithm (such as a greedy algorithm, dynamic programming, heuristic algorithm, etc.) is used to calculate the optimal or approximately optimal maintenance sequence. It can be understood that through path planning, an optimal or approximately optimal maintenance sequence can be found to minimize the total expected outage time of the target computer room group, thereby reducing the impact on the business.

[0103] It should be noted that different computer rooms have different maintenance priorities because the base stations in the computer rooms serve different areas. When performing path planning, in order to perform maintenance according to the priorities as much as possible, different weights can be set for different priorities to increase the proportion of different computer rooms in the total expected deservice time.

[0104] In a feasible implementation manner, before the step S302: performing path planning based on the route information and each of the estimated outage durations with the goal of minimizing the total expected outage duration of the target computer room group to obtain the maintenance order of each of the target computer rooms, the step further includes:

[0105] Step S03, determining a first number of each of the target computer rooms in the target computer room group;

[0106] The total number of target computer rooms in the target computer room group, that is, the first number, is determined.

[0107] The step S302: performing path planning based on the route information and the estimated outage durations, with the goal of minimizing the total expected outage duration of the target computer room group, to obtain the maintenance sequence of each of the target computer rooms, comprises:

[0108] Step S3021: Based on the first quantity, the route information and the estimated outage durations, path planning is performed with the goal of minimizing the total expected outage duration of the target computer room group to obtain a maintenance order for each of the target computer rooms.

[0109] Path planning is performed based on the first quantity, route information and each estimated decommissioning time. Targeted path planning is performed based on the first quantity. For example, if the quantity is small, a full traversal algorithm can be used for path planning, and the maintenance sequence can be adjusted more finely to improve the accuracy of the maintenance sequence; for optimization methods with a large number; if the number is large, a local optimization algorithm or a staged planning algorithm can be used for path planning to improve the overall planning efficiency.

[0110] In a feasible implementation manner, step S3021: based on the first quantity, the route information and each of the estimated outage durations, path planning is performed with the goal of minimizing the total expected outage duration of the target computer room group to obtain the maintenance order of each of the target computer rooms, including:

[0111] Step S30211, if the first number is less than or equal to a preset threshold, traverse each of the target computer rooms starting from the stationing location of the target team to obtain multiple theoretical routes;

[0112] When the first number is less than or equal to the preset threshold, the path planning is performed by traversing the entire amount. Specifically, starting from the station location, each target computer room is traversed in turn to generate all possible theoretical routes. Since the number of computer rooms is small, all possible theoretical routes can be traversed to ensure that the optimal solution or a maintenance sequence close to the optimal solution is found.

[0113] Step S30212, for the target routes in each of the theoretical routes, based on the route information, each of the estimated decommissioning time, the theoretical maintenance time, and the traversal order of each of the target computer rooms, determine the expected decommissioning time of each of the target computer rooms, wherein the expected decommissioning time of the computer room is the time interval between the target team completing maintenance of each of the target computer rooms and decommissioning each of the target computer rooms when the target team performs maintenance on the target computer room group according to the theoretical route;

[0114] For each theoretical route, based on the route information, the estimated deservice time, the theoretical maintenance time and the traversal order of each target computer room, the expected deservice time of each target computer room is determined. The specific formula can be: max(-(Ti–ti–iv), 0), wherein Ti is the estimated deservice time of the i-th computer room, ti is the time for the target team to go from the i-1-th computer room to the i-th computer room, v is the theoretical time for the target team to maintain a single computer room, and iv represents the theoretical time for maintaining i computer rooms. Therefore, the expected deservice time of the computer room is the time interval between the target team completing the maintenance of each target computer room and the deservice of each target computer room when the target team maintains the target computer room group according to the theoretical route. If the -(Ti–ti–iv) duration is less than or equal to 0, it means that the maintenance is completed before the target team exits the computer room. At this time, the expected exit time of the computer room is max(-(Ti–ti–iv), 0), which is 0; if the -(Ti–ti–iv) duration is greater than 0, it means that the maintenance is not completed before the target team exits the computer room. At this time, the expected exit time of the computer room is max(-(Ti–ti–iv), 0), which is -(Ti–ti–iv).

[0115] In one feasible implementation, different weights can be set for different priorities to increase the proportion of different computer rooms in the total expected deservice time. For example, the weight corresponding to a computer room with a maintenance priority of 1 is 4; the weight corresponding to a computer room with a maintenance priority of 2 is 3; the weight corresponding to a computer room with a maintenance priority of 3 is 2; the weight corresponding to a computer room with a maintenance priority of 4 is 1, and so on. Therefore, the actual deservice time of a computer room with a high priority has a greater impact on the result. The algorithm fully considers the maintenance priority factor of the computer room, so that the path planning tends to give priority to computer rooms with high priorities, but at the same time considers the distance advantage of computer rooms with low priorities. Therefore, the specific formula for the expected deservice time of the computer room can be: max(-(Ti–ti–iv), 0)*si, where si is the weight. For example, if the computer room priority is 1, the specific formula can be: max(-(Ti–ti–iv), 0)*4.

[0116] Step S30213, determining a total expected out-of-service duration corresponding to the target line based on the expected out-of-service durations of the target computer rooms;

[0117] The expected out-of-service time of each computer room is accumulated to obtain the total expected out-of-service time of the target line.

[0118] Step S30214: determine the theoretical line with the shortest total expected out-of-service time among the theoretical lines as the maintenance line, and determine the maintenance order of each of the target computer rooms based on the maintenance line.

[0119] The line with the shortest expected outage time is selected from all theoretical lines as the final maintenance line, and only the computer room sequence of the line is maintained, which is determined as the maintenance sequence of each computer room.

[0120] In a feasible implementation manner, the step S3021: based on the first quantity, the route information and each of the estimated outage durations, performing path planning with the goal of minimizing the total expected outage duration of the target computer room group to obtain the maintenance order of each of the target computer rooms, includes:

[0121] Step S30215: if the first number is greater than the preset threshold, each of the target computer rooms is added to the first computer room list, and based on the route information, the estimated service withdrawal time and the theoretical maintenance time, the local expected service withdrawal time of each of the first computer rooms in the first computer room list is determined, wherein the local expected service withdrawal time is the time interval between the target team completing the maintenance of the first computer room and the service withdrawal of the first computer room;

[0122] When the first number is greater than the preset threshold, all target computer rooms are added to the first computer room list. For each first computer room in the list, its local expected deservice time is calculated according to its location, route information, estimated deservice time and theoretical maintenance time. The specific formula for calculating the local expected deservice time can be: max(-(Ti–ti–v), 0). That is, the local expected deservice time refers to the time interval between the target team completing the maintenance of the computer room and the actual deservice of the computer room.

[0123] In one feasible implementation, different weights can be set for different priorities to increase the proportion of different computer rooms in the total expected deservice time. Thus, the specific formula for the local expected deservice time can be: max(-si*(Ti–ti–v), 0), where Ti is the estimated deservice time of the i-th computer room, ti is the time it takes for the target team to move from the i-1th computer room to the i-th computer room, v is the theoretical time it takes for the target team to maintain a single computer room, and si is the weight corresponding to the priority.

[0124] Step S30216, moving the first computer room with the shortest local expected out-of-service time in the first computer room list to the second computer room list, returning to execute the step of determining the local expected out-of-service time of each first computer room in the first computer room list based on the route information, the estimated out-of-service time and the theoretical maintenance time, until the number of the first computer rooms reaches the preset threshold, and determining the order of moving the second computer rooms to the second computer room list as the maintenance order of each second computer room;

[0125] Select the computer room with the shortest local expected deservice time from the first computer room list, move it to the second computer room list, take out the computer room with the shortest local expected deservice time from the first computer room list, return to execute the step of determining the local expected deservice time of each first computer room in the first computer room list based on the route information, the estimated deservice time and the theoretical maintenance time, and recalculate the local expected deservice time of the remaining computer rooms. Repeat the above process until the number of computer rooms in the first computer room list reaches the preset threshold, and determine the movement order of the computer rooms in the second computer room list as their maintenance order. Step S30217, determine the traversal route based on each of the first computer rooms, and determine the route with the shortest total expected deservice time in each of the traversal routes as the local route, and determine the maintenance order of each of the first computer rooms based on the local route.

[0126] For the remaining first computer room, a full traversal algorithm is used to determine the maintenance order. Specifically, all possible traversal routes are generated, and the total expected deservice time is calculated for each traversal route. The calculation process of the total expected deservice time can be specifically referred to steps S20311 to S20314. The traversal route with the shortest total expected deservice time is selected as the local route, and the maintenance order of these computer rooms is determined according to the order of the computer rooms in the local route.

[0127] In this embodiment, multiple maintenance teams are determined based on maintenance resources and the room data of the room to be maintained. Based on the maintenance resources and the room data of the room to be maintained, multiple maintenance teams are intelligently determined, which can fully consider the number of maintenance personnel, skill level, vehicle and equipment and other maintenance resources. The resource status ensures the feasibility and efficiency of subsequent task allocation, and avoids the delay or poor execution of maintenance tasks caused by insufficient resources or improper allocation. Clustering is performed on each of the rooms to be maintained to obtain multiple groups of rooms to be maintained, and the maintenance teams corresponding to each group of rooms to be maintained are determined. Through the clustering algorithm, rooms with similar geographical locations or similar maintenance requirements can be combined to form a room to be maintained group, which can reduce the moving distance of the maintenance team between the rooms, thereby improving the maintenance efficiency. A maintenance team is assigned to each room to be maintained group, which can ensure the balanced distribution of tasks and avoid the situation where some teams have too heavy tasks and other teams have too light tasks. For any target computer room group in each group of computer rooms to be maintained, a maintenance order of each target computer room in the target computer room group is determined, wherein the target team performs maintenance on the target computer room group according to the maintenance order, and the target team is the maintenance team corresponding to the target computer room group. By determining the maintenance order for each group of computer rooms, it is possible to ensure that the maintenance team completes as much maintenance work as possible within a limited time, thereby improving maintenance efficiency.

[0128] In summary, this embodiment uses a clustering algorithm to group computer rooms and determine the maintenance order of computer rooms within the group, which can generate flexible and efficient task allocation plans and maintenance routes to adapt to the actual conditions of different computer rooms, thereby improving maintenance efficiency.

[0129] For example, to help understand the implementation process of the site maintenance method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief flow chart of a site maintenance method is provided, specifically:

[0130] Step 1: Determine the computer room to be maintained, obtain the relevant data of the dynamic environment alarm, extract the power outage alarm, determine the computer room that needs maintenance, and form a list of computer rooms to be maintained. At the same time, obtain basic data such as the geographical location, power outage level, and historical maintenance data of the computer room for subsequent analysis and optimization. Obtain "dynamic environment alarm" from the centralized alarm platform, and extract relevant information of "AC input power outage alarm" and "DC input power outage alarm", including the computer room name, alarm occurrence time, alarm clearing time, etc. According to the obtained dynamic environment alarm data, filter out the computer rooms in the "AC input power outage" or "DC input power outage" state to form a list of computer rooms to be maintained. De-duplicate and check the integrity of the list of computer rooms to be maintained to ensure the accuracy and uniqueness of the information.

[0131] Step 2: Determine the maintenance team. Determine the available maintenance team by obtaining the personnel, vehicles, equipment and other resource data of the maintenance team. Consider the team's skill level, number of personnel, equipment status and other factors, and arrange the maintenance force reasonably to ensure the smooth completion of the task. Obtain the currently available maintenance personnel information from the human resources system, including name, contact information, skill level, etc., and obtain the currently available maintenance vehicle information from the vehicle management system, including license plate number, load capacity, fuel volume, etc. According to the skill level and experience of the maintenance personnel, reasonably match and form multiple maintenance teams, and assign suitable maintenance vehicles to each maintenance team to ensure the team's mobility and equipment adequacy. The operator of the power-off maintenance route optimization tool for the computer room (generally the team leader) can set the number of dispatched maintenance teams k according to the actual situation of the current personnel, vehicles and other resources of the team. If the operator does not set it manually, it will be set automatically. The specific algorithm is: let the number of computer rooms to be allocated obtained by step 1 be N, the median of the straight-line distance between the computer rooms to be allocated be d (km), and let min (number of vehicles, number of personnel, number of oil engines) be r, which represents the value corresponding to the resource type with the least number of currently available resources. The specific algorithm is: the recommended number of dispatched teams k = max(min(ceiling(d / 3*N / 5), r, N), 1), where ceiling represents the rounding up function.

[0132] Step 3: Determine the maintenance task group through the Kmeans clustering algorithm. (1) Selection of the computer room to be assigned. The operator of the computer room power-off maintenance route optimization tool (generally the team leader) can select the computer room to be assigned from their own power-off maintenance computer room pool. If manual selection is not required, the tool defaults to selecting all the power-off rooms in the computer room pool of the team. (2) Determine the number of teams K based on Kmeans clustering, and use the clustering algorithm to divide each computer room to be assigned into K categories based on the coordinates of each computer room to be assigned. According to the number of dispatched teams K determined in step 2 and the geographic coordinate information of each computer room to be assigned obtained in step 1, use the K-means clustering algorithm to divide the computer rooms to be assigned into K categories, and each category corresponds to a dispatched maintenance team. The main steps are as follows: 1) Calculate the distance between each sample. The distance between each sample point in the conventional Kmeans clustering algorithm is generally Euclidean distance or Manhattan distance. The distance of the Kmeans clustering algorithm used in this tool needs to use the distance between two longitude and latitude points. The formula is:

[0133] R*arcos[cos(Y1)*cos(Y2)*cos(X1-X2)+sin(Y1)*sin(Y2)]

[0134] Among them, (X1, Y1) is the longitude and latitude of a point, (X2, Y2) is the longitude and latitude of another point, and R is the radius of the earth 6371; 2) Clustering process, according to the obtained K value as the algorithm parameter, cluster the rooms to be allocated, the input data of the Kmeans model is the longitude and latitude of each room to be allocated, and the output result is a plurality of classes formed by the aggregation of the rooms to be allocated. If K=1, the clustering algorithm does not need to be executed, and all are classified into the same class. By repeatedly executing the Kmeans algorithm U times, U results are generated, and U is currently set to 300.

[0135] For each clustering scheme, select the scheme with the best clustering effect and the most balanced task allocation. For each clustering scheme, calculate the balance index X: Let the total number of computer rooms to be allocated be N, the number of dispatched teams be K, then the average number of tasks per category W = N / K; let the number of tasks actually allocated to the i-th category (that is, the number of computer rooms to be allocated in this category) be Li, where i is an integer from 1 to K; balance index X = ∑i(Li–W) 2, that is, the sum of the squares of the differences between the actual number of tasks in each category and the average number of tasks. Where: N represents the total number of computer rooms to be assigned selected in step 1; K represents the number of dispatched teams determined in step 2; W represents the average number of tasks that should be assigned to each class (i.e., each team) under complete equilibrium; Li represents the number of tasks actually assigned to the i-th class under the current clustering scheme. Calculate the equilibrium index X of all U clustering schemes, and select the scheme with the smallest index as the optimal clustering scheme. The optimal scheme should meet the following conditions: good clustering effect, that is, the geographical locations of computer rooms within a class are close, and the geographical locations of computer rooms between classes are relatively far; balanced task distribution, that is, the actual number of tasks Li of each class is as close as possible to the average number of tasks W.

[0136] Step 4: Assign maintenance teams. According to the optimal clustering scheme, the set of rooms to be assigned to each category is taken as a maintenance task unit and assigned to a maintenance team. Specifically, according to the numbering order of the maintenance teams (such as team 1, team 2, ..., team K), the i-th category of rooms in the optimal clustering scheme is assigned to the i-th maintenance team, where i is an integer from 1 to K. In this way, each maintenance team corresponds to a room class and is responsible for the maintenance tasks of all rooms to be assigned in that class.

[0137] Step 5: Determine the maintenance execution sequence and plan the path. (1) Computer room outage timing: For the computer room in the maintenance task corresponding to each team, obtain the time of power outage and outage of the computer room. AC power outage indicates that the computer room is out of power, and DC power outage indicates that the battery is exhausted and the computer room is out of service. If the computer room has both AC power outage and DC power outage alarms, mark "computer room outage timing" T = 0, indicating that the base station in the computer room has been out of service. If the computer room only has AC power outage alarms, mark "computer room outage timing" T = max(0, computer room battery storage time - (current time - AC power outage alarm time)). Note that "computer room battery storage time" is an estimated value. Computer room battery storage time - (current time - AC power outage alarm time) may be negative, which means that the computer room battery may be exhausted at any time. If the AC power outage alarm of the computer room is eliminated, that is, "alarm clearing time" has been updated and is not empty, it means that the AC power outage has been restored, and the computer room is removed from the maintenance task. (2) Obtaining route information between nodes. The current real-time road conditions, such as traffic congestion and road construction, need to be obtained by calling the Internet map API in real time, and the relevant routes are planned and the required time is calculated. For the computer room in the maintenance task corresponding to each team, the route information is obtained, that is, the Internet map interface is called to obtain the routes, route duration and route length between each computer room, and the routes, route duration and route length from the team station to each computer room are obtained as basic data for subsequent optimization calculations. The route information can be shown in Table 1 below. Assuming that the number of task computer rooms of the team is 5, the number of basic data is arranged as A(5, 2) + 5 = 25, and the strategy parameter is set to 5. Specifically, multiple strategies can be used for path planning, for example, speed priority, cost priority, and distance priority strategies are used to calculate the path at the same time.

[0138] Table 1 Route information

[0139]

[0140] (3) Priority sorting of computer rooms. Different computer rooms have different maintenance levels because the base stations in the computer rooms serve different areas. This data can be obtained from the basic information of the computer rooms. In this tool, computer rooms are divided into maintenance levels 1 to 4, with 1 being the highest priority and 4 being the lowest.

[0141] (4) Path optimization planning. To consider the maintenance priority of the computer room, the calculated outage time q of the computer room with maintenance level 1 is set to 4 times the actual outage time; the calculated outage time q of the computer room with maintenance level 2 is set to 3 times the actual outage time; the calculated outage time q of the computer room with maintenance level 3 is set to 2 times the actual outage time; and the calculated outage time q of the computer room with maintenance level 4 is set to be the same as the actual outage time. Therefore, the actual outage time of the computer room with high priority has a greater impact on the result. The maintenance priority factor of the computer room is fully considered in the algorithm, so that the tool tends to give priority to the computer room with high priority, but at the same time, it will consider the distance advantage of the computer room with low priority. The formula can be: z*=argminz(∑n qi), where z is the order of the maintenance team to maintain the computer room, qi=si*(Ti–ti), and the actual outage time is equal to the outage time T of each computer room obtained in the first step of the previous article minus the time t required for the computer room to complete the maintenance. The actual service withdrawal time is multiplied by the coefficient of the data center priority mentioned above to calculate the service withdrawal time q.

[0142] When the number of task rooms of the maintenance team is ≤9, the full traversal algorithm is used. Assume that the number of rooms is N. The maintenance team starts from the maintenance team station and maintains N rooms, with a total of N! *N ways of walking. The tool traverses and calculates each way and gives the one with the shortest expected out-of-service time to obtain the maintenance sequence z. For example, the scheme is set as station O->A->B->C. The out-of-service timings of rooms A, B, and C can be obtained as Ta, Tb, and Tc respectively. From (2), the time required for OA, AB, and BC can be set as ta, tb, and tc respectively. Assume that the maintenance level of room A is 1, B is 2, and C is 4. The tool sets the maintenance time for each room as v. The expected out-of-service time of the scheme can be calculated as:

[0143] ∑n qi=max(-(Ta–ta–v), 0)*4+max(-(Tb-ta–tb–2*v)*3, 0)+max(-(Tc-ta–tb–tc-3*v), 0), where -(Ta–ta–v) is the expected decommissioning time of the computer room. If it is negative, it means that the computer room will not be decommissioned. The calculated decommissioning time of the computer room is 0, and the maintenance order z* with the smallest ∑n qi is taken.

[0144] When the number of task rooms for a maintenance team is greater than 9, the tool calculation efficiency is affected. In this case, the "greedy algorithm" combined with the traversal algorithm is used for optimization. The greedy algorithm finds a local optimal solution at each step, and finally combines them to form an overall better solution. Suppose the number of tasks for a maintenance team in a certain team is N (N>9). The greedy algorithm is used in the first N-9 steps, and the traversal algorithm described in (1) is used to optimize the routes of the following 9 computer rooms. The first step is to find which computer room should be visited first when starting from the station O. The calculated outage time of each computer room is qi = max(-si*(Ti–ti-v), 0), where i represents the i-th computer room. Therefore, the maintenance team should first go to the computer room with the largest q. If there are identical q, the maintenance team should choose the one with a higher maintenance priority. If the priorities are the same, the one with a shorter arrival time should be chosen. The second step is to optimize and determine the calculated out-of-service time of each computer room from the computer room maintained in the first step to the next computer room: qi = max(-si*(Ti–ti–t1–2*v), 0)2, i represents the N-1 remaining computer rooms. Therefore, the maintenance team should first go to the computer room with the largest q. If there are the same q, choose the one with a higher maintenance priority. If the priorities are the same, choose the one with a shorter arrival time. The above process is repeated until there are only 9 computer rooms left, and the full traversal algorithm is executed.

[0145] After obtaining the maintenance team's on-site order through optimization, the specific path is obtained through the path field data, which is the longitude and latitude point vector. These points are projected onto the map and connected in order to form the planned optimization path.

[0146] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the site maintenance method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0147] This application also provides a site maintenance device, please refer to Figure 4 , the site maintenance device comprises:

[0148] A determination module 10, for determining multiple maintenance teams based on maintenance resources and computer room data of the computer room to be maintained;

[0149] A clustering module 20, for clustering the machine rooms to be maintained to obtain a plurality of machine room groups to be maintained, and determining a maintenance team corresponding to each of the machine room groups to be maintained;

[0150] The maintenance module 30 is used to determine the maintenance order of each target computer room in the target computer room group for any target computer room group in each group of computer rooms to be maintained, wherein the target team maintains the target computer room group according to the maintenance order, and the target team is the maintenance team corresponding to the target computer room group.

[0151] Optionally, the clustering module 20 is further configured to:

[0152] According to the number of the maintenance teams, a plurality of initial cluster centroids are determined from each of the computer rooms to be maintained;

[0153] Traversing each of the machine rooms to be maintained, determining the cluster distance between the machine room to be maintained and each of the initial clustering centroids, and allocating the machine room to be maintained to the cluster cluster to which the initial clustering centroid with the smallest clustering distance belongs;

[0154] The cluster centers of the clusters are determined, and the cluster centers are iterated on each cluster until a preset clustering condition is met to obtain a plurality of target clusters, and each target cluster is determined as a group of computer rooms to be maintained.

[0155] Optionally, the maintenance module 30 is further used for:

[0156] Based on the power-off status of each target computer room in the target computer room group, determining the estimated outage duration of each target computer room, and obtaining route information between each target computer room;

[0157] Based on the route information and the estimated deservice time, path planning is performed with the goal of minimizing the total expected deservice time of the target computer room group, and the maintenance order of each target computer room is obtained, wherein the total expected deservice time is the time interval between the target team completing maintenance of the target computer room group and the deservice of the target computer room group.

[0158] Optionally, the clustering module 20 is further configured to:

[0159] Determine a first number of each of the target computer rooms in the target computer room group;

[0160] The step of performing path planning based on the route information and each of the estimated out-of-service durations with the goal of minimizing the total expected out-of-service duration of the target computer room group to obtain the maintenance sequence of each of the target computer rooms comprises:

[0161] Based on the first quantity, the route information and the estimated outage durations, path planning is performed with the goal of minimizing the total expected outage duration of the target computer room group to obtain a maintenance order for each of the target computer rooms.

[0162] Optionally, the clustering module 20 is further configured to:

[0163] If the first number is less than or equal to a preset threshold, traverse each of the target computer rooms starting from the stationing location of the target team to obtain multiple theoretical routes;

[0164] For the target routes in each of the theoretical routes, based on the route information, each of the estimated decommissioning time, the theoretical maintenance time, and the traversal order of each of the target computer rooms, the expected decommissioning time of each of the target computer rooms is determined, wherein the expected decommissioning time of the computer room is the time interval between the target team completing maintenance of each of the target computer rooms and decommissioning each of the target computer rooms when the target team performs maintenance on the target computer room group according to the theoretical route;

[0165] Determine the total expected out-of-service duration corresponding to the target line based on the expected out-of-service duration of each target computer room;

[0166] The theoretical line with the smallest total expected out-of-service time among the theoretical lines is determined as the maintenance line, and the maintenance order of each of the target computer rooms is determined based on the maintenance line.

[0167] Optionally, the clustering module 20 is further configured to:

[0168] If the first number is greater than the preset threshold, each of the target computer rooms is added to the first computer room list, and based on the route information, the estimated service withdrawal time and the theoretical maintenance time, the local expected service withdrawal time of each first computer room in the first computer room list is determined, wherein the local expected service withdrawal time is the time interval between the target team completing the maintenance of the first computer room and the service withdrawal of the first computer room;

[0169] Move the first computer room with the shortest local expected out-of-service time in the first computer room list to the second computer room list, return to the step of determining the local expected out-of-service time of each first computer room in the first computer room list based on the route information, the estimated out-of-service time and the theoretical maintenance time, until the number of the first computer rooms reaches the preset threshold, and determine the order in which the second computer rooms are moved to the second computer room list as the maintenance order of each second computer room;

[0170] A traversal route is determined based on each of the first computer rooms, and a route with the shortest total expected out-of-service time among the traversal routes is determined as a local route, and a maintenance order of each of the first computer rooms is determined based on the local route.

[0171] Optionally, the determining module 10 is further configured to:

[0172] Based on the computer room data of the computer rooms to be maintained, determine the straight-line distance between any two of the computer rooms to be maintained, determine the median of each of the straight-line distances as the target distance, and determine the first value based on the target distance and the second number of each of the computer rooms to be maintained;

[0173] Determine the number of vehicles, the number of maintenance personnel, and the number of oil engines based on the maintenance resources of the machine room, and determine the minimum value among the number of vehicles, the number of maintenance personnel, and the number of oil engines as a second value;

[0174] The minimum value among the first value, the second value and the second number is determined as the third value, and the maximum value between the third value and the preset number is determined as the team number, and multiple maintenance teams are determined according to the team number.

[0175] Optionally, the determining module 10 is further configured to:

[0176] Acquire dynamic ring alarm data, and determine AC power outage information and DC power outage information from the dynamic ring alarm data;

[0177] The computer room corresponding to the AC power outage information and the DC power outage information is determined as the computer room to be maintained.

[0178] The site maintenance device provided by the present application adopts the site maintenance method in the above embodiment, which can solve the technical problem that the current allocation of operation and maintenance tasks for the computer room of the faulty site is unreasonable, resulting in the operation and maintenance efficiency of the computer room operation and maintenance based on task allocation being affected. Compared with the prior art, the beneficial effects of the site maintenance device provided by the present application are the same as the beneficial effects of the site maintenance method provided by the above embodiment, and other technical features in the site maintenance device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0179] The present application provides a site maintenance device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the site maintenance method in the above-mentioned embodiment.

[0180] Reference below Figure 5 , which shows a structural schematic diagram of a site maintenance device suitable for implementing an embodiment of the present application. Figure 5 The site maintenance device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0181] like Figure 5As shown, the site maintenance device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the site maintenance device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the site maintenance device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a site maintenance device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0182] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0183] The site maintenance device provided by the present application adopts the site maintenance method in the above embodiment, which can solve the technical problem that the current allocation of operation and maintenance tasks for the computer room of the faulty site is unreasonable, resulting in the operation and maintenance efficiency of the computer room operation and maintenance based on task allocation being affected. Compared with the prior art, the beneficial effects of the site maintenance device provided by the present application are the same as the beneficial effects of the site maintenance method provided by the above embodiment, and the other technical features in the site maintenance device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0184] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0185] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0186] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the site maintenance method in the above-mentioned embodiment.

[0187] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0188] The computer-readable storage medium may be included in the site maintenance device; or may exist independently without being assembled into the site maintenance device.

[0189] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the site maintenance device, the site maintenance device implements the solution of the above embodiment.

[0190] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0191] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0192] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0193] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned site maintenance method, and can solve the technical problem that the current allocation of operation and maintenance tasks for the computer room of the faulty site is unreasonable, resulting in the operation and maintenance efficiency of the computer room operation and maintenance based on task allocation being affected. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the site maintenance method provided by the above-mentioned embodiment, and will not be repeated here.

[0194] The present application also provides a computer program product, including a computer program, which implements the steps of the site maintenance method as described above when executed by a processor.

[0195] The computer program product provided by the present application can solve the technical problem that the current allocation of operation and maintenance tasks for the computer room of the fault site is unreasonable, resulting in the operation and maintenance efficiency of the computer room operation and maintenance based on task allocation being affected. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the site maintenance method provided by the above embodiment, and will not be repeated here.

[0196] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A site maintenance method, characterized in that: The site maintenance method comprises: Determine multiple maintenance teams based on maintenance resources and computer room data of computer rooms to be maintained; Clustering the machine rooms to be maintained to obtain multiple groups of machine rooms to be maintained, and determining the maintenance team corresponding to each group of machine rooms to be maintained; For any target computer room group in each group of computer rooms to be maintained, a maintenance order of each target computer room in the target computer room group is determined, wherein a target team maintains the target computer room group according to the maintenance order, and the target team is a maintenance team corresponding to the target computer room group.

2. The site maintenance method according to claim 1, characterized in that: The step of clustering the machine rooms to be maintained to obtain multiple groups of machine rooms to be maintained includes: According to the number of the maintenance teams, a plurality of initial cluster centroids are determined from each of the computer rooms to be maintained; Traversing each of the machine rooms to be maintained, determining the cluster distance between the machine room to be maintained and each of the initial clustering centroids, and allocating the machine room to be maintained to the cluster cluster to which the initial clustering centroid with the smallest clustering distance belongs; The cluster centers of the clusters are determined, and the cluster centers are iterated on each cluster until a preset clustering condition is met to obtain a plurality of target clusters, and each target cluster is determined as a group of computer rooms to be maintained.

3. The site maintenance method according to claim 1, characterized in that: The step of determining the maintenance order of each target computer room in the target computer room group includes: Based on the power-off status of each target computer room in the target computer room group, determining the estimated outage duration of each target computer room, and obtaining route information between each target computer room; Based on the route information and the estimated deservice time, path planning is performed with the goal of minimizing the total expected deservice time of the target computer room group, and the maintenance order of each target computer room is obtained, wherein the total expected deservice time is the time interval between the target team completing maintenance of the target computer room group and the deservice of the target computer room group.

4. The site maintenance method according to claim 3, characterized in that: Before the step of performing path planning based on the route information and each of the estimated out-of-service durations with the goal of minimizing the total expected out-of-service duration of the target computer room group to obtain the maintenance sequence of each of the target computer rooms, the step further includes: Determine a first number of each of the target computer rooms in the target computer room group; The step of performing path planning based on the route information and the estimated outage durations to minimize the total expected outage duration of the target computer room group to obtain the maintenance sequence of each of the target computer rooms comprises: Based on the first quantity, the route information and the estimated outage durations, path planning is performed with the goal of minimizing the total expected outage duration of the target computer room group to obtain a maintenance order for each of the target computer rooms.

5. The site maintenance method according to claim 4, characterized in that: The step of performing path planning based on the first quantity, the route information and the estimated outage durations to minimize the total expected outage duration of the target computer room group to obtain the maintenance sequence of each of the target computer rooms comprises: If the first number is less than or equal to a preset threshold, traverse each of the target computer rooms starting from the stationing location of the target team to obtain multiple theoretical routes; For the target routes in each of the theoretical routes, based on the route information, each of the estimated decommissioning time, the theoretical maintenance time, and the traversal order of each of the target computer rooms, the expected decommissioning time of each of the target computer rooms is determined, wherein the expected decommissioning time of the computer room is the time interval between the target team completing maintenance of each of the target computer rooms and decommissioning each of the target computer rooms when the target team performs maintenance on the target computer room group according to the theoretical route; Determine the total expected out-of-service duration corresponding to the target line based on the expected out-of-service duration of each target computer room; The theoretical line with the smallest total expected out-of-service time among the theoretical lines is determined as the maintenance line, and the maintenance order of each of the target computer rooms is determined based on the maintenance line.

6. The site maintenance method according to claim 5, characterized in that: The step of performing path planning based on the first quantity, the route information and the estimated outage durations to minimize the total expected outage duration of the target computer room group to obtain the maintenance sequence of each of the target computer rooms comprises: If the first number is greater than the preset threshold, each of the target computer rooms is added to the first computer room list, and based on the route information, the estimated service withdrawal time and the theoretical maintenance time, the local expected service withdrawal time of each first computer room in the first computer room list is determined, wherein the local expected service withdrawal time is the time interval between the target team completing the maintenance of the first computer room and the service withdrawal of the first computer room; Move the first computer room with the shortest local expected out-of-service time in the first computer room list to the second computer room list, return to the step of determining the local expected out-of-service time of each first computer room in the first computer room list based on the route information, the estimated out-of-service time and the theoretical maintenance time, until the number of the first computer rooms reaches the preset threshold, and determine the order in which the second computer rooms are moved to the second computer room list as the maintenance order of each second computer room; A traversal route is determined based on each of the first computer rooms, and a route with the shortest total expected out-of-service time among the traversal routes is determined as a local route, and a maintenance order of each of the first computer rooms is determined based on the local route.

7. The site maintenance method according to claim 1, characterized in that: The step of determining multiple maintenance teams based on maintenance resources and computer room data of computer rooms to be maintained includes: Based on the computer room data of the computer rooms to be maintained, determine the straight-line distance between any two of the computer rooms to be maintained, determine the median of each of the straight-line distances as the target distance, and determine the first value based on the target distance and the second number of each of the computer rooms to be maintained; Determine the number of vehicles, the number of maintenance personnel, and the number of oil engines based on the maintenance resources of the machine room, and determine the minimum value among the number of vehicles, the number of maintenance personnel, and the number of oil engines as a second value; The minimum value among the first value, the second value and the second number is determined as the third value, and the maximum value between the third value and the preset number is determined as the team number, and multiple maintenance teams are determined according to the team number.

8. The site maintenance method according to any one of claims 1 to 7, characterized in that: Before the step of determining multiple maintenance teams based on the maintenance resources and the computer room data of the computer room to be maintained, the method further includes: Acquire dynamic ring alarm data, and determine AC power outage information and DC power outage information from the dynamic ring alarm data; The computer room corresponding to the AC power outage information and the DC power outage information is determined as the computer room to be maintained.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the site maintenance method according to any one of claims 1 to 8 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the site maintenance method according to any one of claims 1 to 8 are implemented.

Images