Operation and maintenance task scheduling method based on operation and maintenance data

Abstract

The invention discloses an operation and maintenance task scheduling method based on operation and maintenance data, and relates to the technical field of operation and maintenance management. The method comprises the steps of initializing an operation and maintenance task set, an operation and maintenance resource set, a first time matrix and a second time matrix; a population is initialized, the population comprises a plurality of individuals in one-to-one correspondence with the operation and maintenance tasks, and an operation and maintenance resource sequence occupied by the corresponding operation and maintenance task is recorded in each individual; based on the first time matrix and the second time matrix, according to a preset task execution logic, solving a fitness value, inversely proportional to the spent time of the operation and maintenance task, of each individual; performing crossover and mutation operation on individuals with fitness values lower than a first preset threshold value in the population so as to iteratively update the population; and when an iteration termination condition is reached or the number of iterations reaches a preset maximum number of iterations, determining an operation and maintenance task scheduling scheme based on the operation and maintenance resource sequence occupied by the operation and maintenance task corresponding to each individual in the latest population. The method disclosed by the invention can improve the utilization rate of operation and maintenance resources and reduce the operation and maintenance cost.

Description

Technical Field

[0001] The present invention belongs to the technical field of operation and maintenance management, and in particular relates to an operation and maintenance task scheduling method based on operation and maintenance data. Background Art

[0002] Network operation and maintenance refers to a series of activities to operate and maintain the network system to ensure the stability, security, efficiency and scalability of the network. In today's highly information-based era, network operation and maintenance task scheduling plays an increasingly important role.

[0003] At present, most of the existing operation and maintenance task scheduling schemes are manually scheduled by operation and maintenance personnel. The operation and maintenance task scheduling relies on the experience and judgment of the operation and maintenance personnel. For large-scale concurrent multi-task scheduling, it is often impossible to guarantee reasonable task scheduling, resulting in low utilization of operation and maintenance resources and increased operation and maintenance costs.

[0004] Therefore, how to provide an effective solution to improve the utilization of operation and maintenance resources and reduce operation and maintenance costs has become an urgent problem to be solved in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide an operation and maintenance task scheduling method based on operation and maintenance data to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides an operation and maintenance task scheduling method based on operation and maintenance data, comprising:

[0008] Based on the system logs, performance indicators and fault records of the network devices corresponding to each of the multiple operation and maintenance tasks to be processed, the priority and complexity corresponding to each of the multiple operation and maintenance tasks are determined through a pre-established operation and maintenance data model;

[0009] Based on the complexity of the operation and maintenance tasks, determine the time required for each operation and maintenance resource among multiple operation and maintenance resources to perform each operation and maintenance task;

[0010] Initialize an operation and maintenance task set, an operation and maintenance resource set, a first time matrix, and a second time matrix, wherein the operation and maintenance task set includes the multiple operation and maintenance tasks, the operation and maintenance resource set includes the multiple operation and maintenance resources, the first time matrix records the time required for each operation and maintenance resource in the operation and maintenance resource set to execute each operation and maintenance task in the operation and maintenance task set, and the second time matrix records the time spent by the operation and maintenance resources from the completion time of the previous operation and maintenance task to the start time of the next operation and maintenance task between any two adjacent operation and maintenance tasks;

[0011] Initializing a population, the population including a plurality of individuals corresponding to the plurality of operation and maintenance tasks, each individual recording a sequence of operation and maintenance resources occupied by the corresponding operation and maintenance task;

[0012] Based on the first time matrix and the second time matrix, solving the fitness value of each individual and inversely proportional to the time spent on the operation and maintenance task according to the preset task execution logic, wherein the preset task execution logic indicates that for multiple operation and maintenance tasks corresponding to the same operation and maintenance resource, the operation and maintenance task with a higher priority is executed before the operation and maintenance task with a lower priority, the operation and maintenance task with the earliest required completion time of two operation and maintenance tasks with the same priority is executed before the operation and maintenance task with the latest required completion time, and the operation and maintenance task with a shorter time spent on two operation and maintenance tasks with the same priority and the same latest required completion time is executed before the operation and maintenance task with a shorter time spent on two tasks;

[0013] Performing crossover and mutation operations on individuals in the population whose fitness values ​​are lower than a first preset threshold, so as to iteratively update the population;

[0014] When the iteration termination condition is reached or the number of iterations reaches the preset maximum number of iterations, an operation and maintenance task scheduling plan is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population.

[0015] Based on the above disclosed content, the present invention determines the priority and complexity corresponding to each operation and maintenance task in the multiple operation and maintenance tasks through a pre-established operation and maintenance data model based on the system logs, performance indicators and fault records of the network devices corresponding to each operation and maintenance task in the multiple operation and maintenance tasks to be processed; determines the time required for each operation and maintenance resource in the multiple operation and maintenance resources to execute each operation and maintenance task based on the complexity corresponding to the operation and maintenance task; initializes the operation and maintenance task set, the operation and maintenance resource set, the first time matrix and the second time matrix; initializes the population, the population includes multiple individuals corresponding to the multiple operation and maintenance tasks one by one, and each individual records the operation and maintenance resource sequence occupied by the corresponding operation and maintenance task; based on the first time matrix and the second time matrix, solves the fitness value of each individual and inversely proportional to the time spent on the operation and maintenance task according to the preset task execution logic; performs crossover and mutation operations on individuals in the population whose fitness values ​​are lower than the first preset threshold value to iteratively update the population; when the iteration termination condition is reached or the number of iterations reaches the preset maximum number of iterations, determines the operation and maintenance task scheduling plan based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population. In this way, through the indirect coding method of operation and maintenance tasks and operation and maintenance resources, combined with individual crossover and mutation, large-scale concurrent multi-task scheduling can be transformed into a scheduling scheme based on genetic algorithms for overall optimization. Therefore, while meeting the operational requirements of operation and maintenance tasks, the overall completion time of operation and maintenance tasks can be shortened, the utilization rate of operation and maintenance resources can be improved, and the operation and maintenance costs in network operation and maintenance can be minimized, ensuring the stability and reliability of the network.

[0016] In one possible design, initializing the first time matrix and the second time matrix includes:

[0017] Determine the time required for various operation and maintenance tasks and the time spent between the completion time of the previous operation and maintenance task and the start time of the next operation and maintenance task in any two adjacent operation and maintenance tasks based on historical operation and maintenance records;

[0018] Based on the time required for various operation and maintenance tasks and the time spent between the completion time of the previous operation and maintenance task and the start time of the next operation and maintenance task of any two adjacent operation and maintenance tasks, the first time matrix and the second time matrix are initialized.

[0019] In a possible design, the step of solving the fitness value of each individual and inversely proportional to the time spent on the operation and maintenance task according to the preset task execution logic based on the first time matrix and the second time matrix includes:

[0020] Based on the first time matrix and the second time matrix, solving the time spent on the operation and maintenance tasks of each individual according to the preset task execution logic;

[0021] Determine the fitness value of each individual based on the time spent on the operation and maintenance tasks of each individual;

[0022] The fitness value of any individual is the reciprocal of the time spent on the operation and maintenance task of the individual.

[0023] In a possible design, the time spent on each operation and maintenance resource in the operation and maintenance task is Where fin(i, j) represents the time spent by operation and maintenance resource j in operation and maintenance task i, T(i, j) represents the duration of operation and maintenance resource j executing operation and maintenance task i, E(i, j) represents the start time of operation and maintenance task i on operation and maintenance resource j, max(end(pre(j))) represents the latest time for operation and maintenance resource j to complete the previous task, and Tm(i) represents the time spent by operation and maintenance resource j from the completion time of the previous operation and maintenance task to the start time of operation and maintenance task i.

[0024] In a possible design, crossover and mutation operations are performed on individuals in the population whose fitness values ​​are lower than a first preset threshold to iteratively update the population, including:

[0025] Generate a random number k as the hybridization point of the individual, where 0≤k<n, and n represents the length of the individual;

[0026] Exchanging the target individuals whose fitness values ​​in the population are lower than a first preset threshold and located after the hybridization point to obtain new individuals;

[0027] Performing a mutation operation on at least one of the new individuals to obtain a mutant individual;

[0028] Calculate the fitness value corresponding to the new individual and the fitness value corresponding to the mutated individual;

[0029] Based on the fitness value corresponding to the target individual, the fitness value corresponding to the new individual and the fitness value corresponding to the mutated individual, the target individual in the population is iteratively updated to obtain an updated population.

[0030] In a possible design, the target individual in the population is iteratively updated based on the fitness value corresponding to the target individual, the fitness value corresponding to the new individual, and the fitness value corresponding to the mutated individual, including:

[0031] For a first target individual that has a corresponding variant individual, select an individual with the largest corresponding fitness value from among the first target individual, the new individual corresponding to the first target individual, and the variant individual corresponding to the first target individual as an updated individual of the first target individual;

[0032] For a second target individual without strained individuals, one of the individuals with the largest corresponding fitness value is selected from the second target individual and the new individual corresponding to the second target individual as the updated individual of the second target individual.

[0033] In a possible design, when the iteration termination condition is reached or the number of iterations reaches a preset maximum number of iterations, an operation and maintenance task scheduling scheme is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population, including:

[0034] Determine whether the fitness values ​​corresponding to each individual in the latest population are all lower than a second preset threshold or whether the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is lower than a preset duration, wherein the second preset threshold is greater than or equal to the first preset threshold;

[0035] If the fitness values ​​corresponding to each individual are lower than the second preset threshold or the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is lower than the preset duration, the iteration is stopped, and the operation and maintenance task scheduling plan is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population;

[0036] If there are individuals whose corresponding fitness values ​​are all lower than the second preset threshold or the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is longer than the preset duration, crossover and mutation operations will continue to be performed on the individuals in the population whose fitness values ​​are lower than the first preset threshold until the number of iterations reaches the preset maximum number of iterations, and the operation and maintenance task scheduling plan is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population.

[0037] In a second aspect, the present invention provides an operation and maintenance task scheduling device based on operation and maintenance data, comprising:

[0038] A first determination unit is used to determine the priority and complexity corresponding to each of the multiple operation and maintenance tasks based on the system log, performance index and fault record of the network device corresponding to each of the multiple operation and maintenance tasks to be processed through a pre-established operation and maintenance data model;

[0039] A second determination unit is used to determine the time required for each operation and maintenance resource among the multiple operation and maintenance resources to perform each operation and maintenance task based on the complexity corresponding to the operation and maintenance task;

[0040] A first initialization unit is used to initialize an operation and maintenance task set, an operation and maintenance resource set, a first time matrix, and a second time matrix. The operation and maintenance task set includes the multiple operation and maintenance tasks, the operation and maintenance resource set includes the multiple operation and maintenance resources, the first time matrix records the time required for each operation and maintenance resource in the operation and maintenance resource set to execute each operation and maintenance task in the operation and maintenance task set, and the second time matrix records the time spent by the operation and maintenance resources from the completion time of the previous operation and maintenance task to the start time of the next operation and maintenance task in any two adjacent operation and maintenance tasks;

[0041] A second initialization unit is used to initialize a population, wherein the population includes a plurality of individuals corresponding to the plurality of operation and maintenance tasks one by one, and each individual records a sequence of operation and maintenance resources occupied by the corresponding operation and maintenance task;

[0042] a computing unit, configured to solve, based on the first time matrix and the second time matrix, the fitness value of each individual and inversely proportional to the time taken by the operation and maintenance task according to a preset task execution logic, wherein the preset task execution logic indicates that for multiple operation and maintenance tasks corresponding to the same operation and maintenance resource, an operation and maintenance task with a higher priority is executed before an operation and maintenance task with a lower priority, an operation and maintenance task with an earlier required completion time among two operation and maintenance tasks with the same priority is executed before an operation and maintenance task with a later required completion time, and an operation and maintenance task with a shorter time taken among two operation and maintenance tasks with the same priority and the same latest required completion time is executed before an operation and maintenance task with a shorter time taken;

[0043] An updating unit, used for performing crossover and mutation operations on individuals in the population whose fitness values ​​are lower than a first preset threshold, so as to iteratively update the population;

[0044] The third determining unit is used to determine the operation and maintenance task scheduling plan based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population when the iteration termination condition is reached or the number of iterations reaches a preset maximum number of iterations.

[0045] In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute an operation and maintenance task scheduling method based on operation and maintenance data as described in the first aspect or any possible design of the first aspect.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, executes the operation and maintenance task scheduling method based on operation and maintenance data as described in the first aspect or any possible design of the first aspect.

[0047] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute an operation and maintenance task scheduling method based on operation and maintenance data as described in the first aspect or any possible design of the first aspect.

[0048] Beneficial effects:

[0049] The operation and maintenance task scheduling method based on operation and maintenance data provided by the present invention can transform large-scale concurrent multi-task scheduling into a scheduling scheme based on genetic algorithm for overall optimization by indirect coding of operation and maintenance tasks and operation and maintenance resources, thereby shortening the completion time of operation and maintenance tasks as a whole and improving the utilization rate of operation and maintenance resources while meeting the operational requirements of operation and maintenance tasks, thereby maximizing the reduction of operation and maintenance costs in network operation and maintenance, ensuring the stability and reliability of the network, and facilitating practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of an operation and maintenance task scheduling method based on operation and maintenance data provided in an embodiment of the present application;

[0051] Figure 2 A schematic block diagram of an operation and maintenance task scheduling device based on operation and maintenance data provided in an embodiment of the present application;

[0052] Figure 3 A schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0054] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0055] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0056] In order to facilitate the scheduling of operation and maintenance tasks, an embodiment of the present application provides an operation and maintenance task scheduling method based on operation and maintenance data. The operation and maintenance task scheduling method based on operation and maintenance data can improve the utilization rate of operation and maintenance resources and reduce operation and maintenance costs.

[0057] The operation and maintenance task scheduling method based on operation and maintenance data provided in the embodiment of the present application can be applied to a terminal device or server for operation and maintenance task scheduling. It can be understood that the execution subject does not constitute a limitation on the embodiment of the present application.

[0058] The following is a detailed description of the operation and maintenance task scheduling method based on operation and maintenance data provided in an embodiment of the present application.

[0059] like Figure 1 As shown, it is a flowchart of the operation and maintenance task scheduling method based on operation and maintenance data provided in the first aspect of the embodiment of the present application. The operation and maintenance task scheduling method based on operation and maintenance data may include but is not limited to the following steps S101-S107.

[0060] Step S101. Based on the system logs, performance indicators and fault records of the network devices corresponding to each of the multiple operation and maintenance tasks to be processed, the priority and complexity corresponding to each of the multiple operation and maintenance tasks are determined through a pre-established operation and maintenance data model.

[0061] In an embodiment of the present application, an operation and maintenance data model for determining operation and maintenance tasks is pre-trained. When it is necessary to perform operation and maintenance on network equipment in a network system, the system logs, performance indicators, and fault records of the network equipment corresponding to each of the multiple operation and maintenance tasks can be used as inputs to the operation and maintenance data model for analysis to obtain the priority and complexity corresponding to each of the multiple operation and maintenance tasks.

[0062] The system log of the network device may include but is not limited to the log level (such as information level INFO, warning level WARING or error level ERROR) or system security events (such as login attempts, authorized access, denial of service attacks or intrusion detection and other security-related event related information). Performance indicators may include but are not limited to the CPU usage, memory usage, disk I / O or network traffic of the network device. Fault records may include but are not limited to the fault type, occurrence time or impact scope of the fault of the network device.

[0063] When training the operation and maintenance data model, the historical system logs, historical performance indicators and historical fault records of the network devices corresponding to each historical operation and maintenance task can be used as sample inputs, and the priority and complexity corresponding to each historical operation and maintenance task can be used as sample outputs for training. The priority and complexity corresponding to each historical operation and maintenance task can be marked by the operation and maintenance personnel.

[0064] Step S102: Based on the complexity corresponding to the operation and maintenance task, determine the time required for each operation and maintenance resource among the multiple operation and maintenance resources to execute each operation and maintenance task.

[0065] Among them, operation and maintenance resources can be but are not limited to operation and maintenance personnel involved in network operation and maintenance. The time required for operation and maintenance resources (such as operation and maintenance personnel) to perform operation and maintenance tasks can be obtained based on the complexity of the operation and maintenance tasks and the statistical analysis of the historical operation and maintenance task completion of the operation and maintenance resources.

[0066] Step S103: Initialize an operation and maintenance task set, an operation and maintenance resource set, a first time matrix, and a second time matrix.

[0067] The operation and maintenance task set includes multiple operation and maintenance tasks, and the operation and maintenance resource set includes multiple operation and maintenance resources. The first time matrix records the time required for each operation and maintenance resource in the operation and maintenance resource set to execute each operation and maintenance task in the operation and maintenance task set, and the second time matrix records the time spent by the operation and maintenance resource from the completion time of the previous operation and maintenance task to the start time of the next operation and maintenance task between any two adjacent operation and maintenance tasks.

[0068] When initializing the first time matrix and the second time matrix, the time required for various operation and maintenance tasks and the time consumed between the completion time of the previous operation and maintenance task and the start time of the next operation and maintenance task between any two adjacent operation and maintenance tasks can be determined according to historical operation and maintenance records. Then, based on the time required for various operation and maintenance tasks and the time consumed between the completion time of the previous operation and maintenance task and the start time of the next operation and maintenance task between any two adjacent operation and maintenance tasks, the first time matrix and the second time matrix are initialized.

[0069] Step S104: Initialize a population, the population including a plurality of individuals corresponding to a plurality of operation and maintenance tasks, each individual recording a sequence of operation and maintenance resources occupied by the corresponding operation and maintenance task.

[0070] In genetic algorithms, chromosome encoding can be divided into two encoding methods: direct encoding and spacing encoding. In the embodiment of the present application, the spacing encoding method is used to encode the operation and maintenance resources occupied by each operation and maintenance task, and the operation and maintenance resources occupied by multiple operation and maintenance tasks are encoded as an individual (chromosome) to obtain multiple individuals. That is, each individual corresponds to multiple operation and maintenance tasks (the number of operation and maintenance tasks in an individual is the length of the individual), and each task corresponds to an operation and maintenance resource sequence, and the operation and maintenance resource sequence records the number of the operation and maintenance resources occupied by the operation and maintenance task.

[0071] For example, for a certain individual, it includes three operation and maintenance tasks, namely, operation and maintenance tasks r1, r2, and r3. The operation and maintenance resources occupied by operation and maintenance task r1 are operation and maintenance resources z1 and z2, the operation and maintenance resources occupied by operation and maintenance task r2 are operation and maintenance resources z2 and z3, and the operation and maintenance resources occupied by operation and maintenance task r3 are operation and maintenance resources z4. Then the length of the individual is 3, and can be expressed as [r1(z1, z2), r2(z2, z3), r3(z4)].

[0072] Step S105: Based on the first time matrix and the second time matrix, solve the fitness value of each individual inversely proportional to the time spent on the operation and maintenance task according to the preset task execution logic.

[0073] Among them, the preset task execution logic indicates that for multiple operation and maintenance tasks corresponding to the same operation and maintenance resource, the operation and maintenance task with a higher priority is executed before the operation and maintenance task with a lower priority; among two operation and maintenance tasks of the same priority, the operation and maintenance task with the earliest required completion time is executed before the operation and maintenance task with the latest required completion time; among two operation and maintenance tasks of the same priority and the same latest required completion time, the operation and maintenance task with a shorter time taken is executed before the operation and maintenance task with a longer time taken.

[0074] Specifically, when solving the fitness value of each individual, the time spent on the operation and maintenance tasks of each individual can be solved according to the preset task execution logic based on the first time matrix and the second time matrix, and then the fitness value of each individual is determined based on the time spent on the operation and maintenance tasks of each individual. Among them, the fitness value of any individual is the reciprocal of the time spent on the operation and maintenance tasks of any individual, that is, the shorter the time spent on the operation and maintenance tasks of the individual, the greater the fitness value of the individual.

[0075] In the embodiment of the present application, the time spent on each operation and maintenance resource in the operation and maintenance task can be expressed as Where fin(i, j) represents the time spent by operation and maintenance resource j in operation and maintenance task i, T(i, j) represents the duration of operation and maintenance resource j executing operation and maintenance task i, E(i, j) represents the start execution time of operation and maintenance task i on operation and maintenance resource j, max(end(pre(j))) represents the latest time for operation and maintenance resource j to complete the previous task, and Tm(i) represents the time spent by operation and maintenance resource j from the completion time of the previous operation and maintenance task to the start time of operation and maintenance task i (for example, the time consumed by the operation and maintenance personnel in the process of arriving at the location of operation and maintenance task i after completing the previous operation and maintenance task).

[0076] Step S106: Perform crossover and mutation operations on individuals in the population whose fitness values ​​are lower than the first preset threshold to iteratively update the population.

[0077] Among them, the first preset threshold can be set according to actual conditions.

[0078] Performing crossover and mutation operations on individuals in the population whose fitness values ​​are lower than the first preset threshold may include but is not limited to the following steps S1061-S1065.

[0079] Step S1061. Generate a random number k as the individual hybridization point.

[0080] Wherein, k is an integer and 0≤k<n, and n represents the length of the individual (that is, n represents the number of operation and maintenance tasks corresponding to the individual).

[0081] Step S1062: Exchange the target individuals in the population whose fitness values ​​are lower than the first preset threshold and are located after the hybridization point to obtain new individuals.

[0082] Step S1063: Perform a mutation operation on at least one of the new individuals to obtain a mutant individual.

[0083] Among them, the mutation is to enhance the diversity of the population by changing certain genes of chromosomes (individuals) to avoid premature convergence. In the embodiment of the present application, the mutation can be to migrate a certain operation and maintenance task to another operation and maintenance resource for execution according to a certain probability. At the same time, in order to prevent the population from degenerating due to the increase in the total execution time of the operation and maintenance task after the migration of the operation and maintenance task, the migration of a certain operation and maintenance task can be performed by calculating the time required for other operation and maintenance resources to execute the certain operation and maintenance task, and selecting another operation and maintenance resource with the shortest required time to be allocated to the certain operation and maintenance task.

[0084] Step S1064: Calculate the fitness value corresponding to the new individual and the fitness value corresponding to the mutated individual.

[0085] The process of calculating the fitness value corresponding to the new individual and the fitness value corresponding to the mutated individual is consistent with the process of the aforementioned step S103 and will not be repeated here.

[0086] Step S1065. Based on the fitness value corresponding to the target individual, the fitness value corresponding to the new individual, and the fitness value corresponding to the mutated individual, the target individual in the population is iteratively updated to obtain an updated population.

[0087] Specifically, for a first target individual that has a corresponding variant individual, one of the individuals with the largest corresponding fitness value is selected from the first target individual, the new individual corresponding to the first target individual, and the variant individual corresponding to the first target individual as the updated individual of the first target individual. For a second target individual that does not have a variant individual, one of the individuals with the largest corresponding fitness value is selected from the second target individual and the new individual corresponding to the second target individual as the updated individual of the second target individual.

[0088] Step S107: When the iteration termination condition is reached or the number of iterations reaches the preset maximum number of iterations, an operation and maintenance task scheduling plan is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population.

[0089] Specifically, after each iteration, it can be determined whether the fitness values ​​corresponding to each individual in the latest population are lower than the second preset threshold or whether the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is lower than the preset duration, where the second preset threshold is greater than or equal to the first preset threshold, and the second preset threshold can be set according to actual conditions.

[0090] If the fitness values ​​corresponding to each individual are all lower than the second preset threshold or the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is lower than the preset duration, the iteration is stopped, and the operation and maintenance task scheduling scheme is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population. If there are individuals whose corresponding fitness values ​​are all lower than the second preset threshold or the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is higher than the preset duration, the individuals in the population whose fitness values ​​are lower than the first preset threshold can continue to be crossover and mutation operations to iteratively update the target individuals in the population until the fitness values ​​corresponding to each individual are all lower than the second preset threshold or the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is lower than the preset duration, or the iteration is stopped when the number of iterations reaches the preset maximum number of iterations. After the iteration is stopped, the operation and maintenance task scheduling scheme can be determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population, that is, according to the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population, the operation and maintenance resource sequence is allocated to the operation and maintenance tasks corresponding to each individual in the population.

[0091] It should be noted that after allocating an operation and maintenance resource sequence to the operation and maintenance tasks corresponding to each individual in the population, the operation and maintenance tasks corresponding to each individual still need to be executed according to the preset task execution logic, that is, for multiple operation and maintenance tasks corresponding to the same operation and maintenance resource, the operation and maintenance tasks with higher priority are executed before the operation and maintenance tasks with lower priority; among two operation and maintenance tasks of the same priority, the operation and maintenance task with the earliest required completion time is executed before the operation and maintenance task with the latest required completion time; among two operation and maintenance tasks of the same priority and the same latest required completion time, the operation and maintenance task with a shorter time taken is executed before the operation and maintenance task with a shorter time taken.

[0092] In summary, the operation and maintenance task scheduling method based on operation and maintenance data provided by the present invention is through initializing an operation and maintenance task set, an operation and maintenance resource set, a first time matrix and a second time matrix; initializing a population, the population includes a plurality of individuals corresponding to a plurality of operation and maintenance tasks, and each individual records a sequence of operation and maintenance resources occupied by the corresponding operation and maintenance task; based on the first time matrix and the second time matrix, solving the fitness value of each individual and inversely proportional to the time spent on the operation and maintenance task according to the preset task execution logic; performing crossover and mutation operations on individuals in the population whose fitness value is lower than a first preset threshold value to iteratively update the population; when the iteration termination condition is reached or the number of iterations reaches the preset maximum number of iterations, determining an operation and maintenance task scheduling plan based on the sequence of operation and maintenance resources occupied by the operation and maintenance tasks corresponding to each individual in the latest population. In this way, through the indirect coding method of operation and maintenance tasks and operation and maintenance resources, combined with individual crossover and mutation, large-scale concurrent multi-task scheduling can be transformed into a scheduling scheme based on genetic algorithms for overall optimization. Therefore, on the premise of meeting the operational requirements of operation and maintenance tasks, the completion time of operation and maintenance tasks can be shortened as a whole, the utilization rate of operation and maintenance resources can be improved, and the operation and maintenance costs in network operation and maintenance can be minimized, the stability and reliability of the network can be ensured, and practical application and promotion can be facilitated.

[0093] See also Figure 2 According to a second aspect of an embodiment of the present application, there is provided an operation and maintenance task scheduling device based on operation and maintenance data. The operation and maintenance task scheduling device based on operation and maintenance data includes:

[0094] A first determination unit is used to determine the priority and complexity corresponding to each of the multiple operation and maintenance tasks based on the system log, performance index and fault record of the network device corresponding to each of the multiple operation and maintenance tasks to be processed through a pre-established operation and maintenance data model;

[0095] A second determination unit is used to determine the time required for each operation and maintenance resource among the multiple operation and maintenance resources to perform each operation and maintenance task based on the complexity corresponding to the operation and maintenance task;

[0096] A first initialization unit is used to initialize an operation and maintenance task set, an operation and maintenance resource set, a first time matrix, and a second time matrix. The operation and maintenance task set includes the multiple operation and maintenance tasks, the operation and maintenance resource set includes the multiple operation and maintenance resources, the first time matrix records the time required for each operation and maintenance resource in the operation and maintenance resource set to execute each operation and maintenance task in the operation and maintenance task set, and the second time matrix records the time spent by the operation and maintenance resources from the completion time of the previous operation and maintenance task to the start time of the next operation and maintenance task in any two adjacent operation and maintenance tasks;

[0097] A second initialization unit is used to initialize a population, wherein the population includes a plurality of individuals corresponding to the plurality of operation and maintenance tasks one by one, and each individual records a sequence of operation and maintenance resources occupied by the corresponding operation and maintenance task;

[0098] a computing unit, configured to solve, based on the first time matrix and the second time matrix, the fitness value of each individual and inversely proportional to the time taken by the operation and maintenance task according to a preset task execution logic, wherein the preset task execution logic indicates that for multiple operation and maintenance tasks corresponding to the same operation and maintenance resource, an operation and maintenance task with a higher priority is executed before an operation and maintenance task with a lower priority, an operation and maintenance task with an earlier required completion time among two operation and maintenance tasks with the same priority is executed before an operation and maintenance task with a later required completion time, and an operation and maintenance task with a shorter time taken among two operation and maintenance tasks with the same priority and the same latest required completion time is executed before an operation and maintenance task with a shorter time taken;

[0099] An updating unit, used for performing crossover and mutation operations on individuals in the population whose fitness values ​​are lower than a first preset threshold, so as to iteratively update the population;

[0100] The third determining unit is used to determine the operation and maintenance task scheduling plan based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population when the iteration termination condition is reached or the number of iterations reaches a preset maximum number of iterations.

[0101] The working process, working details and technical effects of the operation and maintenance task scheduling device based on operation and maintenance data provided in the second aspect of this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0102] like Figure 3 As shown, the third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the operation and maintenance task scheduling method based on operation and maintenance data as described in the first aspect of the embodiment.

[0103] For specific examples, the memory may include but is not limited to random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc.; the processor may be but is not limited to a microprocessor of the STM32F105 series, an ARM (Advanced RISC-Machines), an X86 or other architecture processor, or a processor with an integrated NPU (neural-network processing units); the transceiver may be but is not limited to a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee protocol (a low-power local area network protocol based on the IEEE802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc.

[0104] The fourth aspect of this embodiment provides a computer-readable storage medium storing instructions for the operation and maintenance task scheduling method based on operation and maintenance data as described in the first aspect of the embodiment, that is, the computer-readable storage medium stores instructions, and when the instructions are run on a computer, the operation and maintenance task scheduling method based on operation and maintenance data as described in the first aspect is executed. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0105] The fifth aspect of this embodiment provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the operation and maintenance task scheduling method based on operation and maintenance data as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0106] It should be understood that certain details are provided in the following description to facilitate a complete understanding of the example embodiments. However, it should be understood by those of ordinary skill in the art that the example embodiments can be implemented without these certain details. For example, the system can be shown in a block diagram to avoid obscuring the example with unnecessary details. In other examples, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the example embodiments.

[0107] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for scheduling operation and maintenance tasks based on operation and maintenance data, characterized in that: include: Based on the system logs, performance indicators and fault records of the network devices corresponding to each of the multiple operation and maintenance tasks to be processed, the priority and complexity corresponding to each of the multiple operation and maintenance tasks are determined through a pre-established operation and maintenance data model; Based on the complexity of the operation and maintenance tasks, determine the time required for each operation and maintenance resource among multiple operation and maintenance resources to perform each operation and maintenance task; Initialize an operation and maintenance task set, an operation and maintenance resource set, a first time matrix, and a second time matrix, wherein the operation and maintenance task set includes the multiple operation and maintenance tasks, the operation and maintenance resource set includes the multiple operation and maintenance resources, the first time matrix records the time required for each operation and maintenance resource in the operation and maintenance resource set to execute each operation and maintenance task in the operation and maintenance task set, and the second time matrix records the time spent by the operation and maintenance resources from the completion time of the previous operation and maintenance task to the start time of the next operation and maintenance task between any two adjacent operation and maintenance tasks; Initializing a population, the population including a plurality of individuals corresponding to the plurality of operation and maintenance tasks, each individual recording a sequence of operation and maintenance resources occupied by the corresponding operation and maintenance task; Based on the first time matrix and the second time matrix, solving the fitness value of each individual and inversely proportional to the time spent on the operation and maintenance task according to the preset task execution logic, wherein the preset task execution logic indicates that for multiple operation and maintenance tasks corresponding to the same operation and maintenance resource, the operation and maintenance task with a higher priority is executed before the operation and maintenance task with a lower priority, the operation and maintenance task with the earliest required completion time of two operation and maintenance tasks with the same priority is executed before the operation and maintenance task with the latest required completion time, and the operation and maintenance task with a shorter time spent on two operation and maintenance tasks with the same priority and the same latest required completion time is executed before the operation and maintenance task with a shorter time spent on two tasks; Performing crossover and mutation operations on individuals in the population whose fitness values ​​are lower than a first preset threshold, so as to iteratively update the population; When the iteration termination condition is reached or the number of iterations reaches the preset maximum number of iterations, an operation and maintenance task scheduling plan is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population.

2. The operation and maintenance task scheduling method based on operation and maintenance data according to claim 1 is characterized in that: Initializing the first time matrix and the second time matrix includes: Determine the time required for various operation and maintenance tasks and the time spent between the completion time of the previous operation and maintenance task and the start time of the next operation and maintenance task in any two adjacent operation and maintenance tasks based on historical operation and maintenance records; Based on the time required for various operation and maintenance tasks and the time spent between the completion time of the previous operation and maintenance task and the start time of the next operation and maintenance task of any two adjacent operation and maintenance tasks, the first time matrix and the second time matrix are initialized.

3. The operation and maintenance task scheduling method based on operation and maintenance data according to claim 1 is characterized in that: The step of solving the fitness value of each individual and inversely proportional to the time spent on the operation and maintenance task according to the preset task execution logic based on the first time matrix and the second time matrix includes: Based on the first time matrix and the second time matrix, solving the time spent on the operation and maintenance tasks of each individual according to the preset task execution logic; Determine the fitness value of each individual based on the time spent on the operation and maintenance tasks of each individual; The fitness value of any individual is the reciprocal of the time spent on the operation and maintenance task of the individual.

4. The operation and maintenance task scheduling method based on operation and maintenance data according to claim 3 is characterized in that: The time spent on each operation and maintenance resource in the operation and maintenance task is Where fin(i, j) represents the time spent by operation and maintenance resource j in operation and maintenance task i, T(i, j) represents the duration of operation and maintenance resource j executing operation and maintenance task i, E(i, j) represents the start time of operation and maintenance task i on operation and maintenance resource j, max(end(pre(j))) represents the latest time for operation and maintenance resource j to complete the previous task, and Tm(i) represents the time spent by operation and maintenance resource j from the completion time of the previous operation and maintenance task to the start time of operation and maintenance task i.

5. The operation and maintenance task scheduling method based on operation and maintenance data according to claim 1 is characterized in that: Perform crossover and mutation operations on individuals in the population whose fitness values ​​are lower than the first preset threshold to iteratively update the population, including: Generate a random number k as the hybridization point of the individual, where 0≤k<n, and n represents the length of the individual; Exchanging the target individuals whose fitness values ​​in the population are lower than a first preset threshold and located after the hybridization point to obtain new individuals; Performing a mutation operation on at least one of the new individuals to obtain a mutant individual; Calculate the fitness value corresponding to the new individual and the fitness value corresponding to the mutated individual; Based on the fitness value corresponding to the target individual, the fitness value corresponding to the new individual and the fitness value corresponding to the mutated individual, the target individual in the population is iteratively updated to obtain an updated population.

6. The operation and maintenance task scheduling method based on operation and maintenance data according to claim 5 is characterized in that: Based on the fitness value corresponding to the target individual, the fitness value corresponding to the new individual, and the fitness value corresponding to the mutated individual, the target individual in the population is iteratively updated, including: For a first target individual that has a corresponding variant individual, select an individual with the largest corresponding fitness value from among the first target individual, the new individual corresponding to the first target individual, and the variant individual corresponding to the first target individual as an updated individual of the first target individual; For a second target individual without strained individuals, one of the individuals with the largest corresponding fitness value is selected from the second target individual and the new individual corresponding to the second target individual as the updated individual of the second target individual.

7. The operation and maintenance task scheduling method based on operation and maintenance data according to claim 1 is characterized in that: When the iteration termination condition is reached or the number of iterations reaches the preset maximum number of iterations, an operation and maintenance task scheduling scheme is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population, including: Determine whether the fitness values ​​corresponding to each individual in the latest population are all lower than a second preset threshold or whether the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is lower than a preset duration, wherein the second preset threshold is greater than or equal to the first preset threshold; If the fitness values ​​corresponding to each individual are lower than the second preset threshold or the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is lower than the preset duration, the iteration is stopped, and the operation and maintenance task scheduling plan is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population; If there are individuals whose corresponding fitness values ​​are all lower than the second preset threshold or the sum of the time spent on the operation and maintenance tasks corresponding to all individuals is longer than the preset duration, crossover and mutation operations will continue to be performed on the individuals in the population whose fitness values ​​are lower than the first preset threshold until the number of iterations reaches the preset maximum number of iterations, and the operation and maintenance task scheduling plan is determined based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population.

8. An operation and maintenance task scheduling device based on operation and maintenance data, characterized in that: include: A first determination unit is used to determine the priority and complexity corresponding to each of the multiple operation and maintenance tasks based on the system log, performance index and fault record of the network device corresponding to each of the multiple operation and maintenance tasks to be processed through a pre-established operation and maintenance data model; A second determination unit is used to determine the time required for each operation and maintenance resource among the multiple operation and maintenance resources to perform each operation and maintenance task based on the complexity corresponding to the operation and maintenance task; A first initialization unit is used to initialize an operation and maintenance task set, an operation and maintenance resource set, a first time matrix, and a second time matrix. The operation and maintenance task set includes the multiple operation and maintenance tasks, the operation and maintenance resource set includes the multiple operation and maintenance resources, the first time matrix records the time required for each operation and maintenance resource in the operation and maintenance resource set to execute each operation and maintenance task in the operation and maintenance task set, and the second time matrix records the time spent by the operation and maintenance resources from the completion time of the previous operation and maintenance task to the start time of the next operation and maintenance task in any two adjacent operation and maintenance tasks; A second initialization unit is used to initialize a population, wherein the population includes a plurality of individuals corresponding to the plurality of operation and maintenance tasks one by one, and each individual records a sequence of operation and maintenance resources occupied by the corresponding operation and maintenance task; a computing unit, configured to solve, based on the first time matrix and the second time matrix, the fitness value of each individual and inversely proportional to the time taken by the operation and maintenance task according to a preset task execution logic, wherein the preset task execution logic indicates that for multiple operation and maintenance tasks corresponding to the same operation and maintenance resource, an operation and maintenance task with a higher priority is executed before an operation and maintenance task with a lower priority, an operation and maintenance task with an earlier required completion time among two operation and maintenance tasks with the same priority is executed before an operation and maintenance task with a later required completion time, and an operation and maintenance task with a shorter time taken among two operation and maintenance tasks with the same priority and the same latest required completion time is executed before an operation and maintenance task with a shorter time taken; An updating unit, used for performing crossover and mutation operations on individuals in the population whose fitness values ​​are lower than a first preset threshold, so as to iteratively update the population; The third determining unit is used to determine the operation and maintenance task scheduling plan based on the operation and maintenance resource sequence occupied by the operation and maintenance tasks corresponding to each individual in the latest population when the iteration termination condition is reached or the number of iterations reaches a preset maximum number of iterations.

9. An electronic device, characterized in that: It includes a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the operation and maintenance task scheduling method based on operation and maintenance data as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the operation and maintenance task scheduling method based on operation and maintenance data as described in any one of claims 1 to 7 is implemented.

Images