Power maintenance scheduling method and scheduling platform

Abstract

The present application relates to the technical field of power maintenance, and especially relates to a power maintenance scheduling method and a scheduling platform, wherein the method first takes multiple power maintenance requirements, wherein the power maintenance requirements represent required resources of target power maintenance; then, according to the multiple power maintenance requirements and multiple resource distributions, multiple scheduling constraint models are determined; then, according to a scheduling target, the multiple scheduling constraint models are solved to obtain optimal solutions of the multiple scheduling constraint models; finally, according to the optimal solutions of the multiple scheduling constraint models, a scheduling strategy is output. In the present application, through the power maintenance requirements and the multiple resource distributions, a maintenance rate constraint model and a resource consumption model are determined, and according to the scheduling target, optimal solutions of the scheduling resources are determined, so that the power maintenance process meets the deadline requirement while reducing the consumption of resources, achieving the purpose of global resource consumption reduction and avoiding unnecessary resource waste.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power maintenance, and particularly relates to a power maintenance scheduling method and a scheduling platform. BACKGROUND

[0002] With the continuous increase of social power consumption, higher requirements are put forward for the safety and reliability of power system operation. It is an important prerequisite to effectively carry out the safety management and equipment maintenance of the substation system to enhance the safety and stability of the entire system.

[0003] Analysis of the importance of substation operation safety management and equipment maintenance Substation operation is an important part of the operation of the power system, which relates to the actual operation of the entire power system. It is necessary to adopt scientific and reasonable management methods and means to strengthen the management of substation operation in all aspects, achieve the goal of safety management, and do a good job in the overall maintenance of power operation equipment, timely find the abnormal state of equipment operation, and carry out timely maintenance work, so that it always maintains a good working condition, maximizes the overall level of substation operation of the power system, and improves the efficiency and service level of power enterprise work, thereby increasing the economic and social benefits of the power system. In the process of overall safety management, safety hazards can be timely investigated and solved, the complex environment of the actual operation of the power system can be responded to, the advantages of safety management system can be played, and the work can be orderly carried out.

[0004] Implementation of the safety responsibility system of substation operation of the power system In the process of safety management of the power system substation, it is necessary to analyze the use of power resources and the power supply capacity of the power enterprise and other aspects to ensure that a perfect and reasonable maintenance plan can be developed.

[0005] In the prior art, the scheduling of power maintenance is not systematic, lacks a comprehensive information mechanism, and the overall planning of scheduling is poor, resulting in a lot of resource waste. The scheduling technology can often achieve local optimization, but ignores the global optimization, increases the consumption of manpower and material resources that can be avoided, reduces the utilization rate of material resources, and increases the amount of repetitive labor.

[0006] Therefore, it is necessary to develop and design a power maintenance scheduling method. SUMMARY

[0007] The embodiments of the present application provide a power maintenance scheduling method and a scheduling platform, which are used to solve the problem of local optimization caused by the deficiency of the scheduling technology in the prior art, and finally cause unnecessary resource waste.

[0008] In a first aspect, an embodiment of the present application provides a power maintenance scheduling method, comprising: obtaining a plurality of power maintenance requirements, wherein the power maintenance requirements represent required resources of target power maintenance;

[0009] determining a plurality of scheduling constraint models according to the plurality of power maintenance requirements and a plurality of resource distributions, wherein the scheduling constraint models represent consumptions of resources during power maintenance;

[0010] solving the plurality of scheduling constraint models according to a scheduling target to obtain optimal solutions of the plurality of scheduling constraint models, wherein the scheduling target represents resource consumption in power maintenance;

[0011] outputting a scheduling strategy according to the optimal solutions of the plurality of scheduling constraint models.

[0012] In a possible implementation, the power maintenance requirements are determined based on a plurality of characteristics of maintenance targets, wherein the plurality of characteristics include: a maintenance target category, a defect, an influence range, a maintenance duration, and an expected recovery duration, and determining the power maintenance requirements based on the plurality of characteristics of the maintenance targets comprises:

[0013] obtaining a maintenance requirement library, wherein the maintenance requirement library includes a plurality of sample vectors, and each sample vector is associated with a maintenance resource;

[0014] constructing a target vector according to the plurality of characteristics, wherein the plurality of characteristics in the target vector are consistent with a characteristic order of the sample vectors;

[0015] calculating inner products of the target vector and the plurality of sample vectors to obtain a plurality of requirement indexes;

[0016] selecting a maintenance resource associated with a sample vector with the highest requirement index as the power maintenance requirement.

[0017] In a possible implementation, the sample vectors are obtained based on historical maintenance records, comprising:

[0018] obtaining a plurality of maintenance records, wherein the maintenance records record: a maintenance target category, a defect, an influence range, a maintenance duration, an expected recovery duration, and a maintenance resource;

[0019] for each maintenance record in the plurality of maintenance records, a maintenance target category, a defect, an influence range, a maintenance duration, and an expected recovery duration are made into an initial vector in a predetermined order;

[0020] normalizing each initial vector to obtain a sample vector;

[0021] associating a plurality of the sample vectors with a plurality of the maintenance resources to obtain the maintenance requirement library.

[0022] In one possible implementation, determining multiple scheduling constraint models based on the multiple power maintenance needs and multiple resource distributions includes:

[0023] For each of the multiple power maintenance needs, perform the following steps:

[0024] Based on the maintenance target category of the maintenance target, a maintenance rate function is determined, wherein the maintenance rate function characterizes the relationship between the quantity of multiple resources and the maintenance rate;

[0025] The resource consumption function is determined based on the location of the maintenance target and the distribution of the multiple resources.

[0026] In one possible implementation, the maintenance rate function is:

[0027]

[0028] In the formula, S i Let n be the maintenance rate for the i-th power maintenance demand, and n be the total number of power maintenance demands. Let α be the pre-weighting parameter for the i-th power maintenance demand rate. j Let j be the quantity of the j-th resource. Let m be the post-weight parameter for the rate of influence of the j-th resource, m be the total number of resource types, and ln be the natural logarithm.

[0029] The resource consumption function is:

[0030]

[0031] In the formula, R i Let i be the total resource consumption for the i-th power maintenance requirement. β is the pre-weighting parameter for the i-th power maintenance demand. j Let j be the distance between the j-th resource and the maintenance target. Let be the post-weighting parameter for the consumption of the j-th resource, and e be a natural constant.

[0032] In one possible implementation, the scheduling objective includes: a total consumption objective and multiple time-bound objectives, wherein the multiple time-bound objectives correspond to multiple power maintenance needs, and solving the multiple scheduling constraint models based on the scheduling objective includes:

[0033] The multiple power maintenance requirements are sorted according to the target timeframe.

[0034] Initialize a preset number of particles, where each particle is configured with a different position and velocity;

[0035] target computing step: computing total consumption and satisfaction degree of the plurality of deadline targets;

[0036] if the computing total consumption and the satisfaction degree of the plurality of deadline targets meet preset conditions, outputting an optimal solution;

[0037] otherwise, updating the speed and position of each particle;

[0038] updating the individual historical optimal fitness value and position of each particle;

[0039] updating the group historical optimal fitness value, position and inertia weight;

[0040] jumping to the target computing step.

[0041] In a second aspect, an embodiment of the present application provides an electric power maintenance scheduling device, comprising:

[0042] a maintenance demand obtaining module, configured to obtain a plurality of electric power maintenance demands, wherein the electric power maintenance demand represents required resources of target electric power maintenance;

[0043] a constraint model establishing module, configured to determine a plurality of scheduling constraint models according to the plurality of electric power maintenance demands and a plurality of resource distributions, wherein the scheduling constraint model represents consumption generated by resources during electric power maintenance;

[0044] a target solving module, configured to solve the plurality of scheduling constraint models according to a scheduling target to obtain optimal solutions of the plurality of scheduling constraint models, wherein the scheduling target represents resource consumption in electric power maintenance;

[0045] and,

[0046] an output module, configured to output a scheduling strategy according to the optimal solutions of the plurality of scheduling constraint models.

[0047] In a third aspect, an embodiment of the present application provides a server, comprising a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor implements steps of the method according to the first aspect or any possible implementation manner of the first aspect when executing the computer program.

[0048] In a fourth aspect, an embodiment of the present application provides a scheduling platform, comprising: the server according to the third aspect, and the scheduling platform further comprises: a plurality of scheduling terminals, the plurality of scheduling terminals are distributed in a plurality of maintenance centers, and the plurality of scheduling terminals are in signal connection with the server;

[0049] the scheduling terminal is configured to transmit the electric power maintenance demand to the server, and receive the scheduling strategy generated by the server.

[0050] In a fifth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program. The computer program, when executed by a processor, implements the steps of the method according to the first aspect or any possible implementation of the first aspect.

[0051] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0052] The power maintenance scheduling method provided by the embodiment of the present application firstly acquires a plurality of power maintenance demands, wherein the power maintenance demand represents a required resource of target power maintenance; then, according to the plurality of power maintenance demands and a plurality of resource distributions, a plurality of scheduling constraint models are determined, wherein the scheduling constraint model represents consumption of the resource during the power maintenance; then, according to a scheduling target, the plurality of scheduling constraint models are solved to obtain optimal solutions of the plurality of scheduling constraint models, wherein the scheduling target represents resource consumption in the power maintenance; finally, according to the optimal solutions of the plurality of scheduling constraint models, a scheduling strategy is output. The embodiment of the present application determines a maintenance rate constraint model and a resource consumption model through the power maintenance demand and the plurality of resource distributions, and determines the optimal solution of the scheduling resource according to the scheduling target, so that the power maintenance process meets the deadline requirement while reducing the consumption of the resource, thereby achieving the purpose of global resource consumption reduction and avoiding unnecessary resource waste. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative labor based on these drawings.

[0054] Figure 1 is a flowchart of the power maintenance scheduling method provided by the embodiment of the present application;

[0055] Figure 2 is a principle schematic diagram of the particle swarm optimization algorithm provided by the embodiment of the present application;

[0056] Figure 3 is a schematic diagram of the particle velocity updating method provided by the embodiment of the present application;

[0057] Figure 4 is a functional block diagram of the power maintenance scheduling device provided by the embodiment of the present application;

[0058] Figure 5 is a functional block diagram of the terminal provided by the embodiment of the present application. Detailed Implementation

[0059] In the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0060] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0061] The embodiments of the present invention will be described in detail below. This example is implemented based on the technical solution of the present invention, and provides detailed implementation methods and specific operation processes. However, the protection scope of the present invention is not limited to the following embodiments.

[0062] Figure 1 A flowchart of a power maintenance and dispatching method provided for an embodiment of the present invention.

[0063] like Figure 1 The diagram illustrates the implementation flowchart of the power maintenance and dispatching method provided by the embodiments of the present invention, which is described in detail below:

[0064] In step 101, multiple power maintenance requirements are obtained, wherein the power maintenance requirements characterize the resources required for the target power maintenance.

[0065] In some implementations, the power maintenance requirements are determined based on multiple characteristics of the maintenance target, wherein the multiple characteristics include: maintenance target category, defect, scope of impact, maintenance duration, and expected recovery time. Determining power maintenance requirements based on multiple characteristics of the maintenance target includes:

[0066] Obtain a maintenance requirement database, wherein the maintenance requirement database includes multiple sample vectors, and each sample vector is associated with a maintenance resource;

[0067] A target vector is constructed based on the multiple features, wherein the multiple features in the target vector are ordered in the same way as the features in the sample vector;

[0068] Calculate the inner product of the target vector and the plurality of sample vectors to obtain multiple demand indices;

[0069] The associated maintenance resources of the sample vector with the highest demand index are selected as the power maintenance demand.

[0070] In some implementations, the sample vector is obtained based on historical maintenance records, including:

[0071] obtain a plurality of maintenance records, wherein the maintenance records record a maintenance target category, a defect, an influence range, a maintenance duration, an expected recovery duration, and a maintenance resource;

[0072] For each of the plurality of maintenance records, a maintenance target category, a defect, an influence range, a maintenance duration, and an expected recovery duration are made into an initial vector in a predetermined order;

[0073] Each of the initial vectors is normalized to obtain a sample vector;

[0074] The plurality of sample vectors are associated with the plurality of maintenance resources to obtain the maintenance demand library.

[0075] Exemplarily, the power maintenance target refers to a power maintenance project carried out for a specific power facility or equipment and for a certain defect. For example, for a power transformer, internal insulation oil will gradually age with the use of the power transformer, and the internal insulation oil of the power transformer needs to be replaced according to the aging degree or maintenance period.

[0076] As we know, power maintenance involves many aspects of demand. Taking the replacement of the insulation oil of the power transformer as an example, it involves the consumption of human resources, oil replacement equipment, oil replacement consumables, and the consumption of materials such as insulation oil. Due to the existence of many maintenance points, the cooperation of the required deadline, various human and material resources, and the gradual transformation from local optimization to global optimization, that is, the shortest deadline and the least resource consumption are used to achieve the purpose of power maintenance.

[0077] Therefore, before power maintenance scheduling, it should be clear what the maintenance demand is, for example, the example of replacing the insulation oil involves the consumption of manpower, equipment, and materials.

[0078] In the explicit power maintenance, we make it clear through the maintenance demand library. Specifically, for the maintenance target, we obtain the characteristics of the maintenance target, which include the maintenance target category, the defect, the influence range, the maintenance duration, and the expected recovery duration.

[0079] The combination of these characteristics can be understood as a vector. If two vectors have high similarity, the existing vector-associated maintenance resources can be used as the required resources for power maintenance.

[0080] In practice, the vector is calculated by performing an inner product operation between the features of the vector and each sample vector in the demand library, and the sample vector with the largest inner product is regarded as the most similar power maintenance demand. For example, in the project of replacing the insulating oil of a power transformer, although the equipment and consumables for replacing the insulating oil of power transformers of different voltage levels are slightly different, the overall similarity is similar and has reference significance, and the feature similarity is relatively high.

[0081] For the establishment of the demand library, one implementation is to find the association records of maintenance resources and maintenance target features from existing maintenance records. For example, for a power transformer of B voltage level, the maintenance records include the maintenance target category, defect, influence range, maintenance duration, expected recovery duration and maintenance resource. The maintenance target category, defect, influence range, maintenance duration and expected recovery duration are respectively matched with different values, and then an initial vector is obtained.

[0082] As we know, if only the initial vector is used as a sample vector to perform the similarity judgment in the foregoing process, the rules are inconsistent, and therefore, normalization processing is required to obtain a sample vector. Each sample vector is associated with a maintenance resource, and a plurality of sample vectors and maintenance resource data pairs are obtained, and thus the demand library is constructed.

[0083] In step 102, a plurality of scheduling constraint models are determined according to the plurality of power maintenance demands and the distribution of the plurality of resources, wherein the scheduling constraint model represents the consumption of resources during power maintenance.

[0084] In some embodiments, step 102 includes:

[0085] For each power maintenance demand in the plurality of power maintenance demands, the following steps are performed:

[0086] According to the maintenance target category of the maintenance target, a maintenance rate function is determined, wherein the maintenance rate function represents the relationship between the number of resources and the maintenance rate;

[0087] According to the location of the maintenance target and the distribution of the plurality of resources, a resource consumption function is determined.

[0088] In some embodiments, the maintenance rate function is:

[0089]

[0090] In the formula, S i is the maintenance rate of the i-th power maintenance demand, n is the total number of power maintenance demands, is the pre-weight parameter of the i-th power maintenance demand rate, and α jthe number of the jth resource, the post-weight parameter of the jth resource affecting the rate, m is the total number of resource types, and ln is a natural logarithm;

[0091] The resource consumption function is:

[0092]

[0093] In the formula, R i the total resource consumption of the ith power maintenance requirement, the pre-weight parameter of the ith power maintenance requirement consumption, β j the distance between the jth resource and the maintenance target, the post-weight parameter of the jth resource consumption, and e is a natural constant.

[0094] Exemplarily, as mentioned above, the power maintenance scheduling should be planned as a whole to avoid local optimization and achieve global optimization, wherein two indexes that need to be determined are the maintenance period and the resource consumption. However, the two indexes are often contradictory in practice. For example, in order to shorten the maintenance period as much as possible, more resource consumption needs to be invested, and less resource consumption will inevitably affect the maintenance period. Therefore, before determining the reasonable resource allocation, two constraints need to be determined, one is the constraint between the maintenance rate and different resource consumptions, and the other is the constraint of resource distribution and different resources on the overall resource consumption.

[0095] In practice, the maintenance rate function is (maintenance rate constraint):

[0096]

[0097] In the formula, S i the maintenance rate of the ith power maintenance requirement, n is the total number of power maintenance requirements, the pre-weight parameter of the ith power maintenance requirement rate, α j the number of the jth resource, the post-weight parameter of the jth resource affecting the rate, m is the total number of resource types, and ln is a natural logarithm;

[0098] The resource consumption function is (resource consumption constraint):

[0099]

[0100] In the formula, R i the total resource consumption of the ith power maintenance requirement, the pre-weight parameter of the ith power maintenance requirement consumption, β j the distance between the jth resource and the maintenance target, is a post-weight parameter for the jth resource consumption, and e is a natural constant.

[0101] In step 103, the plurality of scheduling constraint models are solved according to a scheduling target to obtain an optimal solution of the plurality of scheduling constraint models, wherein the scheduling target represents resource consumption in power maintenance.

[0102] In some embodiments, the scheduling target includes a total consumption target and a plurality of deadline targets, wherein the plurality of deadline targets correspond to the plurality of power maintenance requirements, and step 103 includes:

[0103] The plurality of power maintenance requirements are sorted according to lengths of the deadline targets;

[0104] A preset number of particles are initialized, wherein each particle is configured as a different position and velocity;

[0105] A target calculation step: total consumption and satisfaction degrees of the plurality of deadline targets are calculated;

[0106] If the total consumption and the satisfaction degrees of the plurality of deadline targets meet a preset condition, an optimal solution is outputted;

[0107] Otherwise, velocities and positions of each particle are updated;

[0108] Individual historical optimal fitness values and positions of each particle are updated;

[0109] A group historical optimal fitness value, position and inertia weight are updated;

[0110] The target calculation step is jumped to.

[0111] Exemplarily, as described above, two conditions of a global optimal solution are optimal solutions of a deadline and resource consumption, and for the optimal solutions of the two targets, a plurality of methods can be adopted to obtain an optimal resource configuration through the two constraints, such as a genetic algorithm or a particle swarm optimization algorithm.

[0112] Embodiments of the present application show a mode of applying a particle swarm optimization algorithm. Figure 2As shown, the principle of the Particle Swarm Optimization (PSO) algorithm originates from the study of bird flock foraging behavior. Bird flocks find the optimal destination through collective information sharing. Imagine this scenario: a flock of birds randomly searches for food 202 in a forest, aiming to find the location with the highest quantity of food 202. However, none of the birds 201 know the exact location of food 202; they can only sense its approximate direction. Each bird 201 searches along its determined direction, recording the locations where it has found the most food 202. Simultaneously, all birds 201 share their findings of food 202 locations and quantities, allowing the flock to determine the current location with the highest quantity of food 202. During the search, each bird 201 adjusts its search direction based on its memory of the location with the highest quantity of food 202 and the flock's current record. After a period of searching, the flock finds the location with the most food 204 in the forest.

[0113] To avoid local optima, for example, Figure 2 As shown, in some scenarios, in a grove of trees, bird 201 will gradually approach the location with the most food 203 in the grove. The bird's direction of movement will be constrained by three directions (e.g., Figure 3 As shown): The inertial direction, the individual optimal direction, and the group optimal direction are combined into a vector to form the bird's direction of travel, which is also the direction of travel of each particle in the particle swarm algorithm.

[0114] In the specific application scenario of this implementation, a preset number of particles are initialized, and each particle is configured with speed and position. The position is a particle element, and each element is the optimal solution for multiple resources in multiple power maintenance needs. The particles are brought into the constraints to obtain the optimal solution, determine the total consumption, and whether multiple time-limited targets are met. If the total consumption does not meet the expectations (or the rate of change of total consumption does not meet the expectations), the speed and position of the particles are updated according to preset conditions until the total consumption meets the expectations.

[0115] At this point, the particle's position represents the optimal solution for multiple resources among various power maintenance needs.

[0116] In step 104, a scheduling strategy is output based on the optimal solution of the multiple scheduling constraint models.

[0117] For example, in the embodiment of the present invention, under the premise of meeting the time limit requirement, the particle swarm optimization algorithm described above is applied to find the optimal solution with the least resource consumption. Based on the optimal solution, a resource scheduling strategy is issued to each maintenance center to complete the resource allocation.

[0118] The embodiment of the power maintenance scheduling method first acquires a plurality of power maintenance requirements, wherein the power maintenance requirement represents required resources of target power maintenance; then determines a plurality of scheduling constraint models according to the plurality of power maintenance requirements and a plurality of resource distributions, wherein the scheduling constraint model represents consumption of resources during power maintenance; next, solves the plurality of scheduling constraint models according to a scheduling target to obtain optimal solutions of the plurality of scheduling constraint models, wherein the scheduling target represents resource consumption in power maintenance; finally, outputs a scheduling strategy according to the optimal solutions of the plurality of scheduling constraint models. The embodiment of the present application determines a maintenance rate constraint model and a resource consumption model through the power maintenance requirement and the plurality of resource distributions, and determines the optimal solution of the scheduling resource according to the scheduling target, so that the power maintenance process meets the deadline requirement while reducing the consumption of resources, achieving the purpose of global resource consumption, and avoiding unnecessary resource waste.

[0119] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0120] The following is the device embodiment of the present application. For details not described in detail, please refer to the corresponding method embodiments described above.

[0121] Figure 4 is the functional block diagram of the power maintenance scheduling device provided by the embodiment of the present application. Referring to Figure 4 , the power maintenance scheduling device 4 comprises a maintenance requirement acquisition module 401, a constraint model establishment module 402, a target solving module 403 and an output module 404.

[0122] The maintenance requirement acquisition module 401 is used to acquire a plurality of power maintenance requirements, wherein the power maintenance requirement represents required resources of target power maintenance;

[0123] The constraint model establishment module 402 is used to determine a plurality of scheduling constraint models according to the plurality of power maintenance requirements and a plurality of resource distributions, wherein the scheduling constraint model represents consumption of resources during power maintenance;

[0124] The target solving module 403 is used to solve the plurality of scheduling constraint models according to a scheduling target to obtain optimal solutions of the plurality of scheduling constraint models, wherein the scheduling target represents resource consumption in power maintenance;

[0125] The output module 404 is used to output a scheduling strategy according to the optimal solutions of the plurality of scheduling constraint models.

[0126] Figure 5is a functional block diagram of a server provided by an embodiment of the present application. As shown in Figure 5 The server 5 of the embodiment includes a processor 500 and a memory 501, and the memory 501 stores a computer program 502 which can be run on the processor 500. The processor 500 implements the steps in the above power maintenance scheduling method and embodiments when running the computer program 502, for example Figure 1 Steps 101 to 104 shown in the above embodiment.

[0127] For example, the computer program 502 can be divided into one or more modules / units, which are stored in the memory 501 and executed by the processor 500 to complete the present application.

[0128] The server 5 can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The server 5 can include, but is not limited to, the processor 500 and the memory 501. Those skilled in the art can understand that Figure 5 The server 5 is only an example and does not constitute a limitation on the server 5, and can include more or fewer components than shown, or combine certain components, or different components, for example, the server can also include an input / output device, a network access device, a bus, etc.

[0129] The processor 500 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0130] The memory 501 can be an internal storage unit of the server 5, for example, a hard disk or a memory of the server 5. The memory 501 can also be an external storage device of the server 5, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the server 5. Further, the memory 501 can also include both the internal storage unit and the external storage device of the server 5. The memory 501 is used to store the computer program and other programs and data required by the server. The memory 501 can also be used to temporarily store data that has been output or will be output.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0132] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can refer to the relevant description of other embodiments.

[0133] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0134] In the embodiments of the present application, it should be understood that the disclosed apparatuses / servers and methods can be implemented in other manners. For example, the described apparatus / server embodiments are merely schematic. For example, the division of the modules or units is merely logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0135] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0136] In addition, each functional unit in the various embodiments of the present application can be integrated into a processing unit, or each unit can be a physically independent unit, or two or more units can be integrated into a unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0137] The integrated module / unit, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above-described various method and device embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0138] The above-described embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent replacements; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A power maintenance scheduling method characterized by, The method comprises the following steps: obtaining a plurality of power maintenance requirements, wherein the power maintenance requirements represent required resources of target power maintenance; determining a plurality of scheduling constraint models representing consumption of resources during power maintenance according to the plurality of power maintenance requirements and a plurality of resource distributions, comprising: for each power maintenance requirement in the plurality of power maintenance requirements, performing the following steps: determining a maintenance rate function according to a maintenance target category of the maintenance target, wherein the maintenance rate function represents a relationship between a number of resources and a maintenance rate, and the maintenance rate function is: In the formula, S i is the maintenance rate of the i-th power maintenance demand, n is the total number of power maintenance demands, is the pre-weight parameter of the i-th power maintenance demand rate, α j is the number of the j-th resource, is the post-weight parameter of the j-th resource influence rate, m is the total number of resource types, and ln is the natural logarithm. determining a resource consumption function according to a location of the maintenance target and a distribution of the plurality of resources, wherein the resource consumption function is: wherein R i is the total amount of resource consumption of the i-th power maintenance requirement, is the pre-weight parameter consumed by the i-th power maintenance requirement, β j is the distance between the j-th resource and the maintenance target, is the post-weight parameter of the j-th resource consumption, e is a natural constant; solving the plurality of scheduling constraint models according to a scheduling target, wherein the scheduling target represents resource consumption in power maintenance, to obtain optimal solutions of the plurality of scheduling constraint models; outputting a scheduling strategy according to the optimal solutions of the plurality of scheduling constraint models.

2. The power maintenance scheduling method of claim 1, wherein, The power maintenance requirements are determined based on a plurality of characteristics of the maintenance target, wherein the plurality of characteristics comprise a maintenance target category, a defect, an influence range, a maintenance duration and an expected recovery duration, and the determination of the power maintenance requirements based on the plurality of characteristics of the maintenance target comprises: obtaining a maintenance requirement library, wherein the maintenance requirement library comprises a plurality of sample vectors, and each sample vector is associated with a maintenance resource; constructing a target vector according to the plurality of characteristics, wherein the plurality of characteristics in the target vector are consistent with a characteristic order of the sample vectors; calculating inner products of the target vector and the plurality of sample vectors to obtain a plurality of requirement indexes; selecting a maintenance resource associated with a sample vector with the highest requirement index as the power maintenance requirement.

3. The power maintenance scheduling method of claim 2, wherein, The sample vectors are obtained based on historical maintenance records, comprising: obtaining a plurality of maintenance records, wherein each maintenance record records a maintenance target category, a defect, an influence range, a maintenance duration, an expected recovery duration and a maintenance resource; for each maintenance record in the plurality of maintenance records, a maintenance target category, a defect, an influence range, a maintenance duration and an expected recovery duration are made into an initial vector in a predetermined order; normalizing each initial vector to obtain a sample vector; associating a plurality of sample vectors with a plurality of maintenance resources to obtain the maintenance requirement library.

4. The power maintenance scheduling method according to any one of claims 1-3, characterized in that, The scheduling target comprises a total consumption target and a plurality of deadline targets, wherein the plurality of deadline targets correspond to the plurality of power maintenance requirements, and the solving of the plurality of scheduling constraint models according to the scheduling target comprises: sorting the plurality of power maintenance requirements according to lengths of the deadline targets; initializing a preset number of particles, wherein each particle is configured to have a different position and velocity, and the position of the particle is an optimal solution of a plurality of resources in the plurality of power maintenance requirements; a target calculation step: calculating a total consumption and a satisfaction degree of the plurality of deadline targets; if the total consumption and the satisfaction degree of the plurality of deadline targets meet a preset condition, outputting an optimal solution; otherwise, updating the velocity and the position of each particle; updating an individual historical optimal fitness value and a position of each particle; updating the population history best fitness value, the position and the inertia weight; jumping to the target calculation step.

5. A power maintenance scheduling apparatus characterized by comprising: The power maintenance scheduling device comprises: a maintenance demand acquisition module, configured to acquire a plurality of power maintenance demands, wherein the power maintenance demand represents a required resource of target power maintenance; a constraint model establishment module, configured to determine a plurality of scheduling constraint models according to the plurality of power maintenance demands and a plurality of resource distributions, wherein the scheduling constraint model represents consumption of the resource during power maintenance; a target solving module, configured to solve the plurality of scheduling constraint models according to a scheduling target to obtain optimal solutions of the plurality of scheduling constraint models, wherein the scheduling target represents resource consumption in power maintenance; an output module, configured to output a scheduling strategy according to the optimal solutions of the plurality of scheduling constraint models. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 4.

6. A server comprising a memory and a processor, the memory having stored therein a computer program executable on the processor, characterized in that, The server of claim 6, the scheduling platform further comprises a plurality of scheduling terminals, the plurality of scheduling terminals are distributed in a plurality of maintenance centers, and the plurality of scheduling terminals are in signal connection with the server.

7. A scheduling platform, characterized by The scheduling terminal is configured to transmit the power maintenance demand to the server and receive the scheduling strategy generated by the server. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 4. ​ 8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: ​

Images