Online resource dynamic scheduling method and system of power transformation intelligent patrol cloud platform

Abstract

The invention belongs to the technical field of resource scheduling, and provides an online resource dynamic scheduling method and system for a power transformation intelligent patrol cloud platform, and the technical scheme comprises the steps: obtaining historical resource scheduling data of the power transformation intelligent patrol cloud platform; training a resource quantity prediction model based on the obtained historical resource scheduling data, and predicting the resource quantity required by the to-be-scheduled task based on the trained resource quantity prediction model; establishing a fitness function according to the total time and the total cost of the to-be-scheduled task, taking the fitness function as an optimization target, and scheduling idle resources of the service terminal by using a multi-target longhorn cattle herd combined artificial fish swarm hybrid algorithm to obtain an optimal resource scheduling scheme; the advantages of good global convergence of the artificial fish swarm algorithm and local rapid convergence, easy realization and the like of the Tiancattle swarm algorithm are comprehensively utilized, the defects that the convergence speed of the artificial fish swarm algorithm is low and the later global convergence of the Tiancattle swarm algorithm is poor are overcome, the advantages of the artificial fish swarm algorithm and the Tiancattle swarm algorithm are fully combined, and the optimal allocation problem of cloud resource scheduling can be well solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of resource scheduling, and in particular, relates to an online resource dynamic scheduling method and system for a substation intelligent patrol cloud platform. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The application background of the dynamic scheduling method and system of substation intelligent patrol online resources mainly stems from the rapid development of cloud storage and big data technology. With the popularization of cloud storage technology, more and more enterprises and organizations choose to migrate data and applications to the cloud to enjoy higher flexibility, scalability and cost-effectiveness. However, this also brings a challenge: how to effectively manage and schedule these cloud resources to meet changing business needs.

[0004] In the cloud environment of intelligent substation patrol, dynamic scheduling of resources becomes particularly important. Because cloud resources are shared, multiple users or applications may request the same resources at the same time. If resources are not properly scheduled, some users or applications may not get enough resources, which will affect their performance and availability. On the other hand, if some resources are idle for a long time, precious computing resources will be wasted. The existing resource scheduling schemes used are particle swarm and artificial fish swarm hybrid optimization algorithms, beetle swarm algorithms, cat swarm algorithms based on ant colony optimization, and other intelligent algorithms. The above algorithms have the disadvantages of slow convergence speed, narrow optimization range, and poor global or local convergence in the later stage of the algorithm, and cannot find the optimal resource scheduling scheme well. Summary of the invention

[0005] In order to solve at least one technical problem existing in the above-mentioned background technology, the present invention provides an online resource dynamic scheduling method and system of a substation intelligent patrol cloud platform, which applies the optimization idea of ​​artificial fish swarm to multi-target beetle swarm. Compared with the existing algorithms, the method can comprehensively utilize the good global convergence of the artificial fish swarm algorithm and the local fast convergence and easy implementation of the beetle swarm algorithm, overcome the shortcomings of slow convergence speed of the artificial fish swarm algorithm and poor global convergence of the beetle swarm algorithm in the later stage; fully combine the advantages of both, expand the optimization scope, effectively avoid the algorithm from falling into premature maturity too early, and make it easier to find the global optimal value; and without affecting the final optimization result, the search domain of the problem can be "narrowed", thereby accelerating the global search and improving the convergence speed and search accuracy of the optimization.

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

[0007] A first aspect of the present invention provides an online resource dynamic scheduling method of a substation intelligent patrol cloud platform, comprising the following steps:

[0008] Obtain historical resource dispatch data from the substation intelligent patrol cloud platform;

[0009] The resource quantity prediction model is trained based on the acquired historical resource scheduling data, and the resource quantity required for the task to be scheduled is predicted based on the trained resource quantity prediction model;

[0010] A fitness function is established according to the total time and total cost of the tasks to be scheduled, and the fitness function is used as the optimization target. The idle resources of the service terminal are scheduled using the multi-objective beetle swarm-artificial fish swarm hybrid algorithm to obtain the optimal resource scheduling plan; among them, the construction process of the multi-objective beetle swarm-artificial fish swarm hybrid algorithm includes: the spatial position of each beetle represents a candidate solution for the substation intelligent patrol resource scheduling plan, and the beetle swarm algorithm is improved by drawing on the foraging, clustering, following, and random optimization behaviors of artificial fish swarms. By comparing the fitness function values ​​of different beetle individuals or judging the number of beetles in the target direction of the beetle's movement, the position and speed of the beetles are continuously updated, and the position of the beetles in the optimized beetle swarm is the optimal resource scheduling plan.

[0011] Furthermore, the fitness function is:

[0012] minF(X)=min[F time (X),F cost (X)],

[0013]

[0014]

[0015] Among them, F time (X) is the total time of task scheduling, F cost (X) is the total cost of task scheduling, j is the processor number; m is the total number of processors in the cloud virtual system; h is the cloud task number; n is the total number of cloud tasks, A h is the cloud task assigned to the processor; V j is the speed of the jth processor; cost j The cost of scheduling each processor.

[0016] Furthermore, in the foraging behavior of longhorn beetles, the artificial fish school algorithm is borrowed to introduce a judgment strategy. It is assumed that at the kth iteration, the ith longhorn beetle searches in the s-dimensional space, randomly selects another longhorn beetle j within the field of view, and calculates the fitness function values ​​of the two longhorn beetles. If the function value of the jth longhorn beetle is less than that of the ith longhorn beetle, the ith longhorn beetle moves in the direction of longhorn beetle j; otherwise, random behavior is performed to randomly explore the position, movement direction and field of view.

[0017] Furthermore, the formula for the foraging behavior of longhorn beetles is:

[0018]

[0019]

[0020] Among them, k is the current iteration number, k max is the maximum number of iterations; is the position of the i-th longicorn beetle in the s-dimensional space at the k-th iteration; is the position of the jth longicorn beetle in the s-dimensional space at the kth iteration; is the moving speed of the i-th longicorn beetle in the s-dimensional space at the k-th iteration; is the moving speed of the i-th beetle in the s-dimensional space at the k+1th iteration, is the increment of the position of the i-th beetle in the s-dimensional space at the k-th iteration; λ is the weight coefficient between the individual movement speed of the beetle and the increment of the individual position of the beetle; rand is a random number between 0 and 1; Visual is the visual range of the beetle group, Visual max 、Visual min It is the maximum and minimum value of the field of view.

[0021] Furthermore, in the clustering and following behaviors of longhorn beetles, the artificial fish school algorithm is used to introduce a crowding factor. It is assumed that the number of longhorn beetles in the field of vision of the i-th longhorn beetle is h, and there is a longhorn beetle c at the center. The function value of longhorn beetle c at the center is smaller than the function value of the i-th longhorn beetle. In addition, if there is food at the center and the crowding degree meets the set conditions, the i-th longhorn beetle will move towards the direction of longhorn beetle c, otherwise it will perform foraging behavior.

[0022] Furthermore, the updated expression of the longhorn beetle velocity is:

[0023]

[0024] In the formula, is the optimal individual position of the i-th beetle in the s-dimensional space at the k-th iteration; is the global optimal position of the longhorn beetle group in the s-dimensional space at the kth iteration, is the moving speed of the i-th beetle in the s-dimensional space at the k-th iteration, is the position of the i-th beetle in the s-dimensional space at the k-th iteration, is the moving speed of the ith beetle in the s-dimensional space at the k+1th iteration, r1 and r2 are both random numbers varying in [0,1]; ω is the inertia weight; k max is the maximum number of iterations.

[0025] Furthermore, the expression of the increment of the position movement of the beetle speed is:

[0026]

[0027] Among them, δ k is the step size at the kth iteration, sign() is the sign function, is the fitness function value of the left antenna of the longicorn beetle at the kth iteration; is the fitness function value of the right antenna of the longicorn at the kth iteration; represents the position of the right antenna of the longicorn in the s-dimensional space at the k-th iteration; represents the position of the left antenna of the longicorn in the s-dimensional space at the k-th iteration, is the moving speed of the i-th longicorn beetle in the s-dimensional space at the k-th iteration.

[0028] A second aspect of the present invention provides an online resource dynamic scheduling system for a substation intelligent patrol cloud platform, comprising:

[0029] Historical data acquisition module, which is used to obtain historical resource scheduling data of the substation intelligent patrol cloud platform;

[0030] A resource quantity prediction module is used to train a resource quantity prediction model based on the acquired historical resource scheduling data, and predict the resource quantity required for the task to be scheduled based on the trained resource quantity prediction model;

[0031] A dynamic scheduling module is used to establish a fitness function according to the total time and total cost of the tasks to be scheduled, and to use the fitness function as the optimization target to schedule the idle resources of the service terminal using a multi-objective beetle swarm-artificial fish swarm hybrid algorithm to obtain the optimal resource scheduling plan; wherein, the construction process of the multi-objective beetle swarm-artificial fish swarm hybrid algorithm includes: using the spatial position of each beetle to represent a candidate solution for the substation intelligent patrol resource scheduling plan, and drawing on the foraging, clustering, following, and random optimization behaviors of artificial fish swarms to improve the beetle swarm algorithm, by comparing the fitness function values ​​of different beetle individuals or judging the number of beetles in the target direction of the beetle's movement, the position and speed of the beetles are continuously updated, and the position of the beetles in the optimized beetle swarm is the optimal resource scheduling plan.

[0032] A third aspect of the present invention provides a computer-readable storage medium.

[0033] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the online resource dynamic scheduling method of a substation intelligent patrol cloud platform as described above.

[0034] A fourth aspect of the present invention provides a computer device.

[0035] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the online resource dynamic scheduling method of a substation intelligent patrol cloud platform as described above are implemented.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention innovatively proposes a dynamic resource scheduling method, which applies the optimization idea of ​​artificial fish swarm to multi-target beetle swarms. Compared with the existing algorithms, the method comprehensively utilizes the advantages of good global convergence of the artificial fish swarm algorithm and local fast convergence and easy implementation of the beetle swarm algorithm, overcomes the shortcomings of slow convergence of the artificial fish swarm algorithm and poor global convergence of the beetle swarm algorithm in the later stage; fully combines the advantages of both, expands the optimization scope, effectively avoids the algorithm from falling into premature maturity too early, and is easier to find the global optimal value; and can "narrow" the search domain of the problem without affecting the final optimization result, thereby accelerating the global search, improving the convergence speed and search accuracy of the optimization, and improving the resource scheduling efficiency.

[0038] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0040] Figure 1 It is a flow chart of a method for dynamic scheduling of resources on a substation intelligent patrol line provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0042] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0043] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0044] In order to solve the defects of the existing resource scheduling algorithm mentioned in the background technology, the present invention establishes a fitness function according to the total time and total cost of the tasks to be scheduled, takes the fitness function as the optimization target, and uses a multi-objective beetle swarm-artificial fish swarm hybrid algorithm to schedule the idle resources of the service terminal to obtain the optimal resource scheduling plan; wherein, the construction process of the multi-objective beetle swarm-artificial fish swarm hybrid algorithm includes: the spatial position of each beetle represents a candidate solution of the substation intelligent patrol resource scheduling plan, and the foraging, clustering, following, and random optimization behaviors of artificial fish swarms are used to improve the beetle swarm algorithm, and the position and speed of the beetles are continuously updated by comparing the fitness function values ​​of different beetle individuals or judging the number of beetles in the target direction of the beetle movement. The position of the beetles in the optimized beetle swarm is the optimal resource scheduling plan.

[0045] Embodiment 1

[0046] like Figure 1 As shown, this implementation provides an online resource dynamic scheduling method for a substation intelligent patrol cloud platform, including the following steps:

[0047] Step 1: Obtain historical resource scheduling data from the substation intelligent patrol cloud platform;

[0048] Step 2: Train the resource quantity prediction model based on the acquired historical resource scheduling data, and predict the resource quantity required for the task to be scheduled based on the trained resource quantity prediction model;

[0049] In this embodiment, the resource quantity prediction model adopts a convolutional neural network model;

[0050] Step 3: Establish a fitness function as the optimization objective based on the total time and total cost of the tasks to be scheduled;

[0051] Among them, the total task scheduling time is:

[0052]

[0053] The total cost of task scheduling is:

[0054]

[0055] Where j is the processor number; m is the total number of processors in the cloud virtual system; h is the cloud task number; n is the total number of cloud tasks, A h is the cloud task assigned to the processor; V j is the speed of the jth processor; cost j The cost of scheduling each processor;

[0056] The objective function is:

[0057] min F(X)=min[F time (X),F cost (X)] (3).

[0058] Step 4: Taking the fitness function as the optimization target, the multi-objective beetle swarm combined with the artificial fish swarm hybrid algorithm is used to schedule the idle resources of the service terminal to obtain the optimal resource scheduling solution;

[0059] When the idle resources of the service terminal are scheduled by using a multi-objective beetle swarm combined with an artificial fish swarm hybrid algorithm, the spatial position of each beetle represents a candidate solution for the intelligent patrol resource scheduling scheme of the substation. By referring to the optimization behavior of artificial fish swarms (foraging, clustering, following, and randomness), the beetle swarm algorithm is improved and a multi-objective beetle swarm-artificial fish swarm hybrid algorithm is proposed, which includes the following steps:

[0060] Step 401, parameter initialization, initializing parameters such as individual positions, number of beetles, field of view, crowding factor, maximum number of iterations, step length, etc. in the beetle group, creating cloud tasks and setting the number and length of cloud tasks according to actual needs;

[0061] Step 402, the bulletin board is initialized, the corresponding fitness value is calculated according to the initial position of each longhorn beetle in the initial longhorn beetle group, and the values ​​are compared, and the smaller value is assigned to the bulletin board;

[0062] Step 403, comparing the fitness values ​​of the longhorn beetles, each longhorn beetle updates its position by simulating foraging, flocking, following and random behaviors, comparing the individual fitness values ​​of the longhorn beetles in the longhorn beetle group obtained after each optimization, and selecting the smaller value;

[0063] Among them, in the foraging behavior of the longhorn beetle, it is assumed that at the kth iteration, the i-th longhorn beetle searches in the s-dimensional space, randomly selects another longhorn beetle j within the field of view, and calculates the fitness function values ​​of the two longhorn beetles. If the function value of the j-th longhorn beetle is less than the function value of the i-th longhorn beetle, the i-th longhorn beetle moves in the direction of longhorn beetle j; otherwise, it performs random behavior and randomly explores a better position. The mathematical description is:

[0064]

[0065] In the original beetle swarm algorithm, the position update formula is:

[0066] Drawing on the artificial fish swarm algorithm, the judgment strategy is introduced (if the function value of the jth beetle is less than the function value of the ith beetle, the ith beetle moves towards the direction of beetle j; otherwise, random behavior is performed, that is, randomly exploring a better position), the movement direction quantity Visual field of view.

[0067] If the function value of the jth beetle is less than the function value of the ith beetle, the ith beetle moves in the direction of beetle j, according to the formula Seek excellence;

[0068] Otherwise, random behavior is performed, that is, randomly exploring a better position, according to the formula Seek excellence.

[0069] In the formula, s = 1, 2, ....., S, i = 1, 2, ....., n; S is the dimension of the space; n is the number of longhorn beetles; k is the current number of iterations, k max is the maximum number of iterations; is the position of the i-th longicorn beetle in the s-dimensional space at the k-th iteration; is the position of the jth longicorn beetle in the s-dimensional space at the kth iteration; is the moving speed of the i-th longicorn beetle in the s-dimensional space at the k-th iteration; is the increment of the position of the i-th beetle in the s-dimensional space at the k-th iteration; λ is the weight coefficient between the individual movement speed of the beetle and the increment of the individual position of the beetle; rand is a random number between 0 and 1; Visual is the visual range of the beetle group, Visual max 、Visual min It is the maximum and minimum value of the field of view.

[0070] The flocking behaviors of longhorn beetles include:

[0071] Assume that the number of beetles in the field of vision of the i-th beetle is h, there is a beetle c in the center, whose function value is smaller than that of the i-th beetle, and there is more food in the center and it is not too crowded, then the i-th beetle moves in the direction of beetle c, otherwise the i-th beetle continues to forage, which can be described mathematically as:

[0072]

[0073] Drawing on the artificial fish school algorithm, the crowding factor is introduced to determine whether the target location is crowded.

[0074] If the number of beetles in the field of vision of the i-th beetle is h, there is a beetle c in the center whose function value is smaller than that of the i-th beetle, and there is more food in the center and it is not too crowded, then the i-th beetle moves in the direction of beetle c. According to the formula Seek excellence;

[0075] Otherwise, the longhorn beetles performed foraging behaviors.

[0076] In the formula, is the position of the cth longhorn beetle in the center in the kth iteration in the s-dimensional space; h is the number of longhorn beetles in the field of view; α is the crowding factor.

[0077] Following behaviors of longhorn beetles include:

[0078] Assume that the number of beetles in the field of vision of the i-th beetle is h, and there is a beetle m in the place with the most food, whose function value is less than that of the i-th beetle, and the place is not too crowded, then the i-th beetle moves in the direction of beetle m, otherwise the i-th beetle continues to forage for food. The mathematical description is:

[0079]

[0080] Drawing on the artificial fish school algorithm, the crowding factor is introduced to determine whether the target location is crowded.

[0081] If the number of beetles in the field of vision of the i-th beetle is h, and there is a beetle m in the place with the most food, and the place is not too crowded, then the i-th beetle moves in the direction of beetle m, according to the formula Seek excellence;

[0082] Otherwise, the longhorn beetles performed foraging behaviors.

[0083] In the formula, is the position of the mth longhorn beetle in the s-dimensional space at the kth iteration; h is the number of longhorn beetles within the field of view.

[0084] The updated expression of the longicorn velocity is:

[0085]

[0086] In the formula,

[0087] is the optimal individual position of the i-th beetle in the s-dimensional space at the k-th iteration; is the global optimal position of the longhorn beetle group in the s-dimensional space at the kth iteration, r1 and r2 are both random numbers varying in [0,1]; ω is the inertia weight; k max is the maximum number of iterations;

[0088] The increment of the position of the i-th beetle in the s-dimensional space at the k+1th iteration is:

[0089]

[0090] δ k is the step size at the kth iteration, sign() is the sign function, is the fitness function value of the left antenna of the longicorn beetle at the kth iteration; is the fitness function value of the right antenna of the longicorn at the kth iteration; represents the position of the right antenna of the longicorn in the s-dimensional space at the k-th iteration; represents the position of the left antenna of the longicorn in the s-dimensional space at the k-th iteration;

[0091] when In order to find the minimum value of the objective function, the beetle will move to the right, and vice versa.

[0092] The search behaviors of the left and right antennae of the longicorn beetle are expressed as follows:

[0093]

[0094] in, represents the position of the right antenna of the longicorn in the s-dimensional space at the k+1th iteration; represents the position of the left antenna of the longicorn beetle in the s-dimensional space at the k+1th iteration; d k is the distance between the left and right antennae of the longicorn beetle at the kth iteration; e is a constant in [0,2];

[0095] Step 404: updating the position and speed of the longhorn beetle, using formula (4) to formula (12) to update the position and speed of the longhorn beetle individual;

[0096] Step 405: Update the fitness value of the longhorn beetle group. For each longhorn beetle, if its fitness value is less than the optimal position P it has experienced, is The fitness value of the longhorn beetle is taken as the optimal position P of the current individual. is ; if P is The fitness value is less than the best position P experienced by the beetle group. gs The fitness value of the beetle group updates the global optimal position P gs ;

[0097] Step 406: Update the bulletin board and update the P obtained in step 405. gs Compare with the value on the bulletin board. If it is less than the value on the bulletin board, update the bulletin board. Otherwise, the value on the bulletin board remains unchanged.

[0098] Step 407: Repeat steps 404 to 406 to allocate the optimal resource solution for all scheduling tasks;

[0099] Step 408: If the objective function value reaches a satisfactory error range or the number of iterations reaches a maximum value, the optimal solution (i.e., the position of the longhorn beetle on the bulletin board and the optimal value) is output, and the optimization algorithm terminates, otherwise, go to step 404;

[0100] Step 409: Determine the n+1th iteration f(X n+1 ) and the nth iteration f(X n )’s fitness function value difference absolute value f(X n+1 )-f(X n) is less than a sufficiently small positive number ε, that is, the values ​​of the two iterations are relatively close, then the algorithm is considered to have reached convergence, the algorithm terminates, the optimal position and the optimal value are updated on the bulletin board, and the process goes to step 408, otherwise, the process goes to step 403;

[0101] Step 410: Feedback the scheduled resource information to the service terminal to update the resource status.

[0102] The present invention draws on the optimization behavior of artificial fish swarms (foraging, clustering, following, randomness), improves the beetle swarm algorithm, and proposes a multi-objective beetle swarm-artificial fish swarm hybrid algorithm. The algorithm comprehensively utilizes the advantages of the artificial fish swarm algorithm, such as good global convergence, local fast convergence, and easy implementation of the beetle swarm algorithm, to overcome the shortcomings of the slow convergence speed of the artificial fish swarm algorithm and the poor global convergence of the beetle swarm algorithm in the later stage, and fully combines the advantages of both, and is applied to solve the optimal allocation problem of cloud resource scheduling. Compared with the commonly used methods, the multi-objective beetle swarm-artificial fish swarm hybrid algorithm has several advantages, such as expanding the optimization scope, effectively avoiding the algorithm from falling into premature maturity too early, and making it easier to find the global optimal value; and without affecting the final optimization result, the search domain of the problem can be "narrowed", thereby accelerating the global search and improving the convergence speed and search accuracy of the optimization.

[0103] After obtaining the optimal cloud resource scheduling plan, the optimal cloud resource scheduling plan formed by the smart patrol data scheduling center is output to the smart patrol data display and collection center, the smart patrol multimodal data management center, and the smart patrol model management center for data display and collection, intelligent identification, deduplication, and cleaning of substation defect images, audio and video, infrared and other data, training, evaluation, quota management, remote deployment of power artificial intelligence models, and monitoring of data and model resources.

[0104] The Zhixun multimodal data management center and the Zhixun model management center can monitor and update data and model resource scheduling in real time during cloud resource scheduling, and feed back the monitoring results to the Zhixun data scheduling center to avoid confusion in cloud resource scheduling.

[0105] Embodiment 2

[0106] This embodiment provides an online resource dynamic scheduling system of a substation intelligent patrol cloud platform, including:

[0107] Historical data acquisition module, which is used to obtain historical resource scheduling data of the substation intelligent patrol cloud platform;

[0108] A resource quantity prediction module is used to train a resource quantity prediction model based on the acquired historical resource scheduling data, and predict the resource quantity required for the task to be scheduled based on the trained resource quantity prediction model;

[0109] A dynamic scheduling module is used to establish a fitness function according to the total time and total cost of the tasks to be scheduled, and to use the fitness function as the optimization target to schedule the idle resources of the service terminal using a multi-objective beetle swarm-artificial fish swarm hybrid algorithm to obtain the optimal resource scheduling plan; wherein, the construction process of the multi-objective beetle swarm-artificial fish swarm hybrid algorithm includes: using the spatial position of each beetle to represent a candidate solution for the substation intelligent patrol resource scheduling plan, and drawing on the foraging, clustering, following, and random optimization behaviors of artificial fish swarms to improve the beetle swarm algorithm, by comparing the fitness function values ​​of different beetle individuals or judging the number of beetles in the target direction of the beetle's movement, the position and speed of the beetles are continuously updated, and the position of the beetles in the optimized beetle swarm is the optimal resource scheduling plan.

[0110] Embodiment 3

[0111] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the online resource dynamic scheduling method of the substation intelligent patrol cloud platform as described above are implemented.

[0112] Embodiment 4

[0113] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the online resource dynamic scheduling method of the substation intelligent patrol cloud platform as described above are implemented.

[0114] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0115] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. 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 dynamic online resource scheduling of a substation intelligent patrol cloud platform, characterized in that: The steps include: Obtain historical resource dispatch data from the substation intelligent patrol cloud platform; The resource quantity prediction model is trained based on the acquired historical resource scheduling data, and the resource quantity required for the task to be scheduled is predicted based on the trained resource quantity prediction model; A fitness function is established according to the total time and total cost of the tasks to be scheduled, and the fitness function is used as the optimization target. The idle resources of the service terminal are scheduled using the multi-objective beetle swarm-artificial fish swarm hybrid algorithm to obtain the optimal resource scheduling plan; among them, the construction process of the multi-objective beetle swarm-artificial fish swarm hybrid algorithm includes: the spatial position of each beetle represents a candidate solution for the substation intelligent patrol resource scheduling plan, and the beetle swarm algorithm is improved by drawing on the foraging, clustering, following, and random optimization behaviors of artificial fish swarms. By comparing the fitness function values ​​of different beetle individuals or judging the number of beetles in the target direction of the beetle's movement, the position and speed of the beetles are continuously updated, and the position of the beetles in the optimized beetle swarm is the optimal resource scheduling plan.

2. The online resource dynamic scheduling method of the substation intelligent patrol cloud platform according to claim 1 is characterized in that: The fitness function is: minF(X)=min[F time (X),F cost (X)], Among them, F time (X) is the total time of task scheduling, F cost (X) is the total cost of task scheduling, j is the processor number; m is the total number of processors in the cloud virtual system; h is the cloud task number; n is the total number of cloud tasks, A h is the cloud task assigned to the processor; V j is the speed of the jth processor; cost j The cost of scheduling each processor.

3. The online resource dynamic scheduling method of the substation intelligent patrol cloud platform according to claim 1 is characterized in that: In the foraging behavior of longhorn beetles, the artificial fish school algorithm is used to introduce a judgment strategy. It is assumed that at the kth iteration, the ith longhorn beetle searches in the s-dimensional space, randomly selects another longhorn beetle j within the field of view, and calculates the fitness function values ​​of the two longhorn beetles. If the function value of the jth longhorn beetle is less than that of the ith longhorn beetle, the ith longhorn beetle moves in the direction of longhorn beetle j; otherwise, random behavior is performed to randomly explore the position, movement direction and field of view.

4. The online resource dynamic scheduling method of the substation intelligent patrol cloud platform according to claim 1 is characterized in that: The formula for the foraging behavior of longhorn beetles is: Among them, k is the current iteration number, k max is the maximum number of iterations; is the position of the i-th longicorn beetle in the s-dimensional space at the k-th iteration; is the position of the jth longicorn beetle in the s-dimensional space at the kth iteration; is the moving speed of the i-th longicorn beetle in the s-dimensional space at the k-th iteration; is the moving speed of the i-th beetle in the s-dimensional space at the k+1th iteration, is the increment of the position of the i-th beetle in the s-dimensional space at the k-th iteration; λ is the weight coefficient between the individual movement speed of the beetle and the increment of the individual position of the beetle; rand is a random number between 0 and 1; Visual is the visual range of the beetle group, Visual max 、Visual min It is the maximum and minimum value of the field of view.

5. The online resource dynamic scheduling method of the substation intelligent patrol cloud platform according to claim 1 is characterized in that: In the herding and following behaviors of longhorn beetles, the artificial fish school algorithm is used to introduce a crowding factor. It is assumed that the number of longhorn beetles in the field of vision of the i-th longhorn beetle is h, and there is a longhorn beetle c at the center. The function value of longhorn beetle c at the center is smaller than the function value of the i-th longhorn beetle. In addition, if there is food at the center and the crowding degree meets the set conditions, the i-th longhorn beetle will move towards the direction of longhorn beetle c, otherwise it will perform foraging behavior.

6. The online resource dynamic scheduling method of the substation intelligent patrol cloud platform according to claim 1 is characterized in that: The updated expression of the longicorn velocity is: In the formula, is the optimal individual position of the i-th beetle in the s-dimensional space at the k-th iteration; is the global optimal position of the longhorn beetle group in the s-dimensional space at the kth iteration, is the moving speed of the i-th beetle in the s-dimensional space at the k-th iteration, is the position of the i-th beetle in the s-dimensional space at the k-th iteration, is the moving speed of the ith beetle in the s-dimensional space at the k+1th iteration, r1 and r2 are both random numbers varying in [0,1]; ω is the inertia weight; k max is the maximum number of iterations.

7. The method for dynamic online resource scheduling of a substation intelligent patrol cloud platform according to claim 1, characterized in that: The expression of the increment of the position movement of the beetle speed is: Among them, δ k is the step size at the kth iteration, sign() is the sign function, is the fitness function value of the left antenna of the longicorn beetle at the kth iteration; is the fitness function value of the right antenna of the longicorn at the kth iteration; represents the position of the right antenna of the longicorn in the s-dimensional space at the k-th iteration; represents the position of the left antenna of the longicorn in the s-dimensional space at the k-th iteration, is the moving speed of the i-th longicorn beetle in the s-dimensional space at the k-th iteration.

8. An online resource dynamic scheduling system for a substation intelligent patrol cloud platform, characterized in that: include: A historical data acquisition module, which is used to obtain historical resource scheduling data of the substation intelligent patrol cloud platform; A resource quantity prediction module is used to train a resource quantity prediction model based on the acquired historical resource scheduling data, and predict the resource quantity required for the task to be scheduled based on the trained resource quantity prediction model; A dynamic scheduling module is used to establish a fitness function according to the total time and total cost of the tasks to be scheduled, and to use the fitness function as the optimization target to schedule the idle resources of the service terminal using a multi-objective beetle swarm-artificial fish swarm hybrid algorithm to obtain the optimal resource scheduling plan; wherein, the construction process of the multi-objective beetle swarm-artificial fish swarm hybrid algorithm includes: using the spatial position of each beetle to represent a candidate solution for the substation intelligent patrol resource scheduling plan, and drawing on the foraging, clustering, following, and random optimization behaviors of artificial fish swarms to improve the beetle swarm algorithm, by comparing the fitness function values ​​of different beetle individuals or judging the number of beetles in the target direction of the beetle's movement, the position and speed of the beetles are continuously updated, and the position of the beetles in the optimized beetle swarm is the optimal resource scheduling plan.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the online resource dynamic scheduling method of a substation intelligent patrol cloud platform as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the online resource dynamic scheduling method of the substation intelligent patrol cloud platform as described in any one of claims 1-7 are implemented.

Images