Power grid equipment communication state evaluation method and device, electronic equipment and storage medium

Abstract

The invention discloses a power grid equipment communication state evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: constructing an initial BP neural network, obtaining a training sample, setting R stages, and setting T iterations for each stage; using the training samples as particles in the population, and initializing the particles in the population; when single iteration is carried out in each stage, the fitness of each particle in the initial population is solved; screening and updating a particle optimal solution and a global optimal solution through a crisscross algorithm; when the traversal of the R stages is completed, taking a final global optimal solution as a network parameter of the BP neural network; and performing model training on the BP neural network based on the training sample to obtain an evaluation model, and evaluating the communication state of the power grid equipment by adopting the evaluation model. The convergence speed of the algorithm is accelerated, the global search capability is improved, the network parameters of the BP neural network can be quickly obtained, the evaluation work efficiency is high, and the accuracy is high.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid equipment maintenance, and in particular to a method, device, electronic equipment and storage medium for evaluating the communication status of power grid equipment. Background Art

[0002] During the extensive application of distribution network automation equipment, the distribution network automation terminals need to be debugged and configured during the installation and commissioning phase, as well as the operation and maintenance and troubleshooting phase. This is especially true for access debugging with the master station, which involves the online launch of automation terminals and debugging and verification of corresponding automation communication points.

[0003] Under the existing debugging mechanism, it is necessary to ensure that the on-site communication is normal in order to complete the entire debugging work of the complete set of automation equipment. The current main practice is to confirm that the communication of the complete set of equipment is normal through multiple inspections by personnel and multiple communications and tests with the main station, and the operating efficiency is low. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method, device, electronic device and storage medium for evaluating the communication status of power grid equipment.

[0005] In a first aspect, the present invention provides a method for evaluating communication status of power grid equipment, comprising:

[0006] Constructing an initial BP neural network and obtaining training samples, setting R stages, setting T iterations for each stage, and the training samples including historical operation status information;

[0007] Use the training samples as particles in the population to initialize the particles in the population;

[0008] When performing a single iteration in each stage, the fitness of each particle in the initial population is calculated according to the preset fitness function;

[0009] Filter and update the particle optimal solution and the global optimal solution through the vertical and horizontal cross algorithm;

[0010] When R phased traversals are completed, the final global optimal solution is used as the network parameters of the BP neural network;

[0011] Performing model training on the BP neural network based on the training samples to obtain an evaluation model;

[0012] The evaluation model is used to evaluate the communication status of power grid equipment.

[0013] In a second aspect, the present invention provides a power grid equipment communication status evaluation device, comprising:

[0014] An algorithm construction module is used to construct an initial BP neural network and obtain training samples, setting R stages, each stage setting T iterations, and the training samples include historical operation status information;

[0015] An initialization module is used to use the training samples as particles in the population to initialize the particles in the population;

[0016] The fitness calculation module is used to calculate the fitness of each particle in the initial population according to a preset fitness function during a single iteration in each stage;

[0017] The optimization module is used to screen and update the particle optimal solution and the global optimal solution through the vertical and horizontal cross algorithm;

[0018] The network parameter determination module is used to use the final global optimal solution as the network parameters of the BP neural network when the R phased traversals are completed;

[0019] An evaluation model training module is used to perform model training on the BP neural network based on the training samples to obtain an evaluation model;

[0020] The evaluation module is used to evaluate the communication status of the power grid equipment by using the evaluation model.

[0021] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0022] at least one processor; and

[0023] a memory communicatively connected to the at least one processor; wherein,

[0024] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for evaluating the communication status of power grid equipment described in the first aspect of the present invention.

[0025] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to implement the method for evaluating the communication status of power grid equipment according to the first aspect of the present invention when executed.

[0026] The communication status evaluation method of power grid equipment provided by the embodiment of the present invention includes: constructing an initial BP neural network and obtaining training samples, setting R stages, setting T iterations for each stage, and the training samples include historical operation status information; using the training samples as particles in the population to initialize the particles in the population; when performing a single iteration in each stage, the fitness of each particle in the initial population is calculated according to a preset fitness function; screening and updating the particle optimal solution and the global optimal solution through a vertical and horizontal cross algorithm; when the R stage traversal is completed, the final global optimal solution is used as the network parameter of the BP neural network; training the BP neural network model based on the training samples to obtain an evaluation model, and using the evaluation model to evaluate the communication status of the power grid equipment. During the training process of the BP neural network, the error is insensitive to the change of the weight, resulting in a large number of iterations and a slow convergence speed, and it is very easy to fall into a local minimum. Now, the optimal parameters of the BP neural network are searched by using the improved vertical and horizontal cross search, the convergence speed of the BP neural network is accelerated, the global search capability is improved, and it is conducive to quickly obtaining the network parameters of the BP neural network. When the evaluation model is used to evaluate the communication status of the device, the process is automated, the operation efficiency is high, and the accuracy is high.

[0027] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 is a flow chart of a method for evaluating communication status of power grid equipment provided by an embodiment of the present invention;

[0030] Figure 2 is a flow chart of a method for evaluating communication status of power grid equipment provided by an embodiment of the present invention;

[0031] Figure 3 It is a structural schematic diagram of a power grid equipment communication status evaluation device provided by an embodiment of the present invention;

[0032] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] The embodiment of the present invention uses a BP neural network, namely a Back Propagation neural network, which is a multi-layer feedforward neural network trained according to an error back propagation algorithm. Structurally, the BP network has an input layer, a hidden layer and an output layer.

[0035] Figure 1 A flow chart of a method for evaluating the communication status of power grid equipment provided in an embodiment of the present invention. This embodiment is applicable to situations where the communication status of power grid equipment is evaluated. Specifically, the power grid equipment may be a communication device or other equipment including a communication function.

[0036] The method may be executed by a power grid device communication status evaluation device, which may be implemented in the form of hardware and / or software, and may be configured in an electronic device.

[0037] like Figure 1 As shown, the power grid equipment communication status evaluation method includes:

[0038] S101, constructing an initial BP neural network and obtaining training samples, setting R stages, and setting T iterations for each stage.

[0039] The parameters of the BP neural network mainly include weights and thresholds. In the initial BP neural network, the initial values ​​of the weights and thresholds can be predefined.

[0040] The training samples include historical operation status information, which can be obtained from the background management system of the device. The operation status information mainly includes: environmental public network signals, network traffic, average message delay time and bit error rate.

[0041] In this step, there are R phases, and each phase is set with T iteration times, that is, each phase performs T iterations. R and T are both positive integers.

[0042] S102: Using the training samples as particles in the population to initialize the particles in the population.

[0043] Specifically, we can first obtain the population size M (i.e., the number of particles), the algorithm dimension D, and the random initial probability Pc to randomly generate the initial position of each particle, i.e., the initial value of the particle.

[0044] S103, when performing a single iteration in each stage, the fitness of each particle in the initial population is calculated according to a preset fitness function.

[0045] The specific method for calculating the fitness of particles can be set based on demand.

[0046] In each round of iteration, the fitness of each particle can be traversed, and the parameters of each particle can be evaluated through the fitness, so as to update the individual optimal solution of each particle (that is, the current optimal parameters of the particle) and the group extreme value of the particle group (that is, the optimal parameters of all particles) according to the fitness.

[0047] S104, screening and updating the particle optimal solution and the global optimal solution through the vertical and horizontal cross algorithm.

[0048] The Crisscross optimization algorithm can evaluate the degree of dispersion of a population by calculating the distribution of individuals in the population in the sample plot.

[0049] S104 specifically includes: performing horizontal crossing on the same dimension between two different particles, calculating the fitness of the particles before and after the crossing, and updating the population using a greedy algorithm; performing vertical crossing on different dimensions of the same particle, calculating the fitness of the particles before and after the crossing, and updating the population using a greedy algorithm.

[0050] The specific formula for horizontal crossover is:

[0051]

[0052] Among them, r1 and r2 are random numbers in the range of [0, 1], c1 and c2 are random numbers with average distribution in the range of [-1, 1]; X m (d) and X n (d) is the parent particle X m and X n dth dimension of and Yes X m and X n The d-th dimension offspring generated by the lateral operation.

[0053] The specific formula for vertical crossover is:

[0054]

[0055] Where r is a random number in the range [0, 1]. is the parent particle X m The offspring generated by vertical crossover between the d1th and d2th dimensions.

[0056] Greedy algorithm (Greedv Alaorihm) is an algorithm design method based on greedy strategy. In each step of selection, the greedy algorithm always chooses the option that currently seems to be the best, without considering the overall optimal solution. Then, in each round of iteration, the fitness of each particle before and after the crossover operation (parent and child) can be traversed, and the parameters of each particle can be evaluated by fitness, so as to update the individual optimal solution of each particle (that is, the current optimal parameters of the particle) according to the fitness. After determining the individual optimal solution of the particle, the group extreme value of the particle group (that is, the optimal parameters of all particles) can be determined.

[0057] Optionally, after each stage-by-stage traversal is completed, it also includes: calculating the maximum number of iterations based on the number of stages R and the number of iterations T; obtaining the degree of dispersion of the population; based on the degree of adaptation between the degree of dispersion and the maximum number of iterations; adjusting the population size based on the degree of adaptation so that the degree of dispersion is adapted to the maximum number of iterations.

[0058] The maximum number of iterations Max = R×T.

[0059] Setting the maximum number of iterations can limit the convergence speed of the neural network and ensure the efficiency of the algorithm. Setting multiple stages can divide the algorithm topology into several parts, which is convenient for adjusting the population size in each stage to ensure faster convergence speed and higher accuracy at the same time.

[0060] The reason for adjusting the population size is that the crossover algorithm is prone to fall into the local optimum in the later stage and fail to obtain the global optimal solution. By adjusting the population size after each stage is completed and introducing a disturbance factor, the algorithm can be prevented from falling into the local optimum and the global search capability of the algorithm can be improved. When the degree of dispersion is relatively dispersed, the number of iterations required is large, which will make the algorithm converge slowly and inefficient. If the number of iterations required exceeds the maximum number of iterations, it means that the population size needs to be reduced. When the degree of dispersion is relatively concentrated, the number of iterations required is small. If the number of iterations required exceeds the maximum number of iterations, it is easy to fall into the local optimum and fail to obtain the global optimal solution. Therefore, it is necessary to introduce a disturbance factor to increase the population size.

[0061] S105. When R phased traversals are completed, the final global optimal solution is used as the network parameters of the BP neural network.

[0062] The weights and thresholds corresponding to the final global optimal solution are used to set the parameters of the BP neural network.

[0063] S106. Perform model training on the BP neural network based on the training samples to obtain an evaluation model.

[0064] Specifically, the method includes: performing model training on the BP neural network to obtain the currently trained BP neural network; calculating the model accuracy of the trained BP neural network; judging whether the model accuracy meets the accuracy requirement; if so, outputting the BP neural network as an evaluation model; if not, re-training the model.

[0065] In addition, you can also set a validation data set to verify the trained evaluation model.

[0066] The step of calculating the model accuracy of the trained BP neural network includes: obtaining a state evaluation value and an actual evaluation value of the trained BP neural network; and calculating a mean square error between the state evaluation value and the actual evaluation value as the model accuracy of the trained BP neural network.

[0067] The formula for calculating the mean square error is as follows:

[0068]

[0069] Among them, P i The state evaluation value output by the model; is the actual evaluation value; N is the number of training samples. The mean square error is used to measure the difference between the predicted value (state evaluation value) and the actual value (actual evaluation value). In this formula, f(i) represents the mean square error of the i-th sample. The mean square error can be obtained by calculating the square of the difference between the predicted value and the actual value of each sample and then averaging it. The smaller the mean square error, the closer the predicted value is to the actual value, and the better the prediction effect of the model.

[0070] Specifically, the evaluation value of the model state can be normalized. Since the communication state of the device is the system output, it is a dimensionless quantitative indicator between 0 and 1, corresponding to the four performance evaluation levels of excellent, good, medium, and poor. The larger the value, the higher the device communication performance, and vice versa. The specific score division is as follows:

[0071] Evaluation value 0.8-1: excellent;

[0072] Evaluation value 0.6-0.8: good;

[0073] Evaluation value 0.4-0.6: medium;

[0074] Evaluation value below 0.4: Poor.

[0075] S107. Use the evaluation model to evaluate the communication status of the power grid equipment.

[0076] Specifically, the real-time operation status information of the device is obtained during operation; the real-time operation status information is input into a trained evaluation model to obtain a communication status evaluation result of the device.

[0077] Optionally, before acquiring the real-time running status information of the device during running, the method further includes:

[0078] Read the device's communication protocol, IP address parameters, line connection status and environmental signal strength;

[0079] Determining whether the communication infrastructure settings of the device are correct through preset communication standard setting information, the communication protocol, and the IP address parameters;

[0080] If so, determining whether a start condition is met, the start condition comprising that the line connection state is a connected state and the environmental signal strength is greater than a preset communication strength standard value;

[0081] When the start condition is met, the device is started.

[0082] Through the above parameter verification before the device is started, it can be ensured that the communication infrastructure settings of the device are correct and the device is started on the basis of meeting the startup conditions, avoiding other interference factors affecting the evaluation of the communication status.

[0083] In order to clearly illustrate the training process of the evaluation model in this embodiment, Figure 2 As shown in the following example, the training process includes the following steps:

[0084] S1: Start;

[0085] S2: Establish BP neural network and determine relevant parameters;

[0086] S3: Initialize the population and determine the parameters of the CSO algorithm;

[0087] S4: number of stages r = 1;

[0088] S5: number of iterations t = 1;

[0089] S6: Calculate population fitness;

[0090] S7: record individual optimal and global optimal;

[0091] S8: Determine whether the maximum number of iterations T in each stage has been reached;

[0092] If not, proceed to S9; if not, proceed to S12;

[0093] S9: number of iterations t = t + 1;

[0094] S10: Perform lateral operations and adopt a greedy strategy to compete with the parent generation and update the population;

[0095] S11: Execute vertical operations and adopt a greedy strategy to compete with the parent generation and update the population;

[0096] After executing S11, return to execute S6;

[0097] S12: Determine whether the maximum number of stages R has been reached;

[0098] If not, proceed to S13; if not, proceed to S15;

[0099] S13: Change population size according to dispersion;

[0100] S14: number of stages r = r + 1;

[0101] After executing S14, enter S5;

[0102] S15: Take the global optimal solution of the CSO algorithm as the weight and threshold of the BP neural network;

[0103] S16: training BP neural network;

[0104] S17: Determine whether the accuracy requirement is met;

[0105] If yes, go to S18 to output the model, if no, go to S4 to retrain the model.

[0106] S18: Evaluation model of the communication status of the output device;

[0107] S19: End.

[0108] The communication status evaluation method of power grid equipment provided by the embodiment of the present invention includes: constructing an initial BP neural network and obtaining training samples, setting R stages, setting T iterations for each stage, and the training samples include historical operation status information; using the training samples as particles in the population to initialize the particles in the population; when performing a single iteration in each stage, the fitness of each particle in the initial population is calculated according to a preset fitness function; screening and updating the particle optimal solution and the global optimal solution through a vertical and horizontal cross algorithm; when the R stage traversal is completed, the final global optimal solution is used as the network parameter of the BP neural network; training the BP neural network model based on the training samples to obtain an evaluation model, and using the evaluation model to evaluate the communication status of the power grid equipment. During the training process of the BP neural network, the error is insensitive to the change of the weight, resulting in a large number of iterations and a slow convergence speed, and it is very easy to fall into a local minimum. Now, the optimal parameters of the BP neural network are searched by using the improved vertical and horizontal cross search, the convergence speed of the BP neural network is accelerated, the global search capability is improved, and it is conducive to quickly obtaining the network parameters of the BP neural network. When the evaluation model is used to evaluate the communication status of the device, the process is automated, the operation efficiency is high, and the accuracy is high.

[0109] Figure 3 A schematic diagram of the structure of a power grid equipment communication status evaluation device provided by an embodiment of the present invention. Figure 3 As shown, the power grid equipment communication status evaluation device includes:

[0110] Algorithm construction module 301, used to construct an initial BP neural network and obtain training samples, set R stages, each stage is set with T iterations, and the training samples include historical operation status information;

[0111] An initialization module 302 is used to initialize particles in the population by using training samples as particles in the population;

[0112] The fitness calculation module 303 is used to calculate the fitness of each particle in the initial population according to a preset fitness function when performing a single iteration in each stage;

[0113] An optimization module 304 is used to screen and update the particle optimal solution and the global optimal solution through a vertical and horizontal cross algorithm;

[0114] A network parameter determination module 305 is used to use the final global optimal solution as the network parameters of the BP neural network when the R phased traversals are completed;

[0115] An evaluation model training module 306 is used to perform model training on the BP neural network based on the training samples to obtain an evaluation model;

[0116] The evaluation module 307 is used to evaluate the communication status of the power grid equipment using the evaluation model.

[0117] Optionally, the optimization module 304 includes:

[0118] The first update submodule is used to perform horizontal crossover of the same dimension between two different particles, calculate the fitness of the particles before and after the crossover, and use a greedy algorithm to update the population;

[0119] The second update submodule is used to vertically cross different dimensions of the same particle, calculate the fitness of the particle before and after the crossover, and use a greedy algorithm to update the population.

[0120] Optionally, the power grid equipment communication status evaluation device further includes:

[0121] A maximum iteration number calculation module is used to calculate the maximum iteration number based on the number of stages R and the number of iterations T after each stage traversal is completed;

[0122] A dispersion degree acquisition module is used to obtain the dispersion degree of the population;

[0123] An adaptation degree calculation module, used for calculating the adaptation degree based on the dispersion degree and the maximum number of iterations;

[0124] A population size adjustment module is used to adjust the population size based on the adaptation degree so that the dispersion degree is adapted to the maximum number of iterations.

[0125] Optionally, the evaluation model training module 306 includes:

[0126] The evaluation model training submodule is used to perform model training on the BP neural network to obtain the currently trained BP neural network;

[0127] The model accuracy calculation submodule is used to calculate the model accuracy of the trained BP neural network;

[0128] The accuracy judgment submodule is used to judge whether the accuracy of the model meets the accuracy requirements; if so, the content of the output submodule is executed, otherwise it returns to execute the content of the evaluation model training submodule.

[0129] The output submodule is used to output the BP neural network as an evaluation model.

[0130] Optionally, the model accuracy calculation submodule includes:

[0131] An evaluation value acquisition unit, used to acquire a state evaluation value and an actual evaluation value of a trained BP neural network;

[0132] The accuracy calculation unit is used to calculate the mean square error between the state evaluation value and the actual evaluation value as the model accuracy of the trained BP neural network.

[0133] Optionally, the evaluation module 307 includes:

[0134] The acquisition submodule is used to obtain real-time operating status information of the equipment during operation;

[0135] The evaluation result acquisition submodule is used to input the real-time operation status information into the trained evaluation model to obtain the communication status evaluation result of the device.

[0136] Optionally, the evaluation module 307 further includes:

[0137] The information reading submodule is used to read the device's communication protocol, IP address parameters, line connection status, and environmental signal strength;

[0138] An information detection submodule, used to determine whether the communication infrastructure settings of the device are correct through preset communication standard setting information, the communication protocol, and the IP address parameters;

[0139] If so, the contents of the start condition verification submodule are executed;

[0140] A start-up condition verification submodule, used to determine whether a start-up condition is met, wherein the start-up condition includes that the line connection state is a connected state and the environmental signal strength is greater than a preset communication strength standard value;

[0141] The startup submodule is used to start the device when the startup conditions are met.

[0142] The power grid equipment communication status evaluation device provided in the embodiment of the present invention can execute the power grid equipment communication status evaluation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0143] Figure 4 A schematic diagram of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0144] like Figure 4As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0145] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0146] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as a method for evaluating the communication status of a power grid device.

[0147] In some embodiments, the method for evaluating the communication status of a power grid device may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the method for evaluating the communication status of a power grid device described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the method for evaluating the communication status of a power grid device by any other appropriate means (e.g., by means of firmware).

[0148] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0149] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0150] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0151] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0152] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0153] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0154] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0155] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the communication status of power grid equipment, characterized in that: include: Constructing an initial BP neural network and obtaining training samples, setting R stages, setting T iterations for each stage, and the training samples including historical operation status information; Use the training samples as particles in the population to initialize the particles in the population; When performing a single iteration in each stage, the fitness of each particle in the initial population is calculated according to the preset fitness function; Filter and update the particle optimal solution and the global optimal solution through the vertical and horizontal cross algorithm; When R phased traversals are completed, the final global optimal solution is used as the network parameters of the BP neural network; Performing model training on the BP neural network based on the training samples to obtain an evaluation model; The evaluation model is used to evaluate the communication status of power grid equipment.

2. The method for evaluating the communication status of power grid equipment according to claim 1, characterized in that: The method of screening and updating the particle optimal solution and the global optimal solution by horizontal crossover and vertical crossover includes: Perform horizontal crossover on the same dimension between two different particles, calculate the fitness of the particles before and after the crossover, and use the greedy algorithm to update the population; The different dimensions of the same particle are vertically crossed, the fitness of the particle before and after the crossover is calculated, and the population is updated using a greedy algorithm.

3. The method for evaluating the communication status of power grid equipment according to claim 1, characterized in that: After each phase is completed, it also includes: Calculate the maximum number of iterations based on the number of stages R and the number of iterations T; Get the dispersion of the population; Based on the degree of adaptation between the dispersion degree and the maximum number of iterations; The population size is adjusted based on the adaptation degree so that the dispersion degree is adapted to the maximum number of iterations.

4. The method for evaluating the communication status of power grid equipment according to claim 1, characterized in that: The step of training the BP neural network to obtain an evaluation model includes: Perform model training on the BP neural network to obtain the currently trained BP neural network; Calculate the model accuracy of the trained BP neural network; Determining whether the model accuracy meets the accuracy requirements; If so, output the BP neural network as the evaluation model; If not, retrain the model.

5. The method for evaluating the communication status of power grid equipment according to claim 4, characterized in that: The calculating the model accuracy of the trained BP neural network includes: Obtain the state evaluation value and actual evaluation value of the trained BP neural network; The mean square error between the state evaluation value and the actual evaluation value is calculated as the model accuracy of the trained BP neural network.

6. The method for evaluating the communication status of power grid equipment according to claim 1, characterized in that: The use of the evaluation model to evaluate the communication status of the power grid equipment includes: Get real-time running status information of the equipment during operation; The real-time operation status information is input into the trained evaluation model to obtain the communication status evaluation result of the device.

7. The method for evaluating the communication status of power grid equipment according to claim 6, characterized in that: Before acquiring the real-time running status information of the device during operation, the method further includes: Read the device's communication protocol, IP address parameters, line connection status and environmental signal strength; Determining whether the communication infrastructure settings of the device are correct through preset communication standard setting information, the communication protocol, and the IP address parameters; If so, determining whether a start condition is met, the start condition comprising that the line connection state is a connected state and the environmental signal strength is greater than a preset communication strength standard value; When the start condition is met, start the device.

8. A power grid equipment communication status evaluation device, characterized in that: include: An algorithm construction module is used to construct an initial BP neural network and obtain training samples, setting R stages, each stage setting T iterations, and the training samples include historical operation status information; An initialization module is used to use the training samples as particles in the population to initialize the particles in the population; The fitness calculation module is used to calculate the fitness of each particle in the initial population according to a preset fitness function during a single iteration in each stage; The optimization module is used to screen and update the particle optimal solution and the global optimal solution through the vertical and horizontal cross algorithm; The network parameter determination module is used to use the final global optimal solution as the network parameters of the BP neural network when the R phased traversals are completed; An evaluation model training module is used to perform model training on the BP neural network based on the training samples to obtain an evaluation model; The evaluation module is used to evaluate the communication status of the power grid equipment by using the evaluation model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for evaluating the communication status of power grid equipment according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for evaluating the communication status of power grid equipment according to any one of claims 1 to 7 when executed.

Images