Intelligent control method, system and medium of switch
By obtaining network traffic information and building a fault prediction model, using genetic algorithms and deep neural networks to dynamically adjust the switch work tasks and quantity, the problem of high switch energy consumption is solved, and more reasonable energy consumption management and green technology are achieved.
Patent Information
- Application Number
- CN202410829423.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-25
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-06-25
AI Technical Summary
The existing switches are still in operation in no use state, resulting in high energy consumption and are not in line with the concept of green.
By obtaining network traffic information in the target area, building a fault prediction model and network traffic characteristic data usage preference model, using genetic algorithms and deep neural networks to dynamically adjust the work tasks and quantity of the switch, optimize the working status of the switch, and reduce energy consumption.
The switch energy consumption is reduced, making the switch control more reasonable, avoiding unnecessary energy consumption and meeting the requirements of green technology.
Smart Images

Figure CN118473923B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of switches, and in particular to an intelligent control method, system and medium of a switch. Background Art
[0002] A switch is a network device used for forwarding electrical signals. It can provide an exclusive electrical signal path for any two network nodes connected to the switch. The most common switch is the Ethernet switch. Other common ones include telephone voice switches and fiber optic switches. The main functions of a switch include physical addressing, network topology, error checking, frame sequence, and flow control. At present, switches also have some new functions, such as support for VLAN (virtual local area network), support for link aggregation, and even some have firewall functions. Nowadays, switches are often used in clusters. The current switches are still in working state when they are not in use, resulting in high energy consumption during use, which is not in line with the concept of green. Summary of the invention
[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent control method, system and medium for a switch.
[0004] To achieve the above object, the technical solution adopted by the present invention is:
[0005] A first aspect of the present invention provides an intelligent control method for a switch, comprising the following steps:
[0006] Obtaining network traffic information of the target area within a preset time, initializing the configuration of the work task of the switch according to the network traffic information of the target area within the preset time, and obtaining initial work task information of the switch;
[0007] Obtain historical service data information of switches in the target area, build a switch fault prediction model based on the historical service data information of switches in the target area, and predict fault information of each switch through the switch fault prediction model;
[0008] Optimize the configuration of the initial work task information of the switch according to the fault information of the switch, obtain the final work task information of the switch, and predict the usage preference information of the network traffic feature data within the current preset time;
[0009] Based on the network traffic feature data within the current preset time, the preference information is used to optimize the switches in the target area.
[0010] Furthermore, in this method, the work task of the switch is initialized and configured according to the network traffic information of the target area within a preset time, and the initial work task information of the switch is obtained, which specifically includes:
[0011] Introduce a genetic algorithm, set the genetic algebra according to the genetic algorithm, obtain the network traffic capacity upper limit data of each switch in the target area through big data, initialize the working quantity information of the switch according to the network traffic information of the target area within a preset time, and randomly select the switch to perform the work task;
[0012] Calculate the total network traffic data according to the working quantity information of the switch and the network traffic capacity upper limit data of each switch in the target area, and determine whether the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area;
[0013] When the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area, the working quantity information of the switch is adjusted according to the genetic iteration of the genetic algebra until the total network traffic data is no greater than the network traffic capacity upper limit data of each switch in the target area;
[0014] When the total network traffic data is not greater than the network traffic capacity upper limit data of each switch in the target area, the work quantity information of the switch is output, and the initial work task information of the switch is generated according to the work quantity information of the switch and the switch implementing the work task.
[0015] Furthermore, in this method, historical service data information of switches in the target area is obtained, and a switch fault prediction model is constructed according to the historical service data information of switches in the target area. Fault information of each switch is predicted by the switch fault prediction model, specifically including:
[0016] Obtain historical service data information of switches in a target area, and divide the historical service data information of switches in the target area to obtain historical service data information whose fluctuation change characteristics are greater than a preset fluctuation change threshold, and remove the historical service data information whose fluctuation change characteristics are greater than the preset fluctuation change threshold;
[0017] Obtain the historical service data information after elimination, and build a switch fault prediction model based on a deep neural network, input the historical service data information after elimination into the switch fault prediction model for encoding learning, and obtain a trained switch fault prediction model;
[0018] Obtaining service data information of the switch within a preset time, and inputting the service data information of the switch within the preset time into the trained switch fault prediction model for prediction;
[0019] Through prediction, the predicted fault time node and the corresponding fault type of the switch are obtained, and the fault information of the switch is generated according to the predicted fault time node and the corresponding fault type of the switch, and the fault information of each switch is output.
[0020] Furthermore, in this method, the initial working task information of the switch is configured and optimized according to the fault information of the switch to obtain the final working task information of the switch, which specifically includes:
[0021] Obtain the predicted fault time node of each switch according to the fault information of the switch, obtain the switch that performs the work task according to the initial work task information of the switch, and obtain the estimated work time information of the switch that performs the work task;
[0022] Determine whether the predicted failure time node of the switch is within the estimated working time information of the switch performing the working task;
[0023] When the predicted failure time node of the switch is not within the estimated working time information of the switch that performs the working task, the initial working task information of the switch is output as the final working task information of the switch;
[0024] When the predicted failure time node of the switch is within the estimated working time information of the switch that implements the work task, the switch that implements the work task in the initial work task information of the switch is readjusted until the predicted failure time node of the switch is no longer within the estimated working time information of the switch that implements the work task.
[0025] Furthermore, in the present method, predicting the usage preference information of the network traffic characteristic data within the current preset time specifically includes:
[0026] Based on the LSTM neural network, a network traffic feature data usage preference prediction model is built, and timestamps are constructed to obtain network traffic feature data in each timestamp, and network traffic feature data based on time series is constructed in combination with timestamps;
[0027] Inputting the network traffic characteristic data based on the time series into the network traffic characteristic data usage preference prediction model for training, and obtaining the trained network traffic characteristic data usage preference prediction model;
[0028] The network traffic feature data usage preference information within the current preset time is predicted according to the trained network traffic feature data usage preference prediction model, and the network traffic feature data usage preference information within the current preset time is output.
[0029] Furthermore, in the present method, the switch in the target area is optimized and adjusted based on the network traffic characteristic data within the current preset time using the preference information, specifically including:
[0030] Obtain network traffic upper limit information of each switch in the target area and information about the number of switches, and obtain total network traffic upper limit information of switches in the target area based on the network traffic upper limit information of each switch in the target area and information about the number of switches;
[0031] Determine whether the network traffic characteristic data usage preference information within the current preset time is greater than the total upper limit information of the network traffic of the switch in the target area;
[0032] If it is greater than, calculate the difference between the network traffic characteristic data usage preference information within the current preset time and the total upper limit information of the network traffic of the switch in the target area, and determine whether the difference is greater than the preset difference value;
[0033] When the difference is greater than the preset difference value, the quantity information of the switches in the target area is expanded until the difference is greater than the preset difference value, the quantity information of the switches in the target area is output, and the switches in the target area are optimized and adjusted according to the quantity information of the switches in the target area.
[0034] A second aspect of the present invention provides an intelligent control system for a switch, the system comprising a memory and a processor, the memory comprising an intelligent control method program for the switch, and when the intelligent control method program for the switch is executed by the processor, the following steps are implemented:
[0035] Obtaining network traffic information of the target area within a preset time, initializing the configuration of the work task of the switch according to the network traffic information of the target area within the preset time, and obtaining initial work task information of the switch;
[0036] Obtain historical service data information of switches in the target area, build a switch fault prediction model based on the historical service data information of switches in the target area, and predict fault information of each switch through the switch fault prediction model;
[0037] Optimize the configuration of the initial work task information of the switch according to the fault information of the switch, obtain the final work task information of the switch, and predict the usage preference information of the network traffic feature data within the current preset time;
[0038] Based on the network traffic feature data within the current preset time, the preference information is used to optimize the switches in the target area.
[0039] A third aspect of the present invention provides a computer-readable storage medium, which includes a switch intelligent control method program. When the switch intelligent control method program is executed by a processor, any step of the switch intelligent control method is implemented.
[0040] The present invention solves the defects existing in the background technology and has the following beneficial effects:
[0041] The present invention obtains network traffic information of the target area within a preset time, initializes the configuration of the work task of the switch according to the network traffic information of the target area within the preset time, obtains the initial work task information of the switch, and then obtains the historical service data information of the switch in the target area, and builds a switch fault prediction model according to the historical service data information of the switch in the target area, predicts the fault information of each switch through the switch fault prediction model, and optimizes the configuration of the initial work task information of the switch according to the fault information of the switch, obtains the final work task information of the switch, and predicts the use preference information of the network traffic feature data within the current preset time, and finally optimizes and adjusts the switch in the target area based on the use preference information of the network traffic feature data within the current preset time. The present invention fully considers the real-time network traffic data in the target area, and thus dynamically adjusts the work task of the switch in the target area through a genetic algorithm, which can reduce the energy consumption of the switch during use, thereby making the control of the switch more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.
[0043] Figure 1 The overall method flow chart of the intelligent control method of the switch is shown;
[0044] Figure 2 A first method flow chart of the intelligent control method of a switch is shown;
[0045] Figure 3 A second method flow chart of the intelligent control method of a switch is shown;
[0046] Figure 4 A system block diagram of an intelligent control system of a switch is shown. DETAILED DESCRIPTION
[0047] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.
[0049] like Figure 1 As shown, the first aspect of the present invention provides an intelligent control method for a switch, comprising the following steps:
[0050] S102: Obtain network traffic information of the target area within a preset time, initialize and configure the work task of the switch according to the network traffic information of the target area within the preset time, and obtain initial work task information of the switch;
[0051] S104: Obtain historical service data information of switches in the target area, and build a switch fault prediction model based on the historical service data information of switches in the target area, and predict fault information of each switch through the switch fault prediction model;
[0052] S106: Optimize the configuration of the initial working task information of the switch according to the fault information of the switch, obtain the final working task information of the switch, and predict the usage preference information of the network traffic feature data within the current preset time;
[0053] S108: Optimize and adjust the switches in the target area based on the network traffic feature data within the current preset time using the preference information.
[0054] It should be noted that the present invention fully considers the real-time network traffic data in the target area, so as to dynamically adjust the work tasks of the switch in the target area through the genetic algorithm, which can reduce the energy consumption of the switch during use, thereby making the control of the switch more reasonable. Among them, the network traffic information can be obtained by the switch uploading the network traffic data at the current timestamp.
[0055] like Figure 2 As shown, further, in this method, the work task of the switch is initialized and configured according to the network traffic information of the target area within a preset time, and the initial work task information of the switch is obtained, which specifically includes:
[0056] S202: Introduce a genetic algorithm, set a genetic algebra according to the genetic algorithm, obtain the network traffic capacity upper limit data of each switch in the target area through big data, initialize the working quantity information of the switch according to the network traffic information of the target area within a preset time, and randomly select the switch to perform the working task;
[0057] S204: Calculate the total network traffic data according to the working number information of the switch and the network traffic capacity upper limit data of each switch in the target area, and determine whether the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area;
[0058] S206: When the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area, the working quantity information of the switch is adjusted according to the genetic iteration of the genetic algebra until the total network traffic data is no greater than the network traffic capacity upper limit data of each switch in the target area;
[0059] S208: When the total network traffic data is not greater than the network traffic capacity upper limit data of each switch in the target area, output the working quantity information of the switch, and generate the initial working task information of the switch according to the working quantity information of the switch and the switch executing the working task.
[0060] It should be noted that since the switch has multiple ports, each port of the switch is used to connect an independent network segment, but sometimes in order to provide faster access speed, we can directly connect some important network computers to the switch port. In this way, the key servers and important users of the network have faster access speeds and support larger information flow. The network flow capacity upper limit data of each switch is calculated by the number of ports and the maximum flow upper limit of each port, so as to calculate the total network flow data, and then the initial work task information of the switch is adaptively adjusted through the genetic algorithm, so as to adjust the working state of the switch, such as switching from the working state to the sleep state, so as to achieve the effect of reducing energy consumption.
[0061] like Figure 3 As shown, further, in this method, historical service data information of switches in the target area is obtained, and a switch fault prediction model is constructed according to the historical service data information of switches in the target area, and the fault information of each switch is predicted by the switch fault prediction model, specifically including:
[0062] S302: Obtain historical service data information of switches in the target area, and divide the historical service data information of switches in the target area to obtain historical service data information whose fluctuation change characteristics are greater than a preset fluctuation change threshold, and remove the historical service data information whose fluctuation change characteristics are greater than the preset fluctuation change threshold;
[0063] S304: Obtain the historical service data information after elimination, and build a switch fault prediction model based on a deep neural network, input the historical service data information after elimination into the switch fault prediction model for encoding learning, and obtain a trained switch fault prediction model;
[0064] S306: Obtain service data information of the switch within a preset time, and input the service data information of the switch within the preset time into the trained switch fault prediction model for prediction;
[0065] S308: Obtain the predicted fault time node and the corresponding fault type of the switch through prediction, generate the fault information of the switch according to the predicted fault time node and the corresponding fault type of the switch, and output the fault information of each switch.
[0066] It should be noted that the method can predict the fault information of the switch, so as to dynamically adjust the number of switches that perform work tasks according to the fault information, avoid high network delays caused by switch failures during use, and make the work distribution of the switch more reasonable. Among them, the historical service data information with fluctuation change characteristics greater than the preset fluctuation change threshold, such as equipment that fails occasionally, and service data with huge fluctuations from a non-fault state to a fault state, can be eliminated to improve the accuracy of fault prediction.
[0067] Furthermore, in this method, the initial working task information of the switch is configured and optimized according to the fault information of the switch to obtain the final working task information of the switch, which specifically includes:
[0068] Obtain the predicted fault time node of each switch according to the fault information of the switch, obtain the switch that performs the work task according to the initial work task information of the switch, and obtain the estimated work time information of the switch that performs the work task;
[0069] Determine whether the predicted failure time node of the switch is within the estimated working time information of the switch performing the working task;
[0070] When the predicted failure time node of the switch is not within the estimated working time information of the switch that performs the working task, the initial working task information of the switch is output as the final working task information of the switch;
[0071] When the predicted failure time node of the switch is within the estimated working time information of the switch that implements the work task, the switch that implements the work task in the initial work task information of the switch is readjusted until the predicted failure time node of the switch is no longer within the estimated working time information of the switch that implements the work task.
[0072] It should be noted that, during the implementation process, the estimated working time information of the switch that implements the work task can be obtained by obtaining the user's historical usage habits, the scheduled working time of the switch, etc. When the predicted failure time node of the switch is within the estimated working time information of the switch that implements the work task, the switch that implements the work task in the initial work task information of the switch is readjusted to make the switch work more reasonably.
[0073] Furthermore, in the present method, predicting the usage preference information of the network traffic characteristic data within the current preset time specifically includes:
[0074] Based on the LSTM neural network, a network traffic feature data usage preference prediction model is built, and timestamps are constructed to obtain network traffic feature data in each timestamp, and network traffic feature data based on time series is constructed in combination with timestamps;
[0075] Inputting the network traffic characteristic data based on the time series into the network traffic characteristic data usage preference prediction model for training, and obtaining the trained network traffic characteristic data usage preference prediction model;
[0076] The network traffic feature data usage preference information within the current preset time is predicted according to the trained network traffic feature data usage preference prediction model, and the network traffic feature data usage preference information within the current preset time is output.
[0077] It should be noted that due to the possible increase or decrease in network users in the target area, the LSTM neural network is a long short-term memory neural network, which uses the long short-term memory neural network to analyze the user's network traffic feature data within a predetermined time to predict the network traffic feature data usage preference information within the current preset time.
[0078] Furthermore, in the present method, the switch in the target area is optimized and adjusted based on the network traffic characteristic data within the current preset time using the preference information, specifically including:
[0079] Obtain network traffic upper limit information of each switch in the target area and information about the number of switches, and obtain total network traffic upper limit information of switches in the target area based on the network traffic upper limit information of each switch in the target area and information about the number of switches;
[0080] Determine whether the network traffic characteristic data usage preference information within the current preset time is greater than the total upper limit information of the network traffic of the switch in the target area;
[0081] If it is greater than, calculate the difference between the network traffic characteristic data usage preference information within the current preset time and the total upper limit information of the network traffic of the switch in the target area, and determine whether the difference is greater than the preset difference value;
[0082] When the difference is greater than the preset difference value, the quantity information of the switches in the target area is expanded until the difference is greater than the preset difference value, the quantity information of the switches in the target area is output, and the switches in the target area are optimized and adjusted according to the quantity information of the switches in the target area.
[0083] It should be noted that this method can optimize and adjust the actual number of switches in service in the target area according to the preference information of the network traffic feature data within the current preset time, thereby realizing dynamic adjustment of the switches in the target area, avoiding waste of resources or improving the user's network experience, and making the control of the switches in the target area more reasonable.
[0084] In addition, the method may further comprise the following steps:
[0085] The network traffic upper limit feature data of the switch during service is obtained through big data, and a network traffic upper limit feature prediction model is constructed based on a deep neural network, and the network traffic upper limit feature data of the switch during service is input into the network traffic upper limit feature prediction model for training;
[0086] Through training, a trained network traffic upper limit feature prediction model is obtained, and network traffic upper limit feature data of the switch within a preset time is obtained, and the network traffic upper limit feature data of the switch within the preset time is input into the trained network traffic upper limit feature prediction model for prediction;
[0087] Obtain network upper limit characteristic data of the switch in the current timestamp through prediction, and based on the network upper limit characteristic data of each switch in the current timestamp;
[0088] The network traffic capacity upper limit data of each switch is updated according to the network upper limit characteristic data of each switch in the current timestamp, and the initial working task information of the switch is adjusted.
[0089] It should be noted that due to the performance degradation of the device, the network upper limit characteristic data of the switch will change to a certain extent. This method can further improve the rationality of the switch configuration.
[0090] In addition, the method may further comprise the following steps:
[0091] Obtain information transmission performance characteristic data of the switch under each working environment factor, and introduce a graph neural network, using the working environment factor as the first graph node of the graph neural network and the information transmission performance characteristic as the second graph node of the graph neural network;
[0092] Constructing a knowledge graph, constructing a topological structure graph according to the first graph node and the second graph node, obtaining a related adjacency matrix based on the topological structure graph, and inputting the related adjacency matrix into the knowledge graph for storage;
[0093] Obtaining working environment factor information of the current switch, inputting the working environment factor information of the current switch into the knowledge graph for data matching, and obtaining information transmission performance characteristic data under the working environment factor of the current switch;
[0094] The network upper limit characteristic data of the switch in the current timestamp is updated according to the information transmission performance characteristic data under the working environment factors of the current switch, and the initial working task information of the switch is adjusted according to the updated network upper limit characteristic data of the switch.
[0095] It should be noted that the working environment factor is mainly temperature. The higher the working temperature of the switch, the more it will affect the working performance and information transmission performance of the switch. For example, it will affect the operating response speed of the switch and the transmission speed of information, which will greatly reduce the information transmission performance, thereby affecting the network upper limit feature data of the switch in the current timestamp. This method can further improve the control rationality of the switch in the target area.
[0096] like Figure 4 As shown, the second aspect of the present invention provides an intelligent control system 4 of a switch, the system 4 includes a memory 41 and a processor 42, the memory 41 includes an intelligent control method program of the switch, and when the intelligent control method program of the switch is executed by the processor 42, the following steps are implemented:
[0097] Obtaining network traffic information of the target area within a preset time, initializing the configuration of the work task of the switch according to the network traffic information of the target area within the preset time, and obtaining initial work task information of the switch;
[0098] Obtain historical service data information of switches in the target area, build a switch fault prediction model based on the historical service data information of switches in the target area, and predict fault information of each switch through the switch fault prediction model;
[0099] Optimize the configuration of the initial work task information of the switch according to the fault information of the switch, obtain the final work task information of the switch, and predict the usage preference information of the network traffic feature data within the current preset time;
[0100] Based on the network traffic feature data within the current preset time, the preference information is used to optimize the switches in the target area.
[0101] Furthermore, in the present system, the work task of the switch is initialized and configured according to the network traffic information of the target area within the preset time, and the initial work task information of the switch is obtained, which specifically includes:
[0102] Introduce a genetic algorithm, set the genetic algebra according to the genetic algorithm, obtain the network traffic capacity upper limit data of each switch in the target area through big data, initialize the working quantity information of the switch according to the network traffic information of the target area within a preset time, and randomly select the switch to perform the work task;
[0103] Calculate the total network traffic data according to the working quantity information of the switch and the network traffic capacity upper limit data of each switch in the target area, and determine whether the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area;
[0104] When the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area, the working quantity information of the switch is adjusted according to the genetic iteration of the genetic algebra until the total network traffic data is no greater than the network traffic capacity upper limit data of each switch in the target area;
[0105] When the total network traffic data is not greater than the network traffic capacity upper limit data of each switch in the target area, the work quantity information of the switch is output, and the initial work task information of the switch is generated according to the work quantity information of the switch and the switch implementing the work task.
[0106] Furthermore, in the present system, historical service data information of switches in the target area is obtained, and a switch fault prediction model is constructed according to the historical service data information of switches in the target area. The fault information of each switch is predicted by the switch fault prediction model, specifically including:
[0107] Obtain historical service data information of switches in a target area, and divide the historical service data information of switches in the target area to obtain historical service data information whose fluctuation change characteristics are greater than a preset fluctuation change threshold, and remove the historical service data information whose fluctuation change characteristics are greater than the preset fluctuation change threshold;
[0108] Obtain the historical service data information after elimination, and build a switch fault prediction model based on a deep neural network, input the historical service data information after elimination into the switch fault prediction model for encoding learning, and obtain a trained switch fault prediction model;
[0109] Obtaining service data information of the switch within a preset time, and inputting the service data information of the switch within the preset time into the trained switch fault prediction model for prediction;
[0110] Through prediction, the predicted fault time node and the corresponding fault type of the switch are obtained, and the fault information of the switch is generated according to the predicted fault time node and the corresponding fault type of the switch, and the fault information of each switch is output.
[0111] Furthermore, in the present system, the initial working task information of the switch is configured and optimized according to the fault information of the switch to obtain the final working task information of the switch, which specifically includes:
[0112] Obtain the predicted fault time node of each switch according to the fault information of the switch, obtain the switch that performs the work task according to the initial work task information of the switch, and obtain the estimated work time information of the switch that performs the work task;
[0113] Determine whether the predicted failure time node of the switch is within the estimated working time information of the switch performing the working task;
[0114] When the predicted failure time node of the switch is not within the estimated working time information of the switch that performs the working task, the initial working task information of the switch is output as the final working task information of the switch;
[0115] When the predicted failure time node of the switch is within the estimated working time information of the switch that implements the work task, the switch that implements the work task in the initial work task information of the switch is readjusted until the predicted failure time node of the switch is no longer within the estimated working time information of the switch that implements the work task.
[0116] Furthermore, in this system, the network traffic characteristic data usage preference information predicted within the current preset time specifically includes:
[0117] Based on the LSTM neural network, a network traffic feature data usage preference prediction model is built, and timestamps are constructed to obtain network traffic feature data in each timestamp, and network traffic feature data based on time series is constructed in combination with timestamps;
[0118] Inputting the network traffic characteristic data based on the time series into the network traffic characteristic data usage preference prediction model for training, and obtaining the trained network traffic characteristic data usage preference prediction model;
[0119] The network traffic feature data usage preference information within the current preset time is predicted according to the trained network traffic feature data usage preference prediction model, and the network traffic feature data usage preference information within the current preset time is output.
[0120] Furthermore, in the present system, the switch in the target area is optimized and adjusted based on the network traffic characteristic data within the current preset time using the preference information, specifically including:
[0121] Obtain network traffic upper limit information of each switch in the target area and information about the number of switches, and obtain total network traffic upper limit information of switches in the target area based on the network traffic upper limit information of each switch in the target area and information about the number of switches;
[0122] Determine whether the network traffic characteristic data usage preference information within the current preset time is greater than the total upper limit information of the network traffic of the switch in the target area;
[0123] If it is greater than, calculate the difference between the network traffic characteristic data usage preference information within the current preset time and the total upper limit information of the network traffic of the switch in the target area, and determine whether the difference is greater than the preset difference value;
[0124] When the difference is greater than the preset difference value, the quantity information of the switches in the target area is expanded until the difference is greater than the preset difference value, the quantity information of the switches in the target area is output, and the switches in the target area are optimized and adjusted according to the quantity information of the switches in the target area.
[0125] A third aspect of the present invention provides a computer-readable storage medium, which includes a switch intelligent control method program. When the switch intelligent control method program is executed by a processor, any step of the switch intelligent control method is implemented.
[0126] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0127] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0128] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0129] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.
[0130] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
[0131] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. An intelligent control method for a switch, characterized in that: The following steps are involved: Acquire network traffic information of the target area within a preset time, initialize and configure the work task of the switch according to the network traffic information of the target area within the preset time, and acquire initial work task information of the switch; Acquire historical service data information of switches in a target area, build a switch fault prediction model based on the historical service data information of switches in the target area, and predict fault information of each switch through the switch fault prediction model; Optimizing the configuration of the initial working task information of the switch according to the fault information of the switch, obtaining the final working task information of the switch, and predicting the usage preference information of the network traffic feature data within the current preset time; Optimizing and adjusting the switches in the target area based on the network traffic characteristic data within the current preset time using the preference information; Initializing the configuration of the work task of the switch according to the network traffic information of the target area within a preset time, and obtaining the initial work task information of the switch, specifically including: Introducing a genetic algorithm, setting a genetic algebra according to the genetic algorithm, obtaining the network traffic capacity upper limit data of each switch in the target area through big data, initializing the working quantity information of the switch according to the network traffic information of the target area within a preset time, and randomly selecting the switch to perform the working task; Calculate the total network traffic data according to the working quantity information of the switch and the network traffic capacity upper limit data of each switch in the target area, and determine whether the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area; When the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area, adjusting the working quantity information of the switch according to the genetic algebra pair genetic iteration until the total network traffic data is no greater than the network traffic capacity upper limit data of each switch in the target area; When the total network traffic data is not greater than the network traffic capacity upper limit data of each switch in the target area, outputting the work quantity information of the switch, and generating the initial work task information of the switch according to the work quantity information of the switch and the switch implementing the work task; Optimizing the configuration of the initial working task information of the switch according to the fault information of the switch to obtain the final working task information of the switch, specifically including: Obtaining a predicted fault time node of each switch according to the fault information of the switch, and obtaining a switch that performs a work task according to the initial work task information of the switch, and obtaining estimated work time information of the switch that performs the work task; Determine whether the predicted failure time node of the switch is within the estimated working time information of the switch performing the working task; When the predicted failure time node of the switch is not within the estimated working time information of the switch that performs the working task, the initial working task information of the switch is output as the final working task information of the switch; When the predicted failure time node of the switch is within the estimated working time information of the switch that performs the work task, the switch that performs the work task in the initial work task information of the switch is readjusted until the predicted failure time node of the switch is no longer within the estimated working time information of the switch that performs the work task; The switch in the target area is optimized and adjusted based on the network traffic characteristic data within the current preset time using the preference information, specifically including: Obtain network traffic upper limit information of each switch in the target area and information about the number of switches, and obtain total network traffic upper limit information of switches in the target area based on the network traffic upper limit information of each switch in the target area and information about the number of switches; Determine whether the network traffic characteristic data usage preference information within the current preset time is greater than the total upper limit information of the network traffic of the switch in the target area; If it is greater than, calculate the difference between the network traffic characteristic data usage preference information within the current preset time and the total upper limit information of the network traffic of the switches in the target area, and determine whether the difference is greater than the preset difference value; When the difference is greater than a preset difference value, the quantity information of the switches in the target area is expanded until the difference is greater than the preset difference value, the quantity information of the switches in the target area is output, and the switches in the target area are optimized and adjusted according to the quantity information of the switches in the target area.
2. The intelligent control method of a switch according to claim 1, characterized in that: Acquiring historical service data information of switches in a target area, and building a switch fault prediction model according to the historical service data information of switches in the target area, and predicting fault information of each switch by using the switch fault prediction model, specifically including: Acquire historical service data information of switches in a target area, and divide the historical service data information of switches in the target area to obtain historical service data information whose fluctuation change characteristics are greater than a preset fluctuation change threshold, and remove the historical service data information whose fluctuation change characteristics are greater than the preset fluctuation change threshold; Obtaining the historical service data information after elimination, and building a switch fault prediction model based on a deep neural network, inputting the historical service data information after elimination into the switch fault prediction model for coding learning, and obtaining a trained switch fault prediction model; Acquire service data information of the switch within a preset time, and input the service data information of the switch within the preset time into the trained switch fault prediction model for prediction; Through prediction, the predicted fault time node and the corresponding fault type of the switch are obtained, and the fault information of the switch is generated according to the predicted fault time node and the corresponding fault type of the switch, and the fault information of each switch is output.
3. The intelligent control method of a switch according to claim 1, characterized in that: Predict the usage preference information of network traffic feature data within the current preset time, including: A network traffic feature data usage preference prediction model is constructed based on the LSTM neural network, and a timestamp is constructed to obtain the network traffic feature data in each timestamp, and the network traffic feature data based on the time series is constructed in combination with the timestamp; Inputting the network traffic characteristic data based on the time series into the network traffic characteristic data usage preference prediction model for training, and obtaining the trained network traffic characteristic data usage preference prediction model; The network traffic feature data usage preference information within a current preset time is predicted according to the trained network traffic feature data usage preference prediction model, and the network traffic feature data usage preference information within the current preset time is output.
4. An intelligent control system for a switch, characterized in that: The system includes a memory and a processor, wherein the memory includes a switch intelligent control method program, and when the switch intelligent control method program is executed by the processor, the following steps are implemented: Acquire network traffic information of the target area within a preset time, initialize and configure the work task of the switch according to the network traffic information of the target area within the preset time, and acquire initial work task information of the switch; Acquire historical service data information of switches in a target area, build a switch fault prediction model based on the historical service data information of switches in the target area, and predict fault information of each switch through the switch fault prediction model; Optimizing the configuration of the initial working task information of the switch according to the fault information of the switch, obtaining the final working task information of the switch, and predicting the usage preference information of the network traffic feature data within the current preset time; Optimizing and adjusting the switches in the target area based on the network traffic characteristic data within the current preset time using the preference information; Initializing the configuration of the work task of the switch according to the network traffic information of the target area within a preset time, and obtaining the initial work task information of the switch, specifically including: Introducing a genetic algorithm, setting a genetic algebra according to the genetic algorithm, obtaining the network traffic capacity upper limit data of each switch in the target area through big data, initializing the working quantity information of the switch according to the network traffic information of the target area within a preset time, and randomly selecting the switch to perform the working task; Calculate the total network traffic data according to the working quantity information of the switch and the network traffic capacity upper limit data of each switch in the target area, and determine whether the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area; When the total network traffic data is greater than the network traffic capacity upper limit data of each switch in the target area, adjusting the working quantity information of the switch according to the genetic algebra pair genetic iteration until the total network traffic data is no greater than the network traffic capacity upper limit data of each switch in the target area; When the total network traffic data is not greater than the network traffic capacity upper limit data of each switch in the target area, outputting the work quantity information of the switch, and generating the initial work task information of the switch according to the work quantity information of the switch and the switch implementing the work task; Optimizing the configuration of the initial working task information of the switch according to the fault information of the switch to obtain the final working task information of the switch, specifically including: Obtaining a predicted fault time node of each switch according to the fault information of the switch, and obtaining a switch that performs a work task according to the initial work task information of the switch, and obtaining estimated work time information of the switch that performs the work task; Determine whether the predicted failure time node of the switch is within the estimated working time information of the switch performing the working task; When the predicted failure time node of the switch is not within the estimated working time information of the switch that performs the working task, the initial working task information of the switch is output as the final working task information of the switch; When the predicted failure time node of the switch is within the estimated working time information of the switch that performs the work task, the switch that performs the work task in the initial work task information of the switch is readjusted until the predicted failure time node of the switch is no longer within the estimated working time information of the switch that performs the work task; The switch in the target area is optimized and adjusted based on the network traffic characteristic data within the current preset time using the preference information, specifically including: Obtain network traffic upper limit information of each switch in the target area and information about the number of switches, and obtain total network traffic upper limit information of switches in the target area based on the network traffic upper limit information of each switch in the target area and information about the number of switches; Determine whether the network traffic characteristic data usage preference information within the current preset time is greater than the total upper limit information of the network traffic of the switch in the target area; If it is greater than, calculate the difference between the network traffic characteristic data usage preference information within the current preset time and the total upper limit information of the network traffic of the switches in the target area, and determine whether the difference is greater than the preset difference value; When the difference is greater than a preset difference value, the quantity information of the switches in the target area is expanded until the difference is greater than the preset difference value, the quantity information of the switches in the target area is output, and the switches in the target area are optimized and adjusted according to the quantity information of the switches in the target area.
5. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a switch intelligent control method program, and when the switch intelligent control method program is executed by a processor, the steps of the switch intelligent control method according to any one of claims 1 to 3 are implemented.
