Multi-network sharing management method
By integrating network resources, data acquisition and time series model prediction, data accuracy and flexibility problems in multi-network sharing management are solved, network performance and service quality are optimized, load balancing and intelligent routing are achieved.
Patent Information
- Application Number
- CN202410035020.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-10
- Publication Date
- 2025-07-11
AI Technical Summary
Traditional multi-network sharing management methods cannot accurately judge the accuracy of network data, resulting in uncertainty and errors in management decision making, lack of flexibility, unable to quickly adapt to changing network environments and needs, and there are incompatible problems, resulting in insufficient performance of network equipment and management software, resulting in network delays and failures.
By integrating network resource types, setting data collection points, collecting original network data and performing minimum-maximum normalization, using time series models to predict network data indicators, and dynamic scheduling management is performed in combination with visual interfaces to optimize the utilization of network resources.
It realizes optimization of network performance, improves the overall performance and service quality of network equipment, reduces network latency and transmission delay, improves data transmission efficiency and speed, and realizes load balancing and intelligent routing across network resources.
Smart Images
Figure CN120301832A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of computer networks. More specifically, the present invention relates to a multi-network sharing management method. Background Art
[0002] Multi-network sharing refers to the sharing of resources and information among multiple network devices. With the development of multi-networks, network management in a multi-network environment has become more complex. Through multi-network sharing management, it is possible to better manage the multi-network environment and improve the accuracy of network data.
[0003] Traditional multi-network sharing management methods cannot accurately judge the accuracy of network data, resulting in uncertainty and errors in management decisions, lacking flexibility, being unable to quickly adapt to changing network environments and requirements, and having incompatibility problems, leading to poor effects of multi-network sharing management, insufficient performance of network devices and management software, resulting in network latency and failures. Summary of the Invention
[0004] In view of the technical problems existing in the prior art, the present invention provides a multi-network sharing management method. By integrating network resource types, network time-series data is obtained and a time series model is constructed to predict network data metrics, and network data scheduling is performed using the predicted high and low peak periods to solve the problems raised in the above background art.
[0005] The technical solution for the present invention to solve the above technical problems is as follows: A multi-network sharing management method includes the following steps: S101: Integrate network resource types, select device network node positions in multiple networks to set data collection points, and store the collected original network data in a database using a wireless transmission method; S102: Check whether there are errors and inconsistent information in the original network data, reduce the original network data to a specified range using min-max normalization, and map it to the same scale. Transmit the processed network data to the database using a wireless transmission method; S103: Call the network data in the database, combine it with a timer to form network time-series data, obtain the central tendency, dispersion degree, and distribution form of the network time-series data using statistical features, and predict network data metrics through a time series model; S104: Obtain high and low peak period network data metrics according to the results of the time series model, and perform multi-network scheduling management using a visualization interface and dynamic selection.
[0006] In a preferred embodiment, in S101, the network resource types are integrated, including servers, storage devices, network devices, virtual machines, and containers. The device network node locations are selected in multiple networks to set data collection points, and traffic monitors are installed at the data collection points to collect raw network data in real time through port mirroring of network resources. The raw network data metrics and the raw network data collection frequency are configured in the traffic monitors. The raw network data metrics include network traffic to represent the network load condition and traffic distribution, bandwidth utilization to monitor the usage of network bandwidth, and latency including network latency and transmission latency to evaluate network performance and response speed. The raw network data collection frequency is selected as high speed to collect subtle network changes, and the collected raw network data is stored in a database using a wireless transmission method.
[0007] In a preferred embodiment, in S102, it is checked whether there are errors and inconsistent information in the raw network data, and preparatory data items are prepared. When there are errors and inconsistent information in the raw network data, the missing values are filled using the preparatory data items, and the raw network data is scaled down to a specified range and mapped to the same scale using min-max normalization. The min-max normalization formula is:
[0008] where represents the normalized network data, represents the network data, represents the minimum value of the raw network data, represents the maximum value of the raw network data. The processed network data is transmitted to the database using a wireless transmission method.
[0009] In a preferred embodiment, in S103, the network data in the database is called, and network time-series data is formed by combining a timer. The central tendency, dispersion degree, and distribution form of the network time-series data are obtained using statistical features. The central tendency is represented by the mean of the network time-series data, and its specific formula is:
[0010] where represents the mean of the network time-series data, represents the i-th normalized network time-series data, represents the number of network time-series data. The dispersion degree is represented by the variance of the network time-series data, and its specific formula is:
[0011]
[0012] where represents the variance of the network time-series data, Denote the mean of network timing data, Denote the i-th normalized network timing data, Denote the number of network timing data. The distribution pattern is represented by the percentile of network timing data. Sort the time series data by percentile, and select the first network timing data as the initial value of the time series model. The time series model selects the recursive least squares method, and its specific formula is:
[0013]
[0014] Where Denote the network timing data at the t-th time point, Denote the intercept term of the model, which represents the network timing data when the independent variable is 0, Denote the influence degree of the initial value of the time series model on the network timing data at the t-th time point, Denote the influence degree of the initial value of the time series model at the previous moment on the network timing data at the t-th time point, Denote the initial value of the time series model, Denote the network timing data at the (t - 1)-th time point. Predict the network data metrics through the network timing data at the t-th time point.
[0015] In a preferred embodiment, in S104, obtain the network data metrics during the peak period according to the results of the time series model. During the peak period, the network controller dynamically adjusts the weight of bandwidth allocation according to the priority and importance of the application, and uses the column chart of the visualization interface to display the load situation and traffic distribution of the network during the peak period. Dynamically select the optimal path and set a cache at the device network node location to reduce network latency and transmission latency. Obtain the network data metrics during the off-peak period according to the results of the time series model. During the off-peak period, perform dynamic load balancing according to the real-time traffic situation and network topology, and manage the connection pool by monitoring different device network nodes and links to reduce the number of handshakes and confirmations during the communication process. Use the column chart of the visualization interface to display the load situation and traffic distribution of the network during the off-peak period.
[0016] The beneficial effects of the present invention are as follows: By analyzing the network load conditions, traffic distribution, bandwidth utilization, network latency, and transmission latency of multiple network resources, and automatically adjusting resource allocation based on real-time data and prediction models, each network resource can be utilized optimally, improving the overall network performance and service quality. Load balancing across multiple network resources is achieved by monitoring and analyzing the load conditions of different network resources, guiding traffic to idle and less-loaded resources to avoid overloading a single resource and affecting network performance. Intelligent routing and path selection are realized by analyzing the network topology, transmission performance, and real-time traffic conditions, reducing network latency and transmission latency, and improving the efficiency and speed of data transmission. By checking whether there are errors and inconsistent information in network data, using min-max normalization to scale it down to a specified range and map it to the same scale, it is easier to detect outliers, errors, and inconsistent information in the data. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0018] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of protection of the present application.
[0019] In the description of the present application, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more, unless otherwise specifically defined.
[0020] In the description of the present application, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present application is not necessarily construed as being more preferred or having more advantages than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present application.
[0021] This embodiment provides a multi-network sharing management method as shown in Figure 1 the following, which specifically includes the following steps: S101: Integrate network resource types, select the device network node locations in multiple networks to set data collection points, and store the collected original network data in a database using a wireless transmission method; Further, integrating network resource types includes servers, storage devices, network devices, virtual machines, and containers. Select the device network node locations in multiple networks to set data collection points, and install traffic monitors at the data collection points to collect original network data in real time through port mirroring of network resources. Configure the original network data metrics and the original network data collection frequency in the traffic monitors. The original network data metrics include network traffic to represent the network load situation and traffic distribution, bandwidth utilization to monitor the usage of network bandwidth, and latency including network latency and transmission latency to evaluate network performance and response speed. The original network data collection frequency is selected as high speed to collect network subtle changes, and the collected original network data is stored in a database using a wireless transmission method.
[0022] S102: Check whether there are errors and inconsistent information in the original network data, reduce the original network data to a specified range using min-max normalization, and map it to the same scale. Transmit the processed network data to the database using a wireless transmission method; Further, check whether there are errors and inconsistent information in the original network data, and prepare preliminary data items. When there are errors and inconsistent information in the original network data, fill in the missing values using the preliminary data items. Reduce the original network data to a specified range using min-max normalization, and map it to the same scale. The min-max normalization formula is:
[0023] where represents the normalized network data, represents the network data, represents the minimum value of the original network data, represents the maximum value of the original network data. Transmit the processed network data to the database using a wireless transmission method.
[0024] S103: Call the network data in the database, combine it with a timer to form network time-series data, obtain the central tendency, dispersion degree, and distribution form of the network time-series data using statistical features, and predict network data metrics through a time-series model; Further, call the network data in the database and combine it with a timer to form network timing data. Use statistical features to obtain the central tendency, dispersion degree, and distribution form of the network timing data. The central tendency is represented by the mean of the network timing data, and its specific formula is:
[0025] Where represents the mean of the network timing data, represents the i-th normalized network timing data, represents the number of network timing data. The dispersion degree is represented by the variance of the network timing data, and its specific formula is:
[0026]
[0027] Where represents the variance of the network timing data, represents the mean of the network timing data, represents the i-th normalized network timing data, represents the number of network timing data. The distribution form is represented by the percentile of the network timing data. Sort the time series data by percentile size and select the first network timing data as the initial value of the time series model. The time series model selects the recursive least squares method, and its specific formula is:
[0028]
[0029] Where represents the network timing data at the t-th time point, represents the intercept term of the model, which represents the network timing data when the independent variable is 0, represents the influence degree of the initial value of the time series model on the network timing data at the t-th time point, represents the influence degree of the initial value of the time series model at the previous moment on the network timing data at the t-th time point, represents the initial value of the time series model, represents the network timing data at the (t - 1)-th time point. Predict the network data index through the network timing data at the t-th time point.
[0030] S104: Obtain the network data indicators during high and low peak periods according to the results of the time series model, and use the visualization interface and dynamic selection for multi-network scheduling management; Furthermore, obtain peak period network data metrics according to the time series model results. During the peak period, the network controller dynamically adjusts the weight of bandwidth allocation according to the priority and importance of the application, and uses the column chart of the visualization interface to display the load condition and traffic distribution of the network during the peak period. Dynamically select the optimal path and set caches at the positions of device network nodes to reduce network latency and transmission latency. Obtain off-peak period network data metrics according to the time series model results. During the off-peak period, perform load balancing dynamically according to the real-time traffic condition and network topology, and manage the connection pool by monitoring different device network nodes and links to reduce the number of handshakes and acknowledgments during communication. Use the column chart of the visualization interface to display the load condition and traffic distribution of the network during the off-peak period.
[0031] It should be noted that in the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0032] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.
[0033] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded computers, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0034] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.
[0035] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the steps of the function specified in one process or multiple processes and / or blocks Figure 1 one process or multiple processes and / or blocks Figure 1 or steps of the function specified in multiple blocks.
[0036] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.
[0037] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.
Claims
1. A multi-network sharing management method, characterized in that, Specifically, it includes the following steps: S101: Integrate network resource types, select the device network node locations in multiple networks to set data collection points, and store the collected original network data in a database using wireless transmission; S102: Check whether there are errors and inconsistent information in the original network data, reduce the original network data to a specified range using min-max normalization and map it to the same scale, and transmit the processed network data to the database using wireless transmission; S103: Call the network data in the database, combine it with a timer to form network time series data, obtain the central tendency, dispersion degree, and distribution pattern of the network time series data using statistical features, and predict network data indicators through a time series model; S104: Obtain the network data indicators during high and low peak periods according to the results of the time series model, and perform multi-network scheduling management using a visualization interface and dynamic selection.
2. The multi-network sharing management method according to claim 1, wherein: In S101, integrating network resource types includes servers, storage devices, network devices, virtual machines, and containers. Select the device network node locations in multiple networks to set data collection points, install a traffic monitor at the data collection points to collect original network data in real time through port mirroring of network resources, and configure the original network data indicators and the original network data collection frequency in the traffic monitor. The original network data indicators include network traffic to represent the network load situation and traffic distribution, bandwidth utilization to monitor the usage of network bandwidth, and latency including network latency and transmission latency to evaluate network performance and response speed. The original network data collection frequency is selected as high speed to collect subtle changes in the network, and the collected original network data is stored in a database using wireless transmission.
3. The multi-network sharing management method according to claim 1, characterized in that: In S102, check whether there are errors and inconsistent information in the original network data, and prepare preparatory data items. When there are errors and inconsistent information in the original network data, fill in the missing values using the preparatory data items, reduce the original network data to a specified range using min-max normalization, and map it to the same scale.
4. A multi-network sharing management method according to claim 3, characterized in that: The min-max normalization formula is: Among them represents the normalized network data, represents the network data, represents the minimum value of the original network data, represents the maximum value of the original network data. The processed network data is transmitted to the database by wireless transmission means.
5. A multi-network sharing management method according to claim 1, characterized in that: In S103, call the network data in the database, combine it with a timer to form network time series data, and obtain the central tendency, dispersion degree, and distribution pattern of the network time series data using statistical features.
6. The multi-network sharing management method according to claim 5, characterized in that: The central tendency is represented by the mean of the network time series data, and its specific formula is: wherein represents the mean value of network timing data represents the i-th normalized network timing data represents the number of network timing data 7. A multi-network sharing management method according to claim 5, characterized in that: The dispersion degree is represented by the variance of the network time series data, and its specific formula is: where represents the variance of network time-series data, represents the mean of network time-series data, represents the i-th normalized network time-series data, represents the number of network time-series data.
8. A multi-network sharing management method according to claim 5, characterized in that: The distribution pattern is represented by the percentile of the network time series data. Sort the time series data according to the percentile size, select the first network time series data as the initial value of the time series model, and the time series model selects the recursive least squares method, and its specific formula is: Among them represents the network time series data at the t-th time point, represents the intercept term of the model, which represents the network time series data when the independent variable is 0, represents the influence degree of the initial value of the time series model on the network time series data at the t-th time point, represents the influence degree of the initial value of the time series model at the previous moment on the network time series data at the t-th time point, represents the initial value of the time series model, represents the network time series data at the (t - 1)-th time point, and predicts the network data index through the network time series data at the t-th time point.
9. A multi-network sharing management method according to claim 1, characterized in that: In S104, peak-period network data metrics are obtained according to the time series model results. During the peak period, the network controller dynamically adjusts the weight of bandwidth allocation according to the priority and importance of the application, and uses the column chart of the visualization interface to display the load condition and traffic distribution of the peak-period network. The optimal path is dynamically selected and a cache is set at the device network node location to reduce network latency and transmission latency. Off-peak-period network data metrics are obtained according to the time series model results. During the off-peak period, load balancing is dynamically performed according to the real-time traffic condition and network topology, and connection pool management is used by monitoring different device network nodes and links to reduce the number of handshakes and acknowledgments during communication. The column chart of the visualization interface is used to display the load condition and traffic distribution of the off-peak-period network.