Optical fiber communication network abnormal flow monitoring method based on big data
Through the fiber communication traffic mining model to process and denoise historical traffic data, the entropy value baseline is constructed and the threshold is set, which solves the real-time monitoring and misjudgment of traffic monitoring of fiber communication networks in the existing technology, and realizes the abnormal traffic of fiber communication networks Accurate identification.
Patent Information
- Application Number
- CN202411635120.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-15
- Publication Date
- 2025-02-21
AI Technical Summary
The existing fiber optic communication network traffic monitoring methods cannot achieve real-time monitoring, there are misjudgment situations, and abnormal traffic cannot be accurately identified.
Through the optical fiber communication traffic mining model, historical traffic data are obtained, data processing and denoising, a normal traffic entropy value baseline is constructed, and an entropy value threshold is set, the window time traffic data entropy value is calculated, and whether it exceeds the threshold is determined to identify abnormal traffic.
It realizes accurate identification of abnormal traffic in fiber optic communication network, reduces misjudgment situations, and improves the accuracy of abnormal traffic recognition.
Smart Images
Figure CN119496555A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of optical fiber communications, and specifically to a method for monitoring abnormal traffic in an optical fiber communication network based on big data. Background Art
[0002] Fiber-optic communication, also known as fiber-optic communication, refers to a method of transmitting information using light and optical fiber. It has the advantages of large transmission capacity and good confidentiality. It is one of the main wired communications today. With the large-scale application of fiber-optic communication networks, the traffic of fiber-optic communication networks has also increased significantly. In the big data environment, fiber-optic communication networks need to process a large amount of data. However, abnormal changes in network traffic may cause congestion in the fiber-optic network, excessive resource occupation, and other problems, affecting the normal operation of the fiber-optic network.
[0003] The existing fiber optic communication network traffic monitoring method cannot achieve real-time monitoring of abnormal network traffic, and cannot provide timely warnings and take corresponding measures when network traffic is abnormal; and the existing network traffic monitoring method has the problem of misjudging normal traffic as abnormal traffic. Summary of the invention
[0004] In order to solve the problem of misjudgment in the existing optical fiber communication network traffic monitoring method, a method for monitoring abnormal traffic in an optical fiber communication network based on big data is proposed.
[0005] A method for monitoring abnormal traffic in an optical fiber communication network based on big data, comprising:
[0006] Step 1: Obtain historical traffic data of the optical fiber communication network through the optical fiber communication traffic mining model, perform data processing on the obtained historical traffic data of the optical fiber communication network, and perform denoising on the processed historical traffic data of the optical fiber communication network to obtain denoised historical traffic data of the optical fiber communication network;
[0007] Step 2: construct an entropy value baseline of normal traffic of the optical fiber communication network according to the denoised historical traffic data of the optical fiber communication network, and set a first entropy value threshold and a second entropy value threshold according to the entropy value baseline of normal traffic of the optical fiber communication network;
[0008] Step three: Obtain window time fiber optic communication network traffic data, and calculate the window time fiber optic communication network traffic data entropy value; determine whether the fiber optic communication network traffic data entropy value exceeds the first threshold or the second threshold, if so, identify it as abnormal traffic, otherwise identify it as normal traffic.
[0009] Beneficial Effects
[0010] The present application discloses a method for monitoring abnormal traffic in an optical fiber communication network based on big data, which obtains historical traffic data of the optical fiber communication network, and performs data processing and denoising on the obtained historical traffic data of the optical fiber communication network; constructs an entropy value baseline for normal traffic in the optical fiber communication network, and sets a first threshold and a second threshold for the entropy value; calculates the entropy value of the traffic data of the optical fiber communication network during the window time, and identifies and distinguishes abnormal traffic from normal traffic by judging whether the entropy value of the traffic data of the optical fiber communication network exceeds the first threshold or the second threshold. The present application discloses a method for monitoring abnormal traffic in an optical fiber communication network based on big data, which can accurately identify abnormal traffic in the optical fiber communication network, reduce misjudgment, improve the accuracy of abnormal traffic identification, and realize abnormal traffic monitoring in the optical fiber communication network. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 This is a flow chart of a method for monitoring abnormal traffic in an optical fiber communication network based on big data, which is a specific implementation method of the present application. DETAILED DESCRIPTION
[0012] Specific implementation method 1: This implementation method is explained in conjunction with the accompanying drawings of the specification to clearly and completely describe the technical solution in the embodiment of the present invention:
[0013] A method for monitoring abnormal traffic in an optical fiber communication network based on big data, comprising:
[0014] Step 1: Obtain historical traffic data of the optical fiber communication network through the optical fiber communication traffic mining model, perform data processing on the obtained historical traffic data of the optical fiber communication network, and perform denoising on the processed historical traffic data of the optical fiber communication network to obtain denoised historical traffic data of the optical fiber communication network;
[0015] Step 2: construct an entropy value baseline of normal traffic of the optical fiber communication network according to the denoised historical traffic data of the optical fiber communication network, and set a first entropy value threshold and a second entropy value threshold according to the entropy value baseline of normal traffic of the optical fiber communication network;
[0016] Step three: Obtain window time fiber optic communication network traffic data, and calculate the window time fiber optic communication network traffic data entropy value; determine whether the fiber optic communication network traffic data entropy value exceeds the first threshold or the second threshold, if so, identify it as abnormal traffic, otherwise identify it as normal traffic.
[0017] Specifically, a method for monitoring abnormal traffic in an optical fiber communication network based on big data is proposed. After data processing and denoising of historical traffic data of the optical fiber communication network, a normal traffic entropy value baseline is constructed, and a first threshold and a second threshold of the entropy value are set. The entropy value of the optical fiber communication network traffic data in the window time is calculated, and it is determined whether the entropy value of the optical fiber communication network traffic data exceeds the first threshold or the second threshold. If so, it is identified as abnormal traffic, otherwise it is identified as normal traffic.
[0018] Furthermore, the optical fiber communication traffic mining model is the least squares support vector machine. The least squares support vector machine regression function is:
[0019] Among them, ω is the main characteristic vector of optical fiber communication traffic, α is the auxiliary vector, is the calculation parameter.
[0020] Specifically, Least Squares Support Vector Machine (LSSVM) is a method that has shown high performance in the field of big data mining.
[0021] Furthermore, the method for processing the obtained historical traffic data of the optical fiber communication network is: deduplication, missing value processing, error value correction and data standardization are performed on the historical traffic data of the optical fiber communication network in sequence to obtain the processed historical traffic data of the optical fiber communication network.
[0022] Specifically, the historical traffic data of the optical fiber communication network is processed to ensure data accuracy, and denoising can eliminate interference from external factors such as equipment noise and electromagnetic interference.
[0023] Furthermore, the method for denoising the processed historical traffic data of the optical fiber communication network is a wavelet transform method.
[0024] Furthermore, a method for constructing a normal traffic entropy value baseline of the optical fiber communication network based on the denoised historical traffic data of the optical fiber communication network is as follows: a normal traffic probability distribution model is constructed based on the denoised historical traffic data of the optical fiber communication network and a relative entropy value of normal traffic is calculated, and a normal traffic entropy value baseline of the optical fiber communication network is obtained based on the relative entropy value of normal traffic.
[0025] Furthermore, a method for monitoring abnormal traffic in an optical fiber communication network based on big data also includes abnormal traffic alarming after abnormal traffic is identified. Specific implementation method 2:
[0027] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first specific implementation mode when executing the computer program.
[0028] Specific implementation method three: A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the method described in specific implementation method one are implemented.
[0029] Although the present invention is described herein with reference to specific embodiments, it should be understood that these embodiments are merely examples of the principles and applications of the present invention. It should therefore be understood that many modifications may be made to the exemplary embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the various dependent claims and features described herein may be combined in a manner different from that described in the original claims. It should also be understood that features described in conjunction with individual embodiments may be used in other described embodiments.
Claims
1. A method for monitoring abnormal traffic in an optical fiber communication network based on big data, characterized in that: include: Step 1: Obtain historical traffic data of the optical fiber communication network through the optical fiber communication traffic mining model, perform data processing on the obtained historical traffic data of the optical fiber communication network, and perform denoising on the processed historical traffic data of the optical fiber communication network to obtain denoised historical traffic data of the optical fiber communication network; Step 2: construct an entropy value baseline of normal traffic of the optical fiber communication network according to the denoised historical traffic data of the optical fiber communication network, and set a first entropy value threshold and a second entropy value threshold according to the entropy value baseline of normal traffic of the optical fiber communication network; Step three: Obtain window time fiber optic communication network traffic data, and calculate the window time fiber optic communication network traffic data entropy value; determine whether the fiber optic communication network traffic data entropy value exceeds the first threshold or the second threshold, if so, identify it as abnormal traffic, otherwise identify it as normal traffic.
2. According to the method for monitoring abnormal traffic in an optical fiber communication network based on big data in claim 1, it is characterized by: The optical fiber communication traffic mining model is a least squares support vector machine.
3. According to the method for monitoring abnormal traffic in an optical fiber communication network based on big data in claim 1, it is characterized by: The method for processing the obtained historical traffic data of the optical fiber communication network is as follows: the historical traffic data of the optical fiber communication network is deduplicated, missing value processed, error value corrected and data standardized in sequence to obtain the processed historical traffic data of the optical fiber communication network.
4. According to claim 1, a method for monitoring abnormal traffic in an optical fiber communication network based on big data is characterized in that: The method for denoising the processed historical traffic data of the optical fiber communication network is the wavelet transform method.
5. The method for monitoring abnormal traffic in an optical fiber communication network based on big data according to claim 1 is characterized in that: The method for constructing a normal traffic entropy value baseline of the optical fiber communication network based on the denoised historical traffic data of the optical fiber communication network is as follows: a normal traffic probability distribution model is constructed based on the denoised historical traffic data of the optical fiber communication network and the relative entropy value of the normal traffic is calculated, and a normal traffic entropy value baseline of the optical fiber communication network is obtained based on the relative entropy value of the normal traffic.
6. The method for monitoring abnormal traffic in an optical fiber communication network based on big data according to claim 1, characterized in that: It also includes abnormal traffic alarm when abnormal traffic is identified.
7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.