A network abnormal traffic detection method and system based on time series analysis technology

Abstract

The invention relates to a network abnormal flow detection method and system based on time sequence analysis technology, belonging to the technical field of network flow data research, comprising the following steps: collecting computer equipment network flow data stored in a data center by means of timing synchronization tasks; The collected raw network traffic data is preprocessed to reduce the complexity of data processing for network traffic anomaly detection and analysis; the preprocessed network traffic data is stored in the database; abnormal traffic is detected on the network traffic data; The abnormal traffic is stored in the abnormal traffic feature database. The present invention can realize efficient and accurate abnormal detection and analysis of network traffic.

Description

technical field [0001] The invention relates to a network abnormal flow detection method and system based on time sequence analysis technology, and belongs to the technical field of network flow data research. Background technique [0002] With the rapid development of informatization, network security has always been the top priority in the process of information development. Without network security, there would be no national security. With the development of information technology, the network architecture and deployment environment are becoming more and more complex, and network services are faced with various threats from all parties during the operation process, such as distributed denial of service (DDoS) attacks, which mainly use A large number of requests consume normal bandwidth and resources, so that the server cannot provide services normally. Generally speaking, when network services are attacked or service interruption occurs, the data trend of network traffi...

AI Technical Summary

Problems solved by technology

For example, when malicious network traffic occurs, it often causes obvious traffic fluctuations

In addition, the current abnormal network traffic detection often requires manual intervention to extract traffic data features. Because the types and compositions of network traffic are relatively complex, feature extraction is not a simple task, and it is easy to increase manual computing overhead.

Finally, network traffic data is continuously generated, and the data scale is large. It is difficult to guarantee the detection efficiency and is often time-consuming to perform detection and analysis directly on the original data.

Images