Mixed P2P flow monitoring system based on BP neural network

Abstract

The invention discloses a mixed P2P flow monitoring system based on a BP neural network. The mixed P2P flow monitoring system comprises a BP network model training module, a classifying module, a matching module, an analyzing module and an updating module. The updating module is used for adjusting a BP trainer irregularly to achieve the design requirement, and for receiving unknown P2P flow data found through the analyzing module based on the method of combining the flow statistic characteristics and the deep layer data package detecting technology to improve the effect of the trainer to enable the classifying module produced by the trainer to be more suitable for a classifier. A management module serves as a main center of a whole management platform, and is used for coordinating the relationship among the matching module, the analyzing module and the updating module and organizing the normal operation of the modules to generate a flow log. By means of the mixed P2P flow monitoring system based on the BP neural network, the precision can be effectively improved, the rate of rejecting the fault and the rate of rejecting the truth are reduced, and the mixed P2P flow monitoring system is suitable for monitoring flow under the situation that the current P2P technology develops rapidly.

Description

technical field [0001] The invention relates to the field of computers, in particular to a hybrid P2P flow monitoring system based on BP neural network. Background technique [0002] The network monitoring system is widely used at present, and it is an important means of network security protection. Through the real-time monitoring of the network status, the network monitoring system can achieve the discovery of specific security events, the deployment of network resources, the management of network traffic and other aspects of security. It is an effective method to realize IT management and control. [0003] With the development of the network, more and more P2P applications appear in the current network environment. The P2P network structure and application can improve the utilization rate of network resources and increase the resource sharing rate, which is the general trend of network development in the future. However, due to the lack of unified standards and usage spe...

AI Technical Summary

Problems solved by technology

The keywords of various P2P applications may change with software upgrades, so the acquisition of keywords is not done once and for all and must be updated at all times; the acquisition of keywords is obtained by analyzing the content of the data package, which is related to the issue of data privacy ; The summary of keywords needs to collect a large number of data packets, intercept or copy the data packets on the backbone network, especially when the network speed of the backbone network reaches 10Gbps, the collection efficiency and storage capacity of data packets are often not optimistic

In addition, more and more P2P application software now encrypts the content of data packets, and the identification technology based on key matching is invalid

Images