Cognitive network QoS (quality of service) guarantee method on basis of service differentiation

Abstract

The invention discloses a cognitive network QoS (quality of service) guarantee method on the basis of service differentiation. The method takes services as the center, the information is gathered to a domain cognitive server for the purpose of being processed by collecting network QoS parameters, service information and network state information, and a processing result serves as a training sample to train a support vector machine (SVM) to obtain a classifier; the classifier predicts possible problems in a network in real time according to an information processing result collected by an edgerouter and a core router; the server issues a new strategy to the edge router according to the problems possibly happening; and the edge router distributes different priority levels to different services according to the new strategy so as to provide guarantee for network QoS. The method is combined with the existing differentiated service frame and has expandability; meanwhile, an artificial intelligence method is introduced in, so that the method can effectively make a decision before problems occur so as to realize network cognition.

Description

technical field [0001] Based on the cognitive network, the invention proposes a cognitive network QoS guarantee method based on service differentiation. The main research is how to combine the cognitive network with the increasingly mature business identification technology and differentiated service architecture, so that the network can achieve self-awareness, self-decision-making, self-management, and self-control while limiting the complexity to edge routers and domain identification. Known server, so that it has good scalability. The method relates to technical fields such as service identification, differentiated service, network QoS, artificial intelligence, and cognitive network. Background technique [0002] In recent years, with the rapid development of network technology and applications and the diversification of network access forms, the network has become more and more complex, and managing the increasingly complex network is one of the main challenges facing t...

AI Technical Summary

Problems solved by technology

[0005] 1. The traditional network can only do corresponding processing after the network has a problem, and there is a lag, which will inevitably affect the QoS of the network;

[0006] 2. The policies in the existing differentiated services are static and cannot be changed, so they cannot adapt to the current dynamic and complex network environment;

[0007] 3. Several existing cognitive network architectures do not differentiate services, but research shows that more than half of the network traffic now comes from P2P services, and P2P services have seriously affected the QoS of the network. is particularly important;

[0008] 4. The current research on cognitive network rarely considers the combination with the existing QoS architecture, so it lacks feasibility and scalability

Images