Year: 2016
Type: conference-paper
Abstract: In this paper, a network performance evaluation algorithm is proposed based on BP neural network.This system collects 8 network parameters in a local area network, and classifies the performance of network into three states: excellent, good and unqualified.Verification and analysis results show that the accuracy of the proposed network performance evaluation algorithm reaches up to 90% by K-fold cross validation test.The experiments indicate that this proposed algorithm is robust and effective.Moreover, the calculation time of this system is less than 1ms.It could be effectively applied for a real-time network performance evaluation.
Authors: Qi Liu, Xiyue Wang, Yiyong Lin, Ling He, Yunzhi Huang
Institution: Sichuan University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2521730199
