无线接入点吞吐率预测的建模与优化

Modeling and Optimizing of Access Point Throughput Prediction

针对接入点吞吐率的多步预测问题,提出基于Nu-支持向量回归的建模策略,设计了并行混合粒子群算法,从特征选择与参数选择两个方面对预测模型进行联合优化。评估结果表明,Nu-支持向量回归模型在吞吐率多步预测中能取得较高精度,并行混合粒子群算法具有良好收敛性,且能显著提高预测模型的性能。

Access point is the key device connecting wired and wireless facilities,its performance information is crucial for package routing,bandwidth allocation and management of quality of service parameter.This paper addresses the problem of generating multi-step-ahead throughput prediction for access point.A modeling strategy is introduced based on Nu-SVR（Nu-Support Vector Regression）,and a PH-PSO（Parallel Hybrid Particle Swarm Optimization） algorithm is proposed,for the purpose of combinational optimization to prediction model,including feature selection and hyper-parameter selection.The evaluation results have shown that Nu-SVR model can achieve higher accuracy in throughput prediction of multi-step-ahead,and its performance can be remarkably improved by PH-PSO algorithm with fast convergence rate.