摘要
为了提高节假日移动话务量的预测精度,提出了一种基于多因素影响的忙时话务量预测方法。首先对忙时话务量进行相关性分析,得到4个影响话务量的重要因子,然后把4个因子与忙时话务量训练数据一起作为输入变量,最后用改进的具有非线性惯性权重的粒子群算法优化的最小二乘支持向量机模型进行预测。实验结果表明该预测模型有更高的预测精度和较强的泛化能力。
In order to improve the prediction accuracy of holiday mobile traffic, this study proposes a busy telephone traffic pre-diction method based on multiple factors. Firstly, analyze busy telephone traffic and get four factors. Secondly, put the four factors and training busy telephone traffic data as input variables. Finally, use least square support vector machine model which is optimized by improved particle swarm optimization algorithm with nonlinear inertia weight to predict. The experimental results show that the prediction model has higher prediction accuracy and strong generalization ability.
出处
《激光杂志》
CAS
CSCD
北大核心
2014年第3期39-41,共3页
Laser Journal
基金
中国移动通信集团新疆有限公司研究发展基金项目(项目编号:XJM2012-01)
关键词
多因素
粒子群算法
最小二乘支持向量机
话务量预测
泛化能力
Multiple factors
particle swarm optimization
least square support vector machine
telephone traffic prediction meth-od
generalization ability
