基于BP神经网络的4G话务预测方法研究  

Research on 4G traffic forecasting method based on BP neural network

作　　者：刘建强[1] 黄海晖[1] 陆南昌[1] LIU Jian-qiang;HUANG Hai-hui;LU Nan-chang(China Mobile Group Guangdong Co.,Ltd.,Guangzhou 510623,China)

机构地区：[1]中国移动通信集团广东有限公司

出　　处：《电信工程技术与标准化》2019年第6期48-53,共6页Telecom Engineering Technics and Standardization

摘　　要：目前常用的话务预测算法主要有移动平均法和指数平滑法,虽然可以达到一定精度的话务趋势预测,但对于短期话务量的周期性变化,例如潮汐效应等场景,传统的话务预测算法存在一定的缺陷。需要运用BP神经网络算法,进行更为精准智能的话务预测,为潮汐载波调度提供算法依据。本文将对BP神经网络用于话务预测进行研究,并对模型的预测性能进行评价。At present,the commonly used traffic prediction algorithms are mainly mobile average method and exponential smoothing method.Although the traffic trend prediction can achieve a certain accuracy,the traditional traffic prediction algorithm has some defects for short-term traffic cyclical changes,such as tidal effects.Therefore,it is necessary to use BP neural network algorithm for more accurate and intelligent traffic prediction,and provide the algorithm basis for tidal carrier scheduling.This paper will study the application of BP neural network in traffic prediction and evaluate the prediction performance of the model.

关 键 词：神经网络 LTE 话务预测 

分 类 号：TN929.5[电子电信—通信与信息系统]