计算机技术与发展2017，Vol.27Issue(7)：6-9,4.DOI:10.3969/j.issn.1673-629X.2017.07.002
基于指数平滑法的动态预测机制
A Dynamic Prediction Mechanism Based on Exponential Smoothing Method
摘要
Abstract
Real time prediction for data and developing the work plan in next phase is significant for the production of life.There are many prediction models in the present stage in which the exponential smoothing method is widely used in short-term forecasting.In view of problems of the traditional forecasting model like single way,fixed forecasting mode,not better following the trend of the change of the data and the limitation and so on,a dynamic prediction mechanism based on the traditional model is proposed.It selects a certain step of data in the prediction process and acquires variable smoothing coefficient according to the actual changes of data.The smoothing coefficient can be adjusted automatically according to the change trend of the actual data,making the forecast model can be traced to the actual trend of the data in the prediction process,which has a higher adaptability.In the simulation experiment,the actual usage frequency of the multimedia classroom in a college is used as the experimental data to compare the modified model and the traditional model.The result shows that the modified dynamic prediction mechanism has higher prediction accuracy,and the model is simple and easy to use,and can meet the needs of the actual situation.关键词
预测模型/指数平滑法/传统模型/动态平滑系数/多媒体教室Key words
prediction model/exponential smoothing method/traditional model/dynamic smoothing coefficient/multimedia classroom分类
信息技术与安全科学引用本文复制引用
沈海迪,万振凯..基于指数平滑法的动态预测机制[J].计算机技术与发展,2017,27(7):6-9,4.基金项目
天津市科技计划项目(15JCTPJC58100) （15JCTPJC58100）
