文章基本信息

标题：Forecasting Malaysia Load Using a Hybrid Model
本地全文：下载
作者：Norizan Mohamed ; Maizah Hura Ahmad
期刊名称：Statistika
印刷版ISSN：1411-5891
出版年度：2010
卷号：10
期号：1
页码：1-8
DOI：10.29313/jstat.v10i1.1003
出版社：Universitas Islam Bandung
摘要：A hybrid model, which combines the seasonal time series ARIMA (SARIMA) and the multilayer feedforward neural network to forecast time series with seasonality, is shown to outperform both two single models. Besides the selection of transfer functions, the determination of hidden nodes to use for the non linear model is believed to improve the accuracy of the hybrid model. In this paper, we focus on the selection of the appropriate number of hidden nodes on the non linear model to forecast Malaysia load. Results show that by using only one hidden node, the hybrid model of Malaysia load performs better than both single models with mean absolute percentage error (MAPE) of less than 1%.
关键词：Load Forecasting; Seasonal Autoregressive Integrated Moving Average; Multilayer Feedforward Neural Network; Hybrid Model; Hidden Nodes