A New Approach to Improve Accuracy of Grey Model GMC(1, n) in Time Series Prediction. (7th December 2015)

• Record Type: Journal Article
• Authors: Moonchai, Sompop; Rakpuang, Wanwisa
• Other Names: Chiu Min-Chie Academic Editor.
• Is Part Of: Modelling and simulation in engineering. Volume 2015(2015)
• Publication Date: 2015-12-07
• Subjects: Engineering -- Simulation methods -- Periodicals; Engineering -- Mathematical models -- Periodicals; 620.004
• DOI: 10.1155/2015/126738
• Languages: English
• ISSNs: 1687-5591

Abstract

Abstract : This paper presents a modified grey model GMC( 1, n ) for use in systems that involve one dependent system behavior andn - 1 relative factors. The proposed model was developed from the conventional GMC( 1, n ) model in order to improve its prediction accuracy by modifying the formula for calculating the background value, the system of parameter estimation, and the model prediction equation. The modified GMC( 1, n ) model was verified by two cases: the study of forecasting CO2 emission in Thailand and forecasting electricity consumption in Thailand. The results demonstrated that the modified GMC( 1, n ) model was able to achieve higher fitting and prediction accuracy compared with the conventional GMC( 1, n ) and D-GMC( 1, n ) models.