Methodology for forecasting electricity consumption by Grey and Vector autoregressive models
| Autor: | Jean Gaston Tamba, Louis Monkam, Serge Guefano, Tchitile Emmanuel Wilfried Azong |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Mean squared error
Computer science Science Clinical Biochemistry 010501 environmental sciences Electricity consumption VAR model 01 natural sciences Vector autoregression 03 medical and health sciences Econometrics hybrid model GM(1 1)-VAR(1) Grey model 030304 developmental biology 0105 earth and related environmental sciences Consumption (economics) 0303 health sciences Energy demand business.industry Method Article Medical Laboratory Technology Autoregressive model Forecast Electricity business Hybrid model Energy (signal processing) |
| Zdroj: | MethodsX MethodsX, Vol 8, Iss, Pp 101296-(2021) |
| ISSN: | 2215-0161 |
| Popis: | Highlights • The Grey and Vector autoregressive models are coupled to improve their accuracy. • Five economic and demographic parameters are included in the new hybrid model. • This new model is a reliable forecasting tool for assessing energy demand. Forecasting energy demand in general, and electricity demand in particular, requires the developing reliable forecasting tools that can be used to monitor the evolution of consumers’ energy needs more accurately. The proposed new hybrid GM(1,1)-VAR(1) model is meant for that purpose. The latter is based on the Grey and Vector autoregressive approaches, and makes it possible to predict future demand, by taking into account economic and demographic determinants with an exponential growth trend. With an associated APE of 1.5, a MAPE of 1.628%, and an RMSE of 15.42, this new model thus presents better accuracy indicators than hybrid models of the same nature. Also, it proves to be as accurate as some recent hybrid artificial intelligence models. The model is thus a reliable forecasting tool that can be used to monitor the evolution of energy demand.•The Grey and Vector autoregressive models are coupled to improve their accuracy.•Five economic and demographic parameters are included in the new hybrid model.•This new model is a reliable forecasting tool for assessing energy demand. Graphical abstract Image, graphical abstract |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|