The Importance of Environmental Factors in Forecasting Australian Power Demand
share
In this paper, a seasonal autoregressive integrated moving average (SARIMA) model is derived to forecast weekly peak power demand for several states of Australia for a yearly time-scale. The explanatory influence of environmental variables such as maximum temperature, minimum temperature and solar exposure is analyzed using linear regression. The SARIMA-regression model shows an average MAPE (mean absolute percentage error) of 3.45 excluded from the average. Additionally, the importance of environmental variables is highlighted by an average MAPE improvement of 45 SARIMA-regression model over the model that does not include environmental variables. The Tasmanian data is a notable exception, with only a 10 improvement. To the best of our knowledge, this paper is the first attempt to investigate the crucial role of environmental factors in improving the Australian electricity power demand forecasts for 52 weeks.
READ FULL TEXT