Forecasting medium-term electricity demand in a South African electric power supply system

Abstract

The paper discusses an application of generalised additive models (GAMs) in predicting medium-term hourly electricity demand using South African data for 2009 to 2013. Variable selection was done using least absolute shrinkage and selection operator (Lasso) via hierarchical interactions, resulting in a model called GAM-Lasso. The GAM-Lasso model was then extended by including tensor product in-teractions to yield a second model, called GAM-te-Lasso. Comparative analyses of these two models were done with a gradient-boosting model to act as a benchmark model and the third model. The fore-casts from the three models were combined using a forecast combination algorithm where the average loss suffered by the models was based on the pinball loss function. The results showed significantly im-proved accuracy of forecasts, making this study a useful tool for decision-makers and system operators in power utility companies, particularly in mainte-nance planning including medium-term risk assess-ment. A major contribution of this paper is the inclu-sion of a nonlinear trend. Another contribution is the inclusion of temperature based on two thermal re-gions of South Africa.