Dispatchable generation analysis and prediction by using machine learning: A case study of South Africa

Abstract

South African power sector has a total installed capacity of about 58,095 MW. However, in the past five years, the nation's energy sector has been struggling to generate a daily average power of about 23,526 MW. Therefore, the use of machine learning technique is crucial to observing the short-term forecast of South African dispatchable power generation and its effects on the nation's economic growth. The choice of SARIMAX as the forecasting tool in this study is due to its flexibility, simplicity, accuracy, and robustness. This study has carried out time series modeling of the South African dispatchable power generation between the period: 2019 and 2023 by using the seasonal auto-regressive moving average with exogenous variables (SARIMAX). The accuracy of the model was measured by the root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), mean bias error (MBE), and mean absolute percentage error (MAPE). When subjected to ARIMA analysis, the predictive model produced the following metrics: RMSE of 669.05 MW, MAE of 575.07 MW, R2 value of 0.937, MBE of -2.45, and MAPE of 0.023. However, upon employing the SARIMAX method, notable improvements were observed, with the metrics indicating RMSE of 469.92 MW, MAE of 330.80 MW, R2 of 0.969, MBE of -0.09 MW, and MAPE of 0.015. The improved accuracy provided by the SARIMAX predictive method confirms the importance of considering seasonal effects in dispatchable generation prediction models. Dispatchable power generation prediction is an important route to achieving sustainable energy for a nation's development, social well-being, and security of life and properties.

Keywords

• Machine learning
• SARIMAX
• Dispatchable generation
• Energy
• Model
• Seasonality