enhancing the interpretability of electricity consumption forecasting models for mining enterprises using shapley additive explanations

The objective of this study is to enhance user trust in electricity consumption forecasting systems for mining enterprises by applying explainable artificial intelligence methods that provide not only forecasts but also their justifications. the research object comprises a complex of mines and ore processing plants of a company purchasing electricity on the wholesale electricity and power market. hourly electricity consumption data for two years, schedules of planned repairs and equipment shutdowns, and meteorological data were utilized. ensemble decision trees were applied for time series forecasting, and an analysis of the impact of various factors on forecasting accuracy was conducted. an algorithm for interpreting forecast results using the shapley additive explanation method was proposed. the mean absolute percentage error was 7.84 % with consideration of meteorological factors, 7.41 % with consideration of meteorological factors and a load plan formulated by an expert, and the expert's forecast error was 9.85 %. the results indicate that the increased accuracy of electricity consumption forecasting, considering additional factors, further improves when combining machine learning methods with expert evaluation. the development of such a system is only feasible using explainable artificial intelligence models.