Artificial Neural Network Based Grey Exponential Smoothing Approach for Forecasting Electricity Demand in Sri Lanka

Abstract

The electricity supply of the country has greatly impacted the economy and the nation’s standard of living; an accurate forecast of electricity demand is essential for any country to enhance industrialization, farming, and residential requirements and to make proper investment decisions. Therefore, most countries have been allocating and spending significant amounts from their annual budgets on power generation. This current study proposes an Artificial Neural Network (ANN) based approach to forecast electricity demands in Sri Lanka. For model validation, GM (1, 1), Moving Average, and Grey Exponential Smoothing models were used based on electricity gross generation data from 2000 to 2022. The empirical results suggest that the hybrid Grey Exponential Smoothing model is highly accurate under the non-stationary framework.