Predictive Variables for Electricity Demand

Abstract

Electricity demand is an important factor in the design and operation of reliable and efficient electric power systems. Over the past decade, many prediction methods have been introduced, including statistical and machine learning-based models, to predict energy demand. Prediction errors are significantly influenced by the selection of input variables as reported in the literature. This paper aims to review various electric load forecasting variables used by six previous papers. There are 30 variables is used in previous researches. The variables are categorized into time factors, historical load, environmental factors and seasonal factors. This study highlights the most commonly used variables and provides insights into their relevance in various forecasting contexts.