Evaluating and Comparing the Performance of Statistical and Machine Learning Algorithms to Achieve Successful Load Forecasting in Saudi Arabia

Abstract

Electricity is a vital resource that powers modern society, and reliable forecasting of electricity demand and supply is essential for the effective operation of power systems. Accurate forecasts allow power system operators to make informed decisions about generation, transmission, and distribution, which can help to prevent blackouts and other disruptions to the electricity supply. Various methods have been developed for forecasting electricity, including statistical methods such as ARIMA and Prophet and artificial intelligence (AI) algorithms such as recurrent neural network (RNN) and support vector machines (SVM). Recent advances in deep learning, particularly Long Short-Term Memory (LSTM) networks, have demonstrated superior performance for time-series forecasting tasks, especially with high-frequency datasets.  In this paper, we compared the performance of six methods covering two statistical and four AI algorithms for forecasting electricity demand. They were applied to four different datasets: 1) A monthly KAPSARC, which stands for The King Abdullah Petroleum Studies and Research Center, Dataset in Saudi Arabia with limited historical data, 2) A generated hourly KAPSARC Dataset in Saudi Arabia, 3) An hourly PJM Dataset in USA with a large amount of data, and 4) A generated monthly PJM Dataset in USA. The performance of the approaches was different with each dataset. Overall, the results confirm that data richness particularly hourly granularity is a decisive factor in forecasting accuracy, and that deep learning models require substantial data volumes to outperform statistical baselines. These findings have direct implications for electricity infrastructure planning in Saudi Arabia under Vision 2030.