Machine learning methods for medium-term load forecasting Study on the North Benghazi stations of the General Electricity Company in eastern Libya

The General Electricity Company of Libya (GECOL) has experienced a surge in electricity demand in recent years, leading to power shortages, particularly during peak summer months. These shortages, often exacerbated by system outages caused by large generating unit failures or transmission line disruptions, have significantly impacted the country's stability. This is further compounded by the ongoing political instability in Libya, which, coupled with electricity supply issues, has negatively affected oil and gas production in some of the country's largest fields. This research addresses the challenge of electricity load demand forecasting by employing Machine Learning (ML) techniques, specifically focusing on Medium Term Load Forecasting (MTLF) based artificial intelligence algorithms. The study compares the accuracy and convergence of different ML methods against actual consumption data, aiming to identify the most effective approach. Accurate load forecasting is crucial for electrical utilities like GECOL to effectively meet customer demands and optimize power generation and transmission. Focusing on Benghazi, this research pioneers the application of Machine learning techniques to predict total energy consumption and demand. The study's findings are validated against real-world data obtained from GECOL's Benghazi Regional Control Center (BRCC), demonstrating the potential of ML for improving electricity load forecasting in Libya. The study concluded with the following results: The Extra Trees Regressor algorithm produced the best results for pregnancy as a target, with an accuracy value of 85%. The Huber Regressor algorithm produced the best results for deficit quantity as a target, with an accuracy value of 77%. Keywords: GECOL, Machine Learning, Load Forecasting, Medium Term Load Forecasting, MTLF.