Enhancing Electricity Demand Forecasting Accuracy Through Hybrid Models and Deep Learning Techniques: A Systematic Literature Review

Abstract: This reviewed literature on electricity forecasting covers its history, terminology, and techniques. A systematic review of existing studies highlighted key findings and future research opportunities. Conventional statistical techniques and MLA can predict electricity demand over time with various techniques and forecasting windows tailored to data and problem specifics. Most studies focused on STLF, often without testing techniques on MTLF and LTLF. The key findings include: Many studies (26%) used conventional statistical methods like ARIMA, ARIMAX, and SARIMAX for electricity forecasting, often without benchmarking algorithms. Various factors, such as time, weather, electricity price, population, and economy, influence ELF. Weather parameters were the most commonly used predictors, though performance varied across studies. A global increase in electricity demand has driven numerous studies, though less research has been done in low- and middle-income countries. Deep neural networks like LSTM have been underutilised in electricity forecasting. LSTM's ability to store memory and address the vanishing gradient problem makes it promising for future research, particularly in hybrid models combining CNN and LSTM for forecasting peak load demand based on economic and environmental factors.