Electrical Load Demand Forecasting Using Feed-Forward Neural Networks

The higher share of renewable energy sources in the electrical grid and electrification significant sectors, such as transport heating, are imposing a tremendous challenge on operation system due to increase complexity, variability uncertainties associated with these changes. recent advances computational technologies ever-growing data availability allowed development sophisticated efficient algorithms that can process information at very fast pace. In this sense, use machine learning models has been gaining increased attention from electricity sector it provide accurate forecasts behaviour generation consumption, helping all stakeholders optimize their activities. This work develops proposes methodology enhance load demand using model, namely feed-forward neural network (FFNN), by incorporating an error correction step involves prediction initial forecast errors another FFNN. results showed proposed was able significantly improve quality forecasts, demonstrating better performance than benchmark models.