Impacts of traffic data on short-term residential load forecasting before and during the COVID-19 pandemic

• DOI: 10.1016/j.esr.2022.100895
• Publication Date: 2022-07-15T07:27:22Z
• Authors: Aksornchan Chaianong; Christian Winzer; Mario Gellrich
• Keywords: Consumption

Accurate load forecasting is essential for power-sector planning and management. This applies during normal situations as well phase changes such the Coronavirus (COVID-19) pandemic due to variations in electricity consumption that made it difficult system operators forecast accurately. So far, few studies have used traffic data improve prediction accuracy. paper aims investigate influence of combination with other commonly features (historical load, weather, time) – better predict short-term residential consumption. Based on from two selected distribution grid areas Switzerland random forest a technique, findings suggest impact forecasts much smaller than time variables. However, could where information historical not available. Another benefit using might explain phenomenon interest demand. Some our vary greatly between datasets, indicating importance based larger numbers features, approaches.