Medium‐term forecasting of daily aggregated peak loads from heat pumps using clustering‐based load duration curves to calculate the annual impact on medium to low voltage transformers

Abstract

Abstract The energy transition drives the adoption of heat pumps (HPs). Their peak loads have a large impact on distribution networks. Therefore, the proposed methodology calculates the annual impact on medium to low voltage (MV/LV) transformers based on a medium‐term forecast of daily aggregated peak loads from HPs using the number, their rated power, a normalised load duration curve, and the daily average ambient temperature. The forecast differentiates between daily aggregated peak loads of HPs with different heating demands and the varying impact due to seasonal weather differences. First, 221 measured residential HPs over two years were randomly selected and clustered to identify different heating demands. These clusters were used to calculate four representation functions. Second, 108 other measured HPs were clustered and used to forecast the aggregated peak load with the calculated four representation functions. These forecasts were used to calculate the annual impact on an MV/LV transformer with a daily time resolution. These results indicate the periods over a year that the MV/LV transformer is at risk of congestion and it indicates the potential to mitigate congestion through demand‐side management.

Keywords

• artificial intelligence and data analytics
• distribution networks
• load forecasting