1A Scaling Law of Short Term Electricity Load Forecasting on Varying Levels of Aggregation

Abstract—We propose a simple empirical scaling law that de-scribes load forecasting accuracy at different levels of aggregation. The model is justified based on a simple decomposition of individual consumption patterns. We show that for different forecasting meth-ods, aggregating more customers improves the relative forecasting performance up to specific point. Beyond this point, no more im-provement in relative performance can be obtained. A benchmarking procedure for applying the scaling law to different forecasting models is presented. The model and procedure are evaluated with experimental data. I