Long-term forecasting of hourly electricity load: Identification of consumption profiles and segmentation of customers

摘要: Data for aggregated hourly electricity demand shows systematic variations over the day, week, and seasons, forecasting of load has been subject many studies. With metering individual customers, data consumption profiles is available. Using this analysing case Denmark, we show that categories customers are equally but very different distinct categories, is, contribute differently to profile. Therefore, model forecast long-term changes in profile, identify link these projections annual by customers. Long-term projection important future energy system planning, profile an input models serves purpose. In particular, often assume unchanged (although level may change). contrast, our suggests also as shares change new technologies such electrical vehicles (for Denmark particular) heat pumps introduced.