Flexibility Prediction of Aggregated Electric Vehicles and Domestic Hot Water Systems in Smart Grids

With the growth of intermittent renewable energy generation in power grids, there is an increasing demand for controllable resources to be deployed guarantee quality and frequency stability. The flexibility response (DR) has become a valuable solution this problem. However, existing research indicates that problems on prediction DR have not been investigated. This study applied temporal convolution network (TCN)-combined transformer, deep learning technique predict aggregated two types resources, is, electric vehicles (EVs) domestic hot water system (DHWS). uses historical consumption data these signals (DSs) facilitate prediction. can generate size maintenance time flexibility. accuracy results was verified through simulations case studies. simulation show under different times, changed. proposed resource method demonstrates its application unlocking demand-side provide reserve grids.