摘要

This letter reports on the averaging effect on prediction errors of the fast automated demand response (FastADR) power limitation amount calculated by our autoregressive and neural net models for a large number of multi-type building air-conditioning facilities. The standard deviation of prediction error variation decreases with the number of FastADR trials according to the N rule. This result will be useful for estimating the averaging effect in the prediction of FastADR for a large number of target facilities.

  • 出版日期2016-11