Paper Conference

Proceedings of eSim 2016: 9th Conference of IBPSA-Canada


Short term forecasting of the electric demand of HVAC system

Mathieu Le Cam, Radu Zmeureanu, Ahmed Daoud

Abstract: This paper presents a multi-step-ahead forecasting method of electric demand in a large institutional building, to be used in the context of demand response control strategy. A cascade-based method is proposed for electric demand forecasting of cooling system over the next six hours with a time-step of 15 minutes. Datadriven models are developed by using data mining techniques from the Building Automation System (BAS) trend data of 15-min time-step. First, the air flow rate supplied by the AHUs is forecasted, followed by the cooling coils load, and the whole building cooling load. Finally the electric demand of the primary and secondary cooling systems is forecasted with a RMSE of 27 kW for the chillers and 1 kW for the cooling towers; and 2 kW for the secondary system.
Pages: 606 - 617