Identification of Power Demand Characteristics for Each Area and Energy Saving Control Selection Method

Demand response (DR), which aims to stabilize power supply and cost of electricity, has garnered considerable research interest in recent years. It is expected to be particularly useful in small and medium-sized office buildings, which are responsible for a large share of the total electricity consumption of an area. In this paper, we propose a method for identification of power demand characteristics for each unit, floor, and area based on a power consumption prediction model developed using heterogeneous mixture learning technology. With experimental data obtained from an eight- story office building, we develop an energy-saving control selection method for DR based on the identified power demand characteristics and our evaluation results are reported herein.