Abstract
Home energy management systems (HEMSs) are the system to manage the energy usage in houses. The use of HEMSs, and especially those which are capable of automatically controlling home energy appliances such as air-conditioners (ACs), is expected to manage energy utilized in domestic field effectively. In the present study, we focused on automatic AC operation by HEMS with the combined goal of improving thermal comfort while reducing electricity costs. In general, the room temperature and electricity consumption of an AC are highly dependent on the characteristics of the installation environment, so that the derivation of an appropriate AC operation plan is generally a difficult task. To tackle this problem, an energy management method to provide AC operation plan tailor-made for the target AC installation environmental by learning the characteristics of the installation environment (CIE) from the historical operation result data is proposed. The efficacy of the proposed method is verified via numerical and real-world experiments.
Original language | English |
---|---|
Pages (from-to) | 351-362 |
Number of pages | 12 |
Journal | Energy and Buildings |
Volume | 177 |
DOIs | |
Publication status | Published - 2018 Oct 15 |
Keywords
- Air Conditioner (AC)
- Characteristics of Installation Environment (CIE)
- Home energy Management System (HEMS)
- Machine learning
- Operation planning
- Particle Swarm Optimization (PSO)
- Predicted Mean Vote (PMV)
- Real-world Experiment
- Smart house
- Support Vector Regression (SVR)
ASJC Scopus subject areas
- Civil and Structural Engineering
- Building and Construction
- Mechanical Engineering
- Electrical and Electronic Engineering