Liu, Yinyan, Ma, Jin, Xing, Xinjie 
ORCID: 0000-0001-6277-5045, Liu, Xinglu and Wang, Wei
(2022)
A home energy management system incorporating data-driven uncertainty-aware user preference.
Applied Energy, 326.
p. 119911.
|
PDF
A_Home_Energy_Management_System_Incorporating_Data_Driven_Uncertainty_Aware_User_Preference.pdf - Author Accepted Manuscript Download (6MB) | Preview |
Abstract
Today, with the increase in the integration of renewable sources, the home energy management system (HEMS) has become a promising approach to improve grid energy efficiency and relieve network stress. Traditionally, complicated thermal models or passive participation of the users prevents HEMS from fully automating the involvement of demand-side energy management. In this paper, an advanced HEMS is proposed incorporating uncertainty-aware user preference. The energy consumption user behavior, including temporal and temperature habits, is firstly characterized in a data-driven way with non-intrusive load monitoring (NILM). To capture the potential uncertainties resulting from the characteristics of NILM modeling, a novel NILM model is developed with Bayesian theory. The NILM-based preference level is further integrated into the HEMS to schedule the appliances and respond the demand response (DR) signals for economic benefits. Extensive experiments are performed with the real-world dataset. The effectiveness and superiority of the proposed algorithm are demonstrated particularly in reducing the energy cost, maintaining the user's preference level, and encouraging users to participate in DR. Compared to a traditional HEMS as a benchmark, the proposed HEMS for a 24-hour horizon can trade-off limited electricity costs to keep the preference at a high level.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Non-intrusive load monitoring, Bayesian neural network, Uncertainty aware, User preference, Home energy management system |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 04 Oct 2022 06:33 |
| Last Modified: | 18 Jan 2023 20:40 |
| DOI: | 10.1016/j.apenergy.2022.119911 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3165167 |
Dimensions
Dimensions
