Study proposes a predictive home energy management system with customizable bidirectional real-time pricing mechanism

With a steady rise within the international inhabitants, vitality consumption and its related environmental and financial prices are additionally growing.

One efficient strategy to handle these rising prices is by selling the usage of good dwelling home equipment, leveraging Web of Issues (IoT) applied sciences to attach gadgets inside a single community. This connectivity can allow customers to observe and management their real-time energy consumption by way of dwelling vitality administration techniques (HEMS). Vitality suppliers can, in flip, make the most of HEMS to gauge residential demand response (DR) and modify the facility consumption of residential clients in response to grid demand.

Efforts to advertise residential DR, corresponding to by providing financial incentives beneath the real-time pricing (RTP) mannequin, have traditionally struggled to foster lasting behavioral change amongst customers. This problem stems from unidirectional electrical energy pricing mechanisms, which diminish client engagement in residential DR actions.

To deal with these points, Professor Mun Kyeom Kim and Hyung Joon Kim, a doctoral candidate from Chung-Ang College, lately performed a study published within the IEEE Web of Issues Journal. Their research proposes a predictive dwelling vitality administration system (PHEMS).

Prof. Mun Kyeom Kim led the research, introducing a custom-made bidirectional real-time pricing (CBi-RTP) mechanism built-in with a sophisticated worth forecasting mannequin. These improvements present compelling causes for customers to take part actively in residential DR efforts.

The CBi-RTP system empowers end-users by permitting them to affect their hourly RTPs by managing their transferred energy and family equipment utilization. Furthermore, PHEMS incorporates a deep-learning-based forecasting mannequin and optimization technique to investigate spatial-temporal variations inherent in RTP implementations. This functionality ensures sturdy and cost-effective operation for residential customers by adapting to irregularities as they come up.

Experimental outcomes from the research show that the PHEMS model not solely enhances person consolation but additionally surpasses earlier fashions in accuracy of forecasting, peak discount, and price financial savings. Regardless of its superior efficiency, the researchers acknowledge room for additional improvement.

Prof. Mun Kyeom Kim notes, “The main challenge with our predictive home energy management system lies in accurately determining the baseline load for calculating hourly shifted power. Future research will focus on enhancing the reliability of PHEMS through improved baseline load calculation methods tailored to specific end-users.”

Supplied by
Chung Ang College