Plug-Mate: An IoT-based occupancy-driven plug load management system in smart buildings

Plug load management systems are touted as promising solutions to reduce the rising energy consumption of plug loads in commercial buildings through different load monitoring and control strategies. However, their real-world applications remain relatively unexplored due to several issues related to deployment viability, energy-saving potentials, and system acceptance. Given these limitations, this paper proposes Plug-Mate, a novel IoT-based occupancy-driven plug load management system that reduces plug load energy consumption and user burden through intelligent plug load automation. The proposed system uses an interconnected network of modules and subsystems to perform plug load automation based on the users' (1) high-resolution occupancy information obtained through a non-intrusive indoor localisation system, (2) plug load type information inferred through an advanced plug load identification feature, and (3) diverse control preferences through a personalised user interface. To demonstrate the system's feasibility, six control strategies were evaluated during a 5-month field study in a university office space. Each control strategy involved different levels of plug load automation (i.e., manual, predefined schedules, and occupancy-driven) and was assessed based on their energy savings and user satisfaction levels to identify the optimal balance between automation and user control. Based on this evaluation, the best control strategy reported an average energy savings of 51.7% among different plug load types evaluated, achieving a 7.5% reduction in the building's energy use and the highest user satisfaction score of 4.7 out of 5. Finally, we concluded this work by highlighting the system's deployment feasibility for a building-wide implementation to guide future real-world applications.

Automated summary

This paper proposes a novel IoT-based plug load management system called Plug-Mate, which reduces energy consumption and user burden through intelligent automation. Different control strategies were evaluated and the optimal balance between automation and user control was found.