Residential Energy Management for Renewable Energy Systems Incorporating Data-Driven Unravelling of User Behavior

Abstract

The penetration of distributed energy resources (DERs) such as photovoltaic (PV) at the residential level has increased rapidly over the past year. It will inevitably induce a paradigm shift in end-user and operations of local energy markets. The energy community with high integration of DERs initiative allows its users to manage their generation (for prosumers) and consumption more efficiently, resulting in various economic, social, and environmental benefits. Specifically, the local energy communities and their members can legally engage in energy generation, distribution, supply, consumption, storage, and sharing to increase levels of autonomy from the power grid, advance energy efficiency, reduce energy costs, and decrease carbon emissions. Reducing energy consumption costs is difficult for residential energy management without understanding the users' preferences. The advanced measurement and communication technologies provide opportunities for individual consumers/prosumers and local energy communities to adopt a more active role in renewable-rich smart grids. Non-intrusive load monitoring (NILM) monitors the load activities from a single point source, such as a smart meter, based on the assumption that different appliances have different power consumption levels and features. NILM can extract the users' load consumption from the smart meter to support the development of the smart grid for better energy management and demand response (DR). Yet to date, how to design residential energy management, including home energy management systems (HEMS) and community energy management systems (CEMS), with an understanding of user preferences and willingness to participate in energy management, is still far from being fully investigated. This thesis aims to develop methodologies for a resident energy management system for renewable energy systems (RES) incorporating data-driven unravelling of the user's energy consumption behaviour.