In Australia, the penetration of rooftop photovoltaic (PV) systems with storage is expected to increase in the future because of rising electricity costs, decreasing capital costs and growing concerns about climate change. Residential energy users can seize the full financial benefits of these systems by using an automated energy management system (EMS) to schedule and coordinate their energy use. An important aspect of an effective EMS is to control the battery state of charge, taking into consideration of the intermittent nature of PV generation and variability of electrical demand over a decision horizon of several days. However, this is difficult because of the computational burden associated with the currently proposed solution techniques. Given these existing shortcomings, this paper evaluates a two-stage stochastic optimisation framework for energy management of residential PV-storage systems to identify the benefits of having a longer decision horizon. That is: a simplified longer-horizon solver that uses stochastic mixed-integer linear programming (MILP) and a more detail shorter horizon solver using dynamic programming. In doing so, this paper discusses the general benefits of residential PV-storage systems coupled with an EMS.Index Terms-future grid, renewable energy sources, demand response, PV-storage systems, home energy management, stochastic mixed-integer linear programming, dynamic programming.
Dynamic programming (DP) can be used to generate the optimal schedules of a smart home energy management system (SHEMS) problem, however, it is computationally difficult because we have to loop over all the possible states, decisions and outcomes. This paper proposes a novel state-space approximate dynamic programming (SS-ADP) approach to quickly solve a SHEMS problem but with similar solutions as DP. The state-space approximations are made using a hierarchical approach, which involves clustering and machine learning. The proposed SS-ADP can generate the day-ahead value functions quickly without compromising the solution quality becasue it only loops over the necessary state-space. Our simulation results showed that the solutions from the SS-ADP approach are within 0.8% of the optimal DP solutions but saves the computational time by at least 20%. The paper also presents a fast real-time control strategy under uncertainty using the Bellman optimality condition and long short-term memory recurrent neural networks (LSTM-RNN). The Bellman equation uses the day-ahead value function from the SS-ADP and the instantaneous contribution function to make fast real-time decisions. The instantaneous contribution is calculated using the PV and load predicted using LSTM-RNN, which performs significantly better than the widely used persistence method. INDEX TERMS PV-storage systems, smart home energy management, state-space approximate dynamic programming, machine learning, long short-term memory recurrent neural networks
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.