Search

• A safe reinforcement learning method for smart home energy management is proposed. • The operation of the components in a multi-energy smart home is modeled as a CMDP. • The approach minimizes total energy cost and avoids constraints violations. This paper proposes a data-driven approach for multi-energy management of a smart home with different types of appliances, including battery energy storage system (BESS), thermal energy storage system (TES), micro combined heat and power system (mCHP), electrical heat pump (EHP), rooftop photovoltaics (PV) and electrical vehicle (EV). Firstly, home energy management (HEM) is formulated as a cost minimization problem with hard constraints to optimize energy generation, storage, and consumption. Secondly, this paper proposes a safe reinforcement learning (SRL) approach with Primal-Dual Optimization (PDO) policy search-based algorithm to solve the HEM problem. Unlike existing DRL methods, the proposed approach learns to minimize costs from accumulated cost functions and automatically tunes the cost function coefficients to achieve zero constraints violation. Besides, a dynamic electricity price forecasting model based on CNN-LSTM neural network is designed to deal with the uncertainties in future prices. To verify the performance of the proposed HEM method, simulations are conducted using Singapore wholesale electricity price data. Numerical results demonstrate that the proposed method has a better ability to minimize energy costs and satisfy constraints compared to existing methods. [ABSTRACT FROM AUTHOR]

Accurate solar photovoltaic (PV) generation forecast is critical to the reliable and economic operation of a modern power system. In practice, due to various faulty issues in the sensor, communication, or database system, the historical and online measurement data may not be always complete, and the missing data could dramatically degrade the forecasting model's accuracy. To solve this problem, this paper proposes an integrated missing-data tolerant model for probabilistic PV power generation forecasting. Taking historical PV generations as input, this model is based on a recursive long short-term memory network (Rec-LSTM), which can provide multi-step ahead forecasting of the probability distribution of PV generation. The unobserved input data will be imputed recursively based on the model output at the previous time step. During the training process, the imputations and forecasting values are iteratively updated by the negative log-likelihood loss function. As a salient advantage, this method can deal with data missing scenarios at both offline and online stages. Numerical experiments are conducted on two one-year datasets from Australia and Singapore, respectively. Probabilistic forecasting for both large-scale and small-scale building-level PV power generation is tested at the time resolution of 15 mins. Testing results show the proposed method can achieve superior probabilistic prediction accuracy as well as strong robustness under various data missing scenarios, compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]