Reinforcement learning based energy management strategy has been an active research subject in the past few years. Different from the baseline reward function (BRF), the work proposes and investigates a multi-stage reward mechanism (MSRM) that scores the agent’s step and final performance during training and returns it to the agent in real time as a reward. MSRM will also improve the agent’s training through expert intervention which aims to prevent the agent from being trapped in sub-optimal strategies. The energy management performance considered by MSRM-based algorithm includes the energy balance, economic cost, and reliability. The reward function is assessed in conjunction with two deep reinforcement learning algorithms: double deep Q-learning network (DDQN) and policy gradient (PG). Upon benchmarking with BRF, the numerical simulation shows that MSRM tends to improve the convergence characteristic, reduce the explained variance, and reduce the tendency of the agent being trapped in suboptimal strategies. In addition, the methods have been assessed with MPC-based energy management strategies in terms of relative cost, self-balancing rate, and computational time. The assessment concludes that, in the given context, PG-MSRM has the best overall performance.

Mid-term load forecasting (MTLF) is of great significance for power system planning, operation, and power trading. However, the mid-term electrical load is affected by the coupling of multiple factors and demonstrates complex characteristics, which leads to low prediction accuracy in MTLF. Furthermore, MTLF is faced with the ``curse of dimensionality'' problem due to a large number of variables. This article proposes an MTLF method based on manifold learning, which can extract the underlying factors of load variations to help improve the accuracy of MTLF and significantly reduce the calculation. Unlike linear dimensionality reduction methods, manifold learning has better nonlinear feature extraction ability and is more suitable for load data with nonlinear characteristics. Furthermore, long short-term memory (LSTM) neural networks are used to establish forecasting models in the low-dimensional space obtained by manifold learning. The proposed MTLF method is tested on independent system operator (ISO) New England datasets, and load forecasting in 24, 168, and 720 h ahead is carried out. The numerical results validate that the proposed method has higher prediction accuracy than many mature methods in the mid-term time scale.

In order to manage electric vehicles (EVs) connected to charging grids, this paper presents an orderly charging approach based on the EVs’ optimal time-of-use pricing (OTOUP) demand response. Firstly, the Monte Carlo approach is employed to anticipate charging power by developing a probability distribution model of the charging behavior of EVs. Secondly, a scientific classification of the load period is performed using the fuzzy clustering approach. Then, a matrix of demand price elasticity is developed to measure the link between EV charging demand and charging price. Finally, the charging scheme is optimized by an adaptive genetic algorithm from the distribution network and EV user viewpoints. This paper describes how to implement the method presented in this paper in an IEEE-33-bus distribution network. The simulation results reveal that, when compared to fixed price and common time-of-use pricing (CTOUP), the OTOUP charging strategy bears a stronger impact on reducing peak–valley disparities, boosting operating voltage, and decreasing charging cost. Additionally, this paper studies the effect of varied degrees of responsiveness on charging strategies for EVs. The data imply that increased responsiveness enhances the likelihood of new load peak, and that additional countermeasures are required.