We propose a new architecture of truck-based mobile energy couriers (MEC) for power distribution networks with high penetration of renewable energy sources (RES). Each MEC is a truck equipped with high-density inverters, converters, capacitor banks, and energy storage devices. The MEC platform can improve the flexibility, resilience, and RES hosting capability of a distribution grid through spatial-temporal energy reallocation based on the stochastic behaviors of RES and loads. The employment of MEC necessitates the development of complex scheduling and control schemes that can adaptively cope with the dynamic natures of both the power grid and the transportation network. The problem is formulated as a non-convex optimization problem to minimize the total generation cost, subject to the various constraints imposed by conventional and renewable energy sources, energy storage, and transportation networks, etc. The problem is solved by combining optimal power flow (OPF) with deep reinforcement learning (DRL) under the framework of deep deterministic policy gradient (DDPG). Simulation results demonstrate that the proposed MEC platform with DDPG can achieve significant cost reduction compared to conventional systems with static energy storage.

A new online scheduling algorithm is proposed for photovoltaic (PV) systems with battery-assisted energy storage systems (BESS). The stochastic nature of renewable energy sources necessitates the employment of BESS to balance energy supplies and demands under uncertain weather conditions. The proposed online scheduling algorithm aims at minimizing the overall energy cost by performing actions such as load shifting and peak shaving through carefully scheduled BESS charging/discharging activities. The scheduling algorithm is developed by using deep deterministic policy gradient (DDPG), a deep reinforcement learning (DRL) algorithm that can deal with continuous state and action spaces. One of the main contributions of this work is a new DDPG reward function, which is designed based on the unique behaviors of energy systems. The new reward function can guide the scheduler to learn the appropriate behaviors of load shifting and peak shaving through a balanced process of exploration and exploitation. The new scheduling algorithm is tested through case studies using real world data, and the results indicate that it outperforms existing algorithms such as Deep Q-learning. The online algorithm can efficiently learn the behaviors of optimum non-casual off-line algorithms.