The location of public electric vehicle charging stations (PEVCSs) has a great influence on the operational efficiency of charging stations, charging behaviours of EVs and the power quality of grids. To optimise the PEVCS locations for plug‐in electric taxis (PETs), this study proposes to utilise the multi‐agent system (MAS) and evidential reasoning (ER) approach. First, an MAS simulation framework for PET operation is proposed to dynamically simulate the PETs’ daily operation and estimate the charging demands of PETs, where a variety of agents are built to simulate not only the operation related players but also the operational environments. To accelerate the convergence rate and provide better operational strategies for PETs, a multi‐step learning is developed to make decisions for PET agents whether to find passengers or to charge under various situations. Moreover, a multi‐objective model for optimising the location of PEVCSs is developed considering the benefits of PETs and the power grid. Finally, an ER approach is applied to determine the final optimal siting considering the uncertainties of the assessor's cognition. Simulation results have demonstrated that the proposed MAS simulation framework and ER approach can effectively optimise the PEVCS locations.
The dynamic reconfiguration of active distribution networks (ADNDR) essentially belongs to a complex high-dimensional mixed-integer nonlinear stochastic optimization problem. Traditional mathematical optimization algorithms tend to encounter issues like slow computational speed and difficulties in solving large-scale models, while heuristic algorithms are prone to fall into local optima. Furthermore, few scholars in the existing research on distribution network (DN) reconfiguration have considered the graph structure information, resulting in the loss of critical topological information and limiting the effect of optimization. Therefore, this paper proposes an ADNDR approach based on the graph convolutional network deep deterministic policy gradient (GCNDDPG). Firstly, a nonlinear stochastic optimization mathematical model for the ADNDR is constructed, taking into account the uncertainty of sources and loads. Secondly, a loop-based encoding method is employed to reduce the action space and complexity of the ADNDR. Then, based on graph theory, the DN structure is transformed into a dynamic network graph model, and a GCNDDPG-based ADNDR approach is proposed for the solution. In this method, graph convolutional networks are used to extract features from the graph structure information, and the state of the DN, and the deep deterministic policy gradient is utilized to optimize the ADNDR decision-making process to achieve the safe, stable, and economic operation of the DN. Finally, the effectiveness of the proposed approach is verified on an improved IEEE 33-bus power system. The simulation results demonstrate that the method can effectively enhance the economy and stability of the DN, thus validating the effectiveness of the proposed approach.