To improve the operating efficiency and economic benefits, this article proposes a modified rainbow-based deep reinforcement learning (DRL) strategy to realize the charging station (CS) optimal scheduling. As the charging process is a real-time matching between electric vehicles ‘(EVs) charging demand and CS equipment resources, the CS charging scheduling problem is duly formulated as a finite Markov decision process (FMDP). Considering the multi-stakeholder interaction among EVs, CSs, and distribution networks (DNs), a comprehensive information perception model was constructed to extract the environmental state required by the agent. According to the random behavior characteristics of the EV charging arrival and departure times, the startup of the charging pile control module was regarded as the agent’s action space. To tackle this issue, the modified rainbow approach was utilized to develop a time-scale-based CS scheme to compensate for the resource requirements mismatch on the energy scale. Case studies were conducted within a CS integrated with the photovoltaic and energy storage system. The results reveal that the proposed method effectively reduces the CS operating cost and improves the new energy consumption.

The rapid development of electric vehicles (EVs) has posed challenges to power grids and transportation networks. Accurately capturing the usage patterns of EV users is a prerequisite for EVs’ interaction with electrified transportation networks. Thus, this paper proposes a full data chain (FDC) driven model to mine EVs’ comprehensive characteristics. By collecting the data of 150 private electric vehicles (PREVs), 100 commercial electric vehicles (CEVs), and 50 official electric vehicles (OEVs) in Chongqing, China, the driving characteristics are firstly mined by the adoption of origin-destination (OD) distribution and driving portrait. Moreover, the charging characteristics are extracted based on the state recognition for data chains. Then, vehicle usage characteristics of different types of users are comprehensively described based on the density-based spatial clustering of applications with noise (DBSCAN). Finally, the results of EV user characteristics are analyzed, and the effectiveness of the proposed model is verified by regional charging load analysis and urban road traffic flow comparison. The findings provide a data source and user behavior model for the planning, operation, and control of power grids and transportation networks.

To improve the decision-making level of active distribution networks (ADNs), this paper proposes a novel framework for coordinated scheduling based on the long short-term memory network (LSTM) with deep reinforcement learning (DRL). Considering the interaction characteristics of ADNs with distributed energy resources (DERs), the scheduling objective is constructed to reduce the operation cost and optimize the voltage distribution. To tackle this problem, a LSTM module is employed to perform feature extraction on the ADN environment, which can realize the recognition and learning of massive temporal structure data. The concerned ADN real-time scheduling model is duly formulated as a finite Markov decision process (FMDP). Moreover, a modified deep deterministic policy gradient (DDPG) algorithm is proposed to solve the complex decision-making problem. Numerous experimental results within a modified IEEE 33-bus system demonstrate the validity and superiority of the proposed method.