This paper proposes a multi-agent deep graph reinforcement learning-based EV on-route charging guidance strategy, aiming at minimizing the charging cost for EV drivers in an uncertain and complex environment. First, a real-time online EV charging guidance framework with bi-timescales coupled transportation electrification is proposed. On the slow timescale, the distribution locational marginal pricing of the node where the charging station is located is solved by the power purchase cost optimization of the power distribution network. On the fast timescale, multi-agent deep reinforcement learning is used to solve real-time EV requests. Second, charging stations are considered as agents, and the potential competition for future charging demand at charging stations is considered. A multi-agent actor critic algorithm with embedded graph attention networks is proposed to optimize charging decision-making of EV drivers, which exploits the interactions between agents' observations using graph attention networks. Case studies are carried out in a practical area of Xi'an, China. We analyze the necessity of model components. The effectiveness of the proposed approach in reducing charging cost and its applicability in PV-equipped scenarios is verified. The convergence performance and scalability are verified by the comparison with SAC and MADDPG algorithms.

This article proposes the operating status prediction model at electric vehicle (EV) charging stations based on the spatiotemporal graph convolutional network (SGCN). The SGCN combines graph convolutional network (GCN) and the gated recurrent unit (GRU), alleviating the queuing time at charging stations due to the lack of information for EV users. First, an urban charging station-traffic flow model is established to portray the interrelationship between charging stations and traffic. Second, a multistep prediction model based on SGCN for operating status at charging stations is proposed to forecast the occupancy of charging stations over the next tens of minutes. The comparison case study with the forecast and actual data reveals that the mean forecast error is around 19.21% when estimating 18 min ahead. Incrementing errors are subtle even after adding random noise to the original data. Finally, the model is applied to charging guidance decisions. Our model can reduce the number of EV queuing by 60% during high charging demand. It also shortens the average charging waiting time by 4 min.

Short-Term Load Forecasting (STLF) for End-User Transformer Level (EUTL) is challenging due to the high penetration of Electric Heating Loads (EHLs), which exhibit significant uncertainty, nonlinearity, and variability. In this paper, a STLF model is proposed based on the Stacked Auto-Encoder Extreme Learning Machine (SAE-ELM) deep learning framework, which can be used to extract hidden features from the time series load data. In order to improve the capability of extracting deep and diverse features from the data and generate a useful knowledge representation structure, a novel specialized feature indices set is proposed to construct the training sample set. The sliding trend, fluctuation rate, grade of change, and smoothness of the time series are considered and quantified as elements of the training sample set. Then, deep nonlinear features are extracted by using the SAE-ELM with no iterative parameter tuning needed. To illustrate the validity of the proposed model, five numerical cases are conducted. Comparison of results shows that the proposed model improves the capability and sensitivity of dealing with load volatility and forecasting accuracy.

As a new energy vehicle, fuel cell vehicles (FCVs) have the advantages of pollution-free and zero-emission, which have attracted wide attention from all over the world. By predicting the ownership of FCVs, decision-makers can grasp the future development potential of FCVs, so that the national government can adopt corresponding policies and measures. To this end, based on analyzing the development trend of FCVs, this article proposes an FCVs ownership prediction method based on the generalized Bass model. From the perspective of technology, application, and market conditions of FCVs, this article first analyzes the development trend of FCVs in the future, which provides the basis for the establishment of the ownership prediction method and the estimation of model parameters. Then, considering the influence of levelized cost of driving (LCD) reduction and hydrogen refueling stations (HRSs) constructions, a prediction method of FCVs ownership based on the generalized Bass model is proposed, and the model parameters are estimated by Grey Verhulst model, electric vehicles data, and liquefied natural gas vehicles data. Through the proposed method, the ownership of FCVs in China from 2021 to 2070 is predicted and the results show that the ownership of FCVs in China will reach about 1.43 million in 2030 and about 10.41 million in 2040. Finally, through sensitivity analysis, this article discusses the influence of external factors such as policy, LCD, and HRSs on the market diffusion of FCVs, and puts forward corresponding suggestions.