Efficiency-oriented vehicle relocation of shared autonomous electric fleet in station-based car-sharing system

Long waiting delays for users and significant imbalances in vehicle distribution are bothering traditional station-based one-way electric car-sharing system operators.To address the problems above,a“demand forecast-station status judgement-vehicle relocation”multistage dynamic relocation algorithm based on the automatic formation cruising technology was proposed in this study.In stage one,a novel trip demand forecast model based on the long short-term memory network was established to predict users'car-pickup and car-return order volumes at each station.In stage two,a dynamic threshold interval was determined by combining the forecast results with the actual vehicle distribution among stations to evaluate the status of each station.Then vehicle-surplus,vehicleinsufficient,vehicle-normal stations,and the number of surplus or insufficient vehicles for each station were counted.In stage three,setting driving mileage and carbon emission as the optimization objectives,an integer linear programming mathematical model was constructed and the optimal vehicle relocation scheme was obtained by the commercial solver Gurobi.Setting 43 stations and 187 vehicles in Jiading District,Shanghai,China,as a case study,results showed that rapid vehicle rebalancing among stations with minimum carbon emissions could be realized within 15 min and the users’car-pickup and car-return demands could be fully satisfied without any refusal.

Distributed Power Control Considering Different Behavioural Responses of Electric Vehicle Drivers in Photovoltaic Charging Station

A distributed energy management in a photovoltaic charging station(PV-CS) is proposed on the basis of different behavioural responses of electric vehicle(EV) drivers. On the basis of the provider or the consumer of the power, charging station and EVs have been modeled as independent players with different preferences. Because of the selfish behaviour of the individuals and their hierarchies, the power distribution problem is modeled as a noncooperative Stackelberg game. Moreover, Karush-Kuhn-Tucker(KKT) conditions and the most socially stable equilibrium are adopted to solve the problem in hand. The consensus network, a learning-based algorithm, is utilized to let the EVs communicate and update their own charging power in a distributed fashion. Simulation analysis is supported to show the static and dynamic responses as well as the effectiveness and workability of the proposed charging power management. For the sake of showing the responses of EV drivers, different behavioural responses of EVs’ drivers to the discount on the charging price offered by the station are introduced. The simulation results show the effectiveness of the proposed energy management.

Exploring best‑matched embedding model and classifier for charging‑pile fault diagnosis

The continuous increase of electric vehicles is being facilitating the large-scale distributed charging-pile deployment.It is crucial to guarantee normal operation of charging piles,resulting in the importance of diagnosing charging-pile faults.The existing fault-diagnosis approaches were based on physical fault data like mechanical log data and sensor data streams.However,there are other types of fault data,which cannot be used for diagnosis by these existing approaches.This paper aims to fill this gap and consider 8 types of fault data for diagnosing,at least including physical installation error fault,charging-pile mechanical fault,charging-pile program fault,user personal fault,signal fault(offline),pile compatibility fault,charging platform fault,and other faults.We aim to find out how to combine existing feature-extraction and machine learning techniques to make the better diagnosis by conducting experiments on realistic dataset.4 word embedding models are investigated for feature extraction of fault data,including N-gram,GloVe,Word2vec,and BERT.Moreover,we classify the word embedding results using 10 machine learning classifiers,including Random Forest(RF),Support Vector Machine,K-Nearest Neighbor,Multilayer Perceptron,Recurrent Neural Network,AdaBoost,Gradient Boosted Decision Tree,Decision Tree,Extra Tree,and VOTE.Compared with original fault record dataset,we utilize paraphrasing-based data augmentation method to improve the classification accuracy up to 10.40%.Our extensive experiment results reveal that RF classifier combining the GloVe embedding model achieves the best accuracy with acceptable training time.In addition,we discuss the interpretability of RF and GloVe.

Novel Planning Approach for Fast-charging Station in Integrated System

A promising way to boost popularity of electric vehicles(EVs)is to properly layout fast charging stations(FCSs)by jointly considering interactions among EV drivers,power systems and traffic network constraints.This paper proposes a novel sensitivity analysis-based FCS planning approach,which considers the voltage sensitivity of each sub-network in the distribution network and charging service availability for EV drivers in the transportation network.In addition,energy storage systems are optimally installed to provide voltage regulation service and enhance charging capacity.Simulation tests conducted on two distribution network and transportation network coupled systems validate the efficacy of the proposed approach.Moreover,comparison studies demonstrate the proposed approach outperforms a Voronoi graph and particle swarm optimization combined planning approach in terms of much higher computation efficiency.