Yuan Chen∗
Intelligent transportation, electric vehicles (EVs), path planning, charging and navigation, Atom Search Optimisation (ASO) algorithm, state transition probability
Traditional electric vehicle (EV) path selection and charging navigation methods have been unable to meet practical needs. The research aims to optimise the travel efficiency and alleviate the impact of many EVs charging simultaneously on the safe operation of the power distribution system, based on real-time traffic information from intelligent transportation systems, an optimisation model for EV path selection and charging navigation strategy is constructed to minimise user travel time, charging costs, and overall costs. Then, after introducing the state transition probability rule and combining crossover and mutation operations, an improved atom search optimisation (ASO) algorithm is built to solve the research model. The maximum recall and mean average precision of the improved ASO were 0.84 and 0.97, respectively, both of which performed the best. The numerical simulation results showed that the research model reduced user travel time by 21.95% compared with traditional methods. Its fast charging cost and conventional slow charging cost were 51.8 RMB and 9.7 RMB, respectively, both lower than traditional methods. The decision center calculates the optimal travel path after using the research method, demonstrating the feasibility and effectiveness, which can optimise the road traffic efficiency of EVs and optimise energy management.
Important Links:
Go Back
