Bayesian Network Based Evidential Reasoning for EV Charging Navigation Considering Dynamic Multiple Attributes
Year: 2025
Type: article
Abstract: ABSTRACT As the number of electric vehicles (EVs) gradually increases, short range and lack of charging places make it necessary for EV users to reasonably arrange their travel routes and choose charging stations (CSs) during the journey. This work first models the EV charging path schedule problem as a multi‐objective optimization problem where the objective functions include the minimum mileage, travel time and total cost. As the alternatives of the charging navigation is finite and known, solving the multi‐objective optimization problem can be transformed into solving the multi‐attribute decision problem. Therefore, a Bayesian network based evidential reasoning (ER) algorithm (BNER), is proposed to solve the optimal EV charging navigation problem considering dynamic multiple attributes. The Bayesian network is used to construct an indicator which keeps EV users away from road intersections where congestion is forming, then the indicator will be used to aid path decision making by the ER algorithm. As a kind of multiple attributes decision making algorithm, the BNER will output a relatively satisfactory path through repeated on‐line single step decision in time‐varying road conditions. Finally, two simulation cases are conducted to prove the effectiveness of the proposed algorithm, with comparisons to other existing navigation methods.
Source: IET Renewable Power Generation
DOI: 10.1049/rpg2.70083
Authors: Jie‐Hui Zheng, Zhiqiang Cao, Zhigang Li, Qing‐Hua Wu
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,500
Awards: G4796731971, G5682050958
OpenAlex ID: W4412361563