Abstract:

Electric vehicles (EV) are an alternative to fossil-fuel vehicles. This work addresses the problem of optimizing the placement of new infrastructures for EV charging. The electric vehicle is gradually being introduced in cities. The impact of this introduction is less due, among other reasons, to the lack of charging infrastructure necessary to satisfy the demand. In today's cities there is no adequate infrastructure and it is necessary to have action plans that allow an easy deployment of a network of EV charging points in current cities. These action plans should try to place the EV charging stations in the most appropriate places for optimizing their use. Accordingly, this study proposes an agent-oriented technique for analysing the various configurations of potential charging station locations for electric vehicles in a given city. In order to estimate the ideal configurations, the suggested multi-agent system considers data from a range of sources, such as social network activity and mobility information. The proposed approach employs a genetic algorithm (GA) that tries to optimize the possible configurations of the charging infrastructure. Additionally, a new crossover method for the GA is proposed considering this context. A new crossover mechanism is also included in the suggested algorithm, which is specifically developed for geolocated domains.