Incorporative Relocation Team Planning and Staff Member Allocation in Electric Vehicle Sharing Systems

This paper presents a design and analyzes the performance of a relocation planner for electric vehicle sharing system, aiming at reducing management cost and enhancing service ratio by avoiding service degradation stemmed from stock imbalance. The proposed planner creates a set of relocation pairs, each of which consists of an overflow station and an underflow station for respective relocation teams. To simultaneously determine the team-byteam number of staff members and relocation pairs based on the genetic algorithm, each plan is encoded by an integer-valued vector composed of relocation pair and staff allocation parts. The relocation pair part translates individual station matching, complementarily combining overflow and underflow indices as well as including negative number separators. The staff part indicates the number of staff members for each team and thus how many identical pairs can be merged. Genetic operators are allowed only in the relocation pair part, while the fitness function gives precedence to a balanced plan. The performance measurement result, obtained by a prototype implementation, shows that our planner outperforms the reference scheme by up to 53.0 % for given parameter setting.