An efficient integration of the genetic algorithm and the reinforcement learning for optimal deployment of the wireless charging electric tram system

To solve the two main issues such as long charging down time and expensive battery price of the electric vehicle systems, lots of researchers have studied about advanced charging and battery technology. In same time, the new electric vehicle system which applying the wireless charging technology is also regarded as alternative means of transportation because it can reduce both the long charging down time and the battery capacity. It is called as the wireless charging electric vehicle system and it can be supplied the electricity wirelessly from the wireless charging infrastructure buried under the road. In the similar reason, the wireless charging electric tram system is received lots of interests as the alternative mass transportation in urban and suburb area. To derive the optimal decision-making elements such as the required minimum battery capacity and the allocation of the wireless charging infrastructure, which have a trade-off relationship, a mathematical model is developed. In addition, the genetic algorithm integrated with the reinforcement learning are proposed to generate an optimal solution. By assuming the several integration situations of them, an efficient integration level of the genetic algorithm and the reinforcement learning are examined.