Optimization algorithm analysis of EV waste battery recycling logistics based on neural network

It is noteworthy today that the creation and popularization of new energy has piqued the world's interest. As a result, new energy electric cars are liked and acknowledged by most customers as a representation of the development and use of new energy. The advancement of electric vehicles (EVs) has important implications for the sustainable use of energy resources. As the number of new energy EVs grows, so does the need for charging stations for these vehicles. Maximum simplification of charging station distribution may successfully satisfy the charging demands of EVs. As a result, determining the appropriate arrangement of EV charging stations has become an essential study issue. This paper proposed a novel algorithm for EV charging station optimization based on a neural network. The main idea is to optimize the cost of charging cost and the user's budget. Then, considering the target planning region of the charging station, the historical data is deployed to predict the time distribution of EVs based on the backpropagation neural network algorithm. Finally, the performance of swarm optimization is improved through the dynamic probability mutation method. Simulation results show that the proposed algorithm has better performance than existing algorithms in terms of global economic cost and low-power and high-power charging station's spatial location.