Car driving safety, comfort, energy economy and battery life extension are important factors for electric vehicles. To optimize these factors, this paper proposes an economic adaptive cruise control (Eco-ACC) strategy for electric vehicles based on multi-step tree backtracking algorithm in the Q-Learning framework. First, the vehicle's longitudinal dynamics and energy storage models are established, and the control objectives are presented. Then, the control and state variables, reward and value functions are defined, and the Eco-ACC control strategy based on the multi-step tree backtracking algorithm is designed. Finally, simulations are performed, and compared with the benchmark algorithm, the proposed method achieves lower energy consumption and longer battery life.
With the continuous development of deep learning technology, various deep neural networks have been proposed to solve various problems, but the artificial design of neural network architecture requires certain professional knowledge and experience. The emergence of neural architecture search provides an automated solution for network architecture design. Current neural architecture search methods have a huge computational problem, and further research is needed to improve sample efficiency and network evaluation cost to obtain better results. In this paper, a neural architecture search method based on improved Monte Carlo Tree Search(MCTS) is proposed. The upper confidence interval (UCT) strategy of the tree is replaced by the RAVE strategy combining UCT strategy and AMAF strategy, and the absolute pruning strategy is added to better guide the search trajectory, speed up the convergence of the search tree and improve the accuracy of the results. By comparing the improved algorithm with the original tree search on the benchmark dataset, the feasibility of applying the improved algorithm to the neural network architecture search is proved, and the search process is accelerated.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)