The social economy and rail transit of China had tremendous growth over recent years, the energy consumption of transportation has increased. Aiming at the problem of energy-saving driving strategy, this paper proposes a train energy-saving driving strategy based on PPO (Proximal Policy Optimization) algorithm. By constructing a Markov decision-making process model and training parameters, this paper combines driving strategy with deep reinforcement learning algorithm. According to train running conditions and energy consumption evaluation model, considering that the train needs to follow the requirements of the timetable, this paper combines punctuality with energy consumption to make up the reward function. At last, this paper takes the parameters of actual transmission lines, from Chibibei to Changshanan of Wuhan to Guangzhou railway line for passenger traffic as example to verify the effectiveness of the method. The simulation results show that this algorithm has advantages in optimizing train traction energy consumption, it also has reference suggestions for the development of Green Transport.
Research on Optimization of Energy-Saving Driving Strategy of High-Speed Train Based on PPO
24.03.2023
1669962 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Train energy-saving speed trajectory optimization method based on dynamic programming
Europäisches Patentamt | 2024
|Europäisches Patentamt | 2023
|Europäisches Patentamt | 2020
|Minimal-Energy Driving Strategy for High-Speed Electric Train With Hybrid System Model
Online Contents | 2013
|