Energy-saving optimization method, device and equipment for urban rail transit train and storage medium

Abstract

The invention discloses an urban rail transit train energy-saving optimization method, device and equipment and a storage medium, and the method comprises the steps: S10, obtaining state information and a reward value in a train operation environment at a current moment, the reward function comprises a first reward function in the DDPG model and a second reward function in which the work applied by the traction force in the train running process is combined with the running punctuality; s20, based on the state information and the reward value in the train operation environment, selecting an operation action and issuing the operation action to the train so as to enable the train to run according to the operation action at the next moment; and S30, determining the next moment as the current moment, and repeatedly executing the steps S10-S20. According to the method, every time the train executes the running action, the environment can immediately feed back one piece of state information and one reward value to guide the subsequent operation sequence so as to update and optimize the running strategy, and finally a convergent ideal train running strategy is obtained, so that the purpose of saving energy consumption is achieved.

Description

technical field [0001] The invention belongs to the technical field of rail transit, and in particular relates to an energy-saving optimization method, device, equipment and storage medium for urban rail transit trains. Background technique [0002] The term Reinforcement Learning comes from behavioral psychology, which means that creatures more frequently implement behavior strategies that are beneficial to themselves in order to seek advantages and avoid disadvantages. Reinforcement learning is a specific type of machine learning problem. In a reinforcement learning system, the agent can observe the environment and act according to the observation. After the action, the agent can obtain a reward and continuously improve the action decision through the reward. . The process of reinforcement learning is the process in which the agent obtains the maximum reward by interacting with the environment. [0003] In today's era, the urban rail transit system represented by the sub...

AI Technical Summary

Problems solved by technology

However, due to the large total traffic volume of the rail transit system, its energy consumption problem has been to be solved

However, this method uses the Q-Learning algorithm. Since the parameters of the Q network are frequently updated to update the gradient, they are also used to calculate the gradient of the Q network and the policy network, so the learning process is very unstable.

Images