A traffic signal optimization control method based on a Bayesian depth Q network relates to the technical field of intelligent traffic, and comprises the following steps: (1) establishing a traffic signal control model based on deep reinforcement learning: s11, defining the state of the model; s12, defining the action of the model; s13, defining a reward function of the model; s14, designing a priority Bayesian depth Q network; (2) training a multi-intersection cooperative adaptive signal timing optimization control model based on deep reinforcement learning; and (3) generating a traffic signal timing optimization control strategy and a continuous updating model. According to the method, the reinforcement learning capability of the Bayesian depth Q network is utilized, and the traffic signal control problem is optimized, so that the traffic flow efficiency is improved and the traffic jam is reduced.
基于贝叶斯深度Q网络的交通信号优化控制方法,涉及智慧交通技术领域,包括如下步骤:(1)建立基于深度强化学习的交通信号控制模型,具体包括:s11定义模型的状态;s12定义模型的动作;s13定义模型的奖励函数;s14设计优先贝叶斯深度Q网络;(2)训练基于深度强化学习的多交叉口协同自适应信号配时优化控制模型;(3)生成交通信号配时优化控制策略和持续更新模型。该方法利用贝叶斯深度Q网络的强化学习能力,针对交通信号控制问题进行优化,以提高交通流效率和减少交通拥堵。
Traffic signal optimization control method based on Bayesian depth Q network
基于贝叶斯深度Q网络的交通信号优化控制方法
29.09.2023
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Message-based complex network traffic signal optimization control method
Europäisches Patentamt | 2015
|Dynamic Network-Wide Traffic Signal Optimization
DataCite | 2015
|Dynamic network-wide traffic signal optimization
TIBKAT | 2015
|