The invention discloses a flexible bus dynamic scheduling method considering a mixed request and fairness, and the method comprises the following steps: building a Markov decision process model based on a rolling time domain framework, and explaining a flexible bus dynamic scheduling problem considering the mixed request and fairness through the Markov decision process model; a Markov decision process model is used for designing a temporary request rejection mechanism, a prediction error correction mechanism and an overdue compensation mechanism, and the problems occurring in flexible bus dynamic scheduling are solved; determining the cost of flexible bus dynamic scheduling, establishing an objective function of a Markov decision process model, and setting constraint conditions of the Markov decision process model; core elements are defined based on multi-agent reinforcement learning, a novel multi-agent reinforcement learning framework is designed, and a flexible bus dynamic scheduling problem is solved. The method has remarkable advantages in the aspects of reducing the operation cost, improving the fairness of passengers and improving the service quality, has good solving performance, and has a relatively strong practical application prospect.
本发明公开了一种考虑混合请求以及公平性的灵活公交动态调度方法,包括以下步骤:基于滚动时域框架建立马尔可夫决策过程模型,通过马尔科夫决策过程模型解释考虑混合请求及公平性的灵活公交动态调度问题;马尔科夫决策过程模型设计临时请求拒绝机制、预测误差修正机制和超期补偿机制,解决灵活公交动态调度中出现的问题;确定灵活公交动态调度的成本,建立马尔科夫决策过程模型的目标函数,设置马尔科夫决策过程模型的约束条件;基于多智能体强化学习定义核心要素,设计新型多智能体强化学习框架,求解灵活公交动态调度问题。本发明在降低运营成本、改善乘客公平性和提高服务质量方面具有显著优势,具有良好的求解性能,具备较强的实际应用前景。
Flexible bus dynamic scheduling method considering mixed requests and fairness
考虑混合请求以及公平性的灵活公交动态调度方法
2024-10-01
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
A Dynamic Requests Scheduling Model Based on Prediction in Multi-core Web Server
British Library Conference Proceedings | 2014
|Pure electric public transport network planning method considering fairness
European Patent Office | 2024
|