C-MP: A decentralized adaptive-coordinated traffic signal control using the Max Pressure framework
Coordinated traffic signals seek to provide uninterrupted flow through a series of closely spaced intersections, typically using pre-defined fixed signal timings and offsets. Adaptive traffic signals dynamically change signal timings based on observed traffic conditions in a way that might disrupt coordinated movements, particularly when these decisions are made independently at each intersection. To alleviate this issue, this paper introduces a novel Max Pressure-based traffic signal framework that can provide coordination even under decentralized decision-making. The proposed Coordinated Max Pressure (C-MP) algorithm uses the space mean speeds of vehicles to explicitly detect freely flowing platoons of vehicles and prioritizes their movement along a corridor. Specifically, upstream platoons are detected and their weight in the MP framework increased to provide priority, while downstream platoons are detected and their weight reduced to ensure smooth traffic flow across corridors. The study analytically proves that C-MP maintains the desirable maximum stability property, while micro-simulation analyses conducted on an arterial network demonstrate its ability to achieve a larger stable region compared to benchmark MP control policies. Simulation results also reveal that the proposed control algorithm can effectively coordinate traffic signals in both directions along an arterial without explicitly assigned offsets or constraints. The results also reveal C-MP's superiority to benchmark coordination strategies in reducing travel time, and fuel consumption both at the corridor level and the network level by balancing the negative impact imparted to vehicles in the minor direction.
Code (0)
등록된 구현이 없습니다.
Tasks
Traffic Signal ControlMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Integrating Transit Signal Priority into Multi-Agent Reinforcement Learning based Traffic Signal Control
This study integrates Transit Signal Priority (TSP) into multi-agent reinforcement learning (MARL) based traffic signal control. The first part of the study develops adaptive signal control based on MARL for a pair of co…
Multi-agent Reinforcement LearningTraffic Signal ControlDistributed Traffic Signal Control via Coordinated Maximum Pressure-plus-Penalty
This paper develops an adaptive traffic control policy inspired by Maximum Pressure (MP) while imposing coordination across intersections. The proposed Coordinated Maximum Pressure-plus-Penalty (CMPP) control policy feat…
Computational EfficiencyDistributed OptimizationTraffic Signal ControlTraffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies
Traffic congestion in urban areas is a significant problem, leading to prolonged travel times, reduced efficiency, and increased environmental concerns. Effective traffic signal control (TSC) is a key strategy for reduci…
Traffic Signal ControlConnected Vehicle Supported Adaptive Traffic Control for Near-congested Condition in a Mixed Traffic Stream
Connected Vehicles (CVs) have the potential to significantly increase the safety, mobility, and environmental benefits of transportation applications. In this research, we have developed a real time adaptive traffic sign…
Traffic Signal ControlSystematic Analyses of Reinforcement Learning Controllers in Signalized Urban Corridors
In this work, we extend our systematic capacity region perspective to multi-junction traffic networks, focussing on the special case of an urban corridor network. In particular, we train and evaluate centralized, fully d…
Reinforcement Learning