Traffic signal control optimization under severe incident conditions using Genetic Algorithm
원문 초록
Traffic control optimization is a challenging task for various traffic centres in the world and majority of approaches focus only on applying adaptive methods under normal (recurrent) traffic conditions. But optimizing the control plans when severe incidents occur still remains a hard topic to address, especially if a high number of lanes or entire intersections are affected. This paper aims at tackling this problem and presents a novel methodology for optimizing the traffic signal timings in signalized urban intersections, under non-recurrent traffic incidents. The approach relies on deploying genetic algorithms (GA) by considering the phase durations as decision variables and the objective function to minimize as the total travel time in the network. Firstly, we develop the GA algorithm on a signalized testbed network under recurrent traffic conditions, with the purpose of fine-tuning the algorithm for crossover, mutation, fitness calculation, and obtain the optimal phase durations. Secondly, we apply the optimal signal timings previously found under severe incidents affecting the traffic flow in the network but without any further optimization. Lastly, we further apply the GA optimization under incident conditions and show that our approach improved the total travel time by almost 40.76%.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Joint Pedestrian and Vehicle Traffic Optimization in Urban Environments using Reinforcement Learning
A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control
Generalized Phase Pressure Control Enhanced Reinforcement Learning for Traffic Signal Control
A Parallel Hybrid Action Space Reinforcement Learning Model for Real-world Adaptive Traffic Signal Control
CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
MacLight: Multi-scene Aggregation Convolutional Learning for Traffic Signal Control
토론
이 논문과 연결된 포럼 글이 아직 없습니다.