GCRIS

Traffic congestion and delays caused in traffic light intersections can adversely affect countries in terms of money, time, and air pollution. With the advancement of computational power as well as artificial intelligent algorithms, researchers seek novel and optimized solutions to the traffic congestion problem. Most modern traffic light systems use manually designed traffic phase plans at intersections, and although this has proven to be relatively sufficient for today's traffic management systems, implementing a smarter traffic phase selection system is deemed to be more effective. Traditional approaches rely heavily on traffic history (static information), whereas Reinforcement Learning (RL) algorithms, which offer an 'adoptable'/dynamic traffic management system, are gaining increased research interest. Despite the usefulness of these RL based deep learning techniques, they inherently suffer from training time to apply them in real-world traffic management systems. This study aims to alleviate the training time problem of deep learning-based techniques, The research brings forth a novel graph-based approach that is able to use known occupancies of roads to predict which other roads in a given network would become congested in the future. Based on the predictions obtained, we are able to dynamically set traffic light times in all intersections within a connected network, starting from roads with known occupancies, and moving along connected roads that are anticipated to be congested. Predications are done using edge-based semi-supervised graph algorithms. Conducted simulations show that our approach can yield comparable average wait time to that of deep-learning based approach in minutes, compared to the much longer training time required by the deep-learning models. Keywords: Deep Learning, Reinforcement Learning, Traffic Flow, Congestion

Yüksek Lisans Tezleri

Browse

Filters

Settings

Sort By

Results per page

Search Results