Open AccessTraffic Signal Control Model on Isolated Intersection Using Reinforcement Learning: A Case Study on Algiers City, Algeria
Author(s) -
Fares Bouriachi,
Hicham Zatla,
Bilal Tolbi,
Koceila Becha,
Allaeddine Ghermoul
Publication year - 2021
Publication title -
revue d'intelligence artificielle
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.146
H-Index - 14
eISSN - 1958-5748
pISSN - 0992-499X
DOI - 10.18280/ria.350508
Subject(s) - reinforcement learning , intersection (aeronautics) , traffic congestion , traffic signal , computer science , control (management) , traffic congestion reconstruction with kerner's three phase theory , transport engineering , signal (programming language) , real time computing , engineering , artificial intelligence , programming language
Traffic jams and congestion in our cities are a major problem because of the huge increase in the number of cars on the road. To remedy this problem, several control methods are proposed to prevent or reduce traffic congestion based on traffic lights. There are few works using reinforcement learning technique for traffic light control and recent studies have shown promising results. However, existing works have not yet tested the methods on the real-world traffic data and they only focus on studying the rewards without interpreting the policies. In this paper, we proposed a reinforcement learning algorithm to address the traffic signal control problem in real multi-phases isolated intersection. A case study based on Algiers city is conducted the simulation results from the different scenarios show that our proposed scheme reduces the total travel time of the vehicles compared to those obtained with traffic-adaptive control.