Intelligent traffic signal controller for heterogeneous traffic using reinforcement learning
A traffic signal controller is an essential part of a signalized intersection to alleviate congestion and pollution by ensuring safety. However, the available research solutions are focused on homogeneous traffic scenarios, whereas heterogeneous traffic is the reality in most countries. Hence, a tra...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Green Energy and Intelligent Transportation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2773153723000609 |
| _version_ | 1827630266822164480 |
|---|---|
| author | Savithramma R M R. Sumathi |
| author_facet | Savithramma R M R. Sumathi |
| author_sort | Savithramma R M |
| collection | DOAJ |
| description | A traffic signal controller is an essential part of a signalized intersection to alleviate congestion and pollution by ensuring safety. However, the available research solutions are focused on homogeneous traffic scenarios, whereas heterogeneous traffic is the reality in most countries. Hence, a traffic signal control scheme suitable for heterogeneous traffic conditions is proposed in the current study using Reinforcement Learning. A novel reward function with an objective to reduce the traffic residual is defined and a combination of exploration and exploitation optimal policy is applied which made the system learn quickly. The proposed scheme can choose the appropriate phase sequence with optimal signal lengths based on traffic demand on each approaching road. The simulation results proved that the proposed model is well-suited for heterogeneous traffic conditions and its performance against the actuated traffic signal controller is significant in reducing the green time wastage and mean waiting time at the intersection. |
| first_indexed | 2024-03-09T14:04:26Z |
| format | Article |
| id | doaj.art-ffbb87d851744a49b6caded715ab9a49 |
| institution | Directory Open Access Journal |
| issn | 2773-1537 |
| language | English |
| last_indexed | 2024-03-09T14:04:26Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Green Energy and Intelligent Transportation |
| spelling | doaj.art-ffbb87d851744a49b6caded715ab9a492023-11-30T05:12:14ZengElsevierGreen Energy and Intelligent Transportation2773-15372023-12-0126100124Intelligent traffic signal controller for heterogeneous traffic using reinforcement learningSavithramma R M0R. Sumathi1Corresponding author.; Department of Computer Science and Engineering, Siddaganga Institute of Technology, Tumakuru, Karnataka, IndiaDepartment of Computer Science and Engineering, Siddaganga Institute of Technology, Tumakuru, Karnataka, IndiaA traffic signal controller is an essential part of a signalized intersection to alleviate congestion and pollution by ensuring safety. However, the available research solutions are focused on homogeneous traffic scenarios, whereas heterogeneous traffic is the reality in most countries. Hence, a traffic signal control scheme suitable for heterogeneous traffic conditions is proposed in the current study using Reinforcement Learning. A novel reward function with an objective to reduce the traffic residual is defined and a combination of exploration and exploitation optimal policy is applied which made the system learn quickly. The proposed scheme can choose the appropriate phase sequence with optimal signal lengths based on traffic demand on each approaching road. The simulation results proved that the proposed model is well-suited for heterogeneous traffic conditions and its performance against the actuated traffic signal controller is significant in reducing the green time wastage and mean waiting time at the intersection.http://www.sciencedirect.com/science/article/pii/S2773153723000609Machine learningReinforcement learningMulti-agentSignalized intersectionCongestion optimizationTraffic light control |
| spellingShingle | Savithramma R M R. Sumathi Intelligent traffic signal controller for heterogeneous traffic using reinforcement learning Green Energy and Intelligent Transportation Machine learning Reinforcement learning Multi-agent Signalized intersection Congestion optimization Traffic light control |
| title | Intelligent traffic signal controller for heterogeneous traffic using reinforcement learning |
| title_full | Intelligent traffic signal controller for heterogeneous traffic using reinforcement learning |
| title_fullStr | Intelligent traffic signal controller for heterogeneous traffic using reinforcement learning |
| title_full_unstemmed | Intelligent traffic signal controller for heterogeneous traffic using reinforcement learning |
| title_short | Intelligent traffic signal controller for heterogeneous traffic using reinforcement learning |
| title_sort | intelligent traffic signal controller for heterogeneous traffic using reinforcement learning |
| topic | Machine learning Reinforcement learning Multi-agent Signalized intersection Congestion optimization Traffic light control |
| url | http://www.sciencedirect.com/science/article/pii/S2773153723000609 |
| work_keys_str_mv | AT savithrammarm intelligenttrafficsignalcontrollerforheterogeneoustrafficusingreinforcementlearning AT rsumathi intelligenttrafficsignalcontrollerforheterogeneoustrafficusingreinforcementlearning |