Adaptive signal control for bus service reliability with connected vehicle technology via reinforcement learning

2021 ◽  
Vol 129 ◽  
pp. 103264
Author(s):  
Andy H.F. Chow ◽  
Z.C. Su ◽  
E.M. Liang ◽  
R.X. Zhong
Keyword(s):  
Reinforcement Learning ◽  
Signal Control ◽  
Service Reliability ◽  
Connected Vehicle ◽  
Adaptive Signal Control ◽  
Connected Vehicle Technology ◽  
Vehicle Technology ◽  
Bus Service ◽  
Adaptive Signal

Adaptive Coordination Based on Connected Vehicle Technology

2017 ◽  
Vol 2619 (1) ◽  
pp. 1-12 ◽  
Author(s):  
Byungho Beak ◽  
K. Larry Head ◽  
Yiheng Feng
Keyword(s):  
Mixed Integer ◽  
Signal Control ◽  
Connected Vehicle ◽  
Average Delay ◽  
Mixed Integer Linear Program ◽  
Adaptive Signal Control ◽  
Connected Vehicle Technology ◽  
Vehicle Technology ◽  
Adaptive Control Algorithm ◽  
Adaptive Signal

This paper presents a methodology that integrates coordination with adaptive signal control in a connected vehicle environment. The model consists of two levels of optimization. At the intersection level, an adaptive control algorithm allocates the optimal green time to each phase in real time by using dynamic programming that considers coordination constraints. At the corridor level, a mixed-integer linear program is formulated on the basis of data from the intersection level to optimize offsets along the corridor. After the corridor-level algorithm solves the optimization problem, the optimized offsets are sent to the intersection-level algorithm to update the coordination constraints. The model was compared with actuated–coordinated signal control by means of Vissim simulation. The results indicate that the model can reduce average delay and average number of stops for both coordinated routes and the entire network.

Real-Time Detector-Free Adaptive Signal Control with Low Penetration of Connected Vehicles

2018 ◽  
Vol 2672 (18) ◽  
pp. 35-44 ◽  
Author(s):  
Yiheng Feng ◽  
Jianfeng Zheng ◽  
Henry X. Liu
Keyword(s):  
Real Time ◽  
Traffic Control ◽  
Penetration Rate ◽  
Traffic Volume ◽  
Signal Control ◽  
Connected Vehicle ◽  
Estimation Model ◽  
Loop Detectors ◽  
Adaptive Signal Control ◽  
Adaptive Signal

Most of the existing connected vehicle (CV)-based traffic control models require a critical penetration rate. If the critical penetration rate cannot be reached, then data from traditional sources (e.g., loop detectors) need to be added to improve the performance. However, it can be expected that over the next 10 years or longer, the CV penetration will remain at a low level. This paper presents a real-time detector-free adaptive signal control with low penetration of CVs ([Formula: see text]10%). A probabilistic delay estimation model is proposed, which only requires a few critical CV trajectories. An adaptive signal control algorithm based on dynamic programming is implemented utilizing estimated delay to calculate the performance function. If no CV is observed during one signal cycle, historical traffic volume is used to generate signal timing plans. The proposed model is evaluated at a real-world intersection in VISSIM with different demand levels and CV penetration rates. Results show that the new model outperforms well-tuned actuated control regarding delay reduction, in all scenarios under only 10% penetrate rate. The results also suggest that the accuracy of historical traffic volume plays an important role in the performance of the algorithm.

Connected Vehicle–Based Adaptive Signal Control and Applications

2016 ◽  
Vol 2558 (1) ◽  
pp. 11-19 ◽  
Author(s):  
Yiheng Feng ◽  
Mehdi Zamanipour ◽  
K. Larry Head ◽  
Shayan Khoshmagham
Keyword(s):  
Signal Control ◽  
Connected Vehicle ◽  
Adaptive Signal Control ◽  
Adaptive Signal

scholarly journals Resilience Analysis of Urban Road Networks Based on Adaptive Signal Controls: Day-to-Day Traffic Dynamics with Deep Reinforcement Learning

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-19
Author(s):  
Wen-Long Shang ◽  
Yanyan Chen ◽  
Xingang Li ◽  
Washington Y. Ochieng
Keyword(s):  
Reinforcement Learning ◽  
Road Networks ◽  
Flow Distribution ◽  
Fixed Time ◽  
Time Signal ◽  
Signal Control ◽  
Dynamic Learning ◽  
Urban Road ◽  
Adaptive Signal Control ◽  
Adaptive Signal

Improving the resilience of urban road networks suffering from various disruptions has been a central focus for urban emergence management. However, to date the effective methods which may mitigate the negative impacts caused by the disruptions, such as road accidents and natural disasters, on urban road networks is highly insufficient. This study proposes a novel adaptive signal control strategy based on a doubly dynamic learning framework, which consists of deep reinforcement learning and day-to-day traffic dynamic learning, to improve the network performance by adjusting red/green time split. In this study, red time split is regarded as extra traffic flow to discourage drivers to use affected roads, so as to reduce congestion and improve the resilience when urban road networks are subject to different levels of disruptions. In addition, we utilize the convolution neural network as Q-network to approximate Q values, link flow distribution and link capacity are regarded as the state space, and actions are denoted as red/green time split. A small network is utilized as a numerical example, and a fixed time signal control and other two adaptive signal controls are employed for the comparisons with the proposed one. The results show that the proposed adaptive signal control based on deep reinforcement learning can achieve better resilience in most of the cases, particularly in the scenarios of moderate and severe disruptions. This study may shed light on the advantages of the proposed adaptive signal control dealing with major emergencies compared to others.

An adaptive signal control using connected-vehicle data

2019 ◽  
Vol 172 (2) ◽  
pp. 102-110 ◽  
Author(s):  
Linghui Xu ◽  
Jia Lu ◽  
Fengping Zhan ◽  
Shanglu He ◽  
Jian Zhang
Keyword(s):  
Signal Control ◽  
Connected Vehicle ◽  
Adaptive Signal Control ◽  
Vehicle Data ◽  
Adaptive Signal
Sign in / Sign up

Export Citation Format

Share Document