Decentralised Progressive Signal Systems for Organic Traffic Control

Tomforde, Sven; Prothmann, Holger; Rochner, Fabian; Branke, Jürgen; Hähner, Jörg; Müller-Schloer, Christian; Schmeck, Hartmut

doi:10.1109/saso.2008.31

Cited by 29 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their results show 10-12% improvement in average delay distributed among the three days for the bigger junction and 6 -8% for the smaller junction against a fixed-time controller. As an extension of the OTC work, coordination among OTC controllers was added [40], however on a small-scale Manhattan-like grid simulation, no significant improvement on their previous results was obtained. In [39], an RL approach to optimizing UTC while responding to traffic volume change and driver behaviour (Nagel-Schreckenberg model [41]) is presented.…”

Section: Related Workmentioning

confidence: 98%

Soilse: A decentralized approach to optimization of fluctuating urban traffic using Reinforcement Learning

Salkham

Cahill

2010

13th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

Abstract-Increasing traffic congestion is a major problem in urban areas, which incurs heavy economic and environmental costs in both developing and developed countries. Efficient urban traffic control (UTC) can help reduce traffic congestion. However, the increasing volume and the dynamic nature of urban traffic pose particular challenges to UTC. Reinforcement Learning (RL) has been shown to be a promising approach to efficient UTC. Dublin's inner city centre. Results from using our scheme show an approximate 35% -43% and 40% -54% better performance in terms of average vehicle waiting time and average number of vehicle stops respectively against the best baseline performance in our simulation.

show abstract

Section: Related Workmentioning

confidence: 98%

Soilse: A decentralized approach to optimization of fluctuating urban traffic using Reinforcement Learning

Salkham

Cahill

2010

13th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

show abstract

“…OTC is based on the Observer/Controller model [12] as known from the domain of Organic Computing [3] and learns the best traffic control strategy at an urban intersection a runtime. In general, OTC consists of three major components: (1) autonomous learning of self-configuration strategies for traffic lights (i.e., duration of green times at each intersection) [42], (2) self-coordination to establish Progressive Signal Systems (PSS) [43], and (3) negotiation to derive route recommendations following Internet-based protocols [44]. In the context of this article, the aspect of self-adaptation in terms of configuring green duration of phases are of particular interest.…”

Section: Application 1: Traffic Controlmentioning

confidence: 99%

To Adapt or Not to Adapt: A Quantification Technique for Measuring an Expected Degree of Self-Adaptation

Tomforde

Goller

2020

Computers

Self Cite

View full text Add to dashboard Cite

Self-adaptation and self-organization (SASO) have been introduced to the management of technical systems as an attempt to improve robustness and administrability. In particular, both mechanisms adapt the system's structure and behavior in response to dynamics of the environment and internal or external disturbances. By now, adaptivity has been considered to be fully desirable. This position paper argues that too much adaptation conflicts with goals such as stability and user acceptance. Consequently, a kind of situation-dependent degree of adaptation is desired, which defines the amount and severity of tolerated adaptations in certain situations. As a first step into this direction, this position paper presents a quantification approach for measuring the current adaptation behavior based on generative, probabilistic models. The behavior of this method is analyzed in terms of three application scenarios: urban traffic control, the swidden farming model, and data communication protocols. Furthermore, we define a research roadmap in terms of six challenges for an overall measurement framework for SASO systems.

show abstract

“…It is the signal cycle that local traffic signal controllers agree to coordinate and optimize. The common signal cycle of intersection group in intraregional boundaries is calculated as in Algorithm 1 [13]. Thus, the signal intersection of intersection group in intraregional boundaries can optimize and dynamically adjust the traffic signal based on real-time traffic flow data.…”

Section: Traffic Flow Self-monitoringmentioning

confidence: 99%

Intersection Group Dynamic Subdivision and Coordination at Intraregional Boundaries in Sudden Disaster

Lin

Gong

Yang

et al. 2015

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper aims at the traffic flow agglomeration effect characteristics and rapid evacuation requirement in sudden disaster; operation time of intraregional boundaries traffic signal coordination was presented firstly. Then intraregional boundaries intersection group dynamic subdivision and consolidation method based on relative similarity degree and similarity coefficient of adjacent intersections was put forward. As to make the traffic control strategy adapt to traffic condition of different intraregional boundaries intersection groups, this paper proposes an intraregional boundaries traffic signal coordination and optimization technology based on organic computing theory. Finally, this paper uses Delphi 7.0, MapX, and Oracle developing a software package, combined with Paramics V6 Simulator to validate the methods of this paper. The result shows that it can obviously improve disaster affected regional traffic signal control efficiency which reduces average traffic delay by 30-35%, decreases vehicle queue by more than 20% and reduces evacuation time more than 13.06%.

show abstract

Decentralised Progressive Signal Systems for Organic Traffic Control

Cited by 29 publications

References 12 publications

Soilse: A decentralized approach to optimization of fluctuating urban traffic using Reinforcement Learning

Soilse: A decentralized approach to optimization of fluctuating urban traffic using Reinforcement Learning

To Adapt or Not to Adapt: A Quantification Technique for Measuring an Expected Degree of Self-Adaptation

Intersection Group Dynamic Subdivision and Coordination at Intraregional Boundaries in Sudden Disaster

Contact Info

Product

Resources

About