A sudden traffic surge immediately after special events (e.g., conventions, sporting events, concerts) can create substantial traffic congestion in the area where the events are held. One desirable solution is to develop a short-term traffic signal timing adjustment for the high-volume traffic movements associated with special events so that progression is as efficient as possible. In this paper, we present a case study of special-events traffic signal timing control for a small-scale network. A neural network (NN) is used as a signal controller with its weights determined via the Simultaneous Perturbation Stochastic Approximation (SPSA) method. The SPSA optimization is conducted by minimizing a chosen tolerance index as our performance criterion. The timing plans are developed, and the performance evaluations using the existing signal timing and the one generated by the proposed algorithm are also investigated. Our study shows the advantage and potential of using the NN-based SPSA optimization approach to special-events traffic signal timing control. Although this paper presents a case study, the results can be easily modified and applied to large-scale events traffic control.
|Original language||English (US)|
|Number of pages||7|
|Journal||Control and Intelligent Systems|
|State||Published - Apr 28 2008|
- Neural networks
- Simultaneous perturbation stochastic approximation
- Traffic timing