An Investigation of SPSA for Signal Timing Optimization at Isolated Intersections

Simultaneous Perturbation Stochastic Approximation (SPSA) has gradually gained favor as an efficient method for optimizing computationally expensive, 'black box' traffic simulations. However, few recent studies have investigated the efficiency of SPSA for traffic signal timing optimization. It is important for this to be investigated, because significant room for improvement exists in the area of signal optimization. Some signal timing methods and products perform optimization very quickly, but deliver mediocre solutions. Other methods and products deliver high-quality solutions, but deliver those solutions very slowly. When using commercialized desktop signal timing products, engineers are often forced to choose between speed and solution quality. Real-time adaptive control products, which must optimize timings within seconds on a cycle-by-cycle basis, do not have enough time to reach a high-quality solution. Based on research results in the literature, SPSA holds the possibility of upgrading both desktop and adaptive solutions alike, by delivering high-quality solutions within seconds. This paper describes an extensive set of optimization tests involving SPSA. The final results suggest that today's signal timing solutions could be improved significantly by incorporating SPSA, genetic algorithms, and 'playbooks' of pre-optimized starting points.