Adaptive Performance Optimization for Large-Scale Traffic Control Systems

Abstract The majority of practical Large-Scale Traffic Control Systems (LSTCSs) requires the optimization (fine-tuning) of their design parameters. A tremendous amount of human effort and time is spent for optimization of the overall LSTCS, which is usually performed by experienced personnel in the lack of an automated – well established – systematic approach. This paper, investigates the efficiency of the Adaptive Fine-Tuning algorithm, when applied for automated fine-tuning of an urban traffic LSTCS with mutually-interacting control modules, each one with its distinct design parameters. The approach of AFT is based on a recently proposed Adaptive Optimization (AO) methodology that is aiming at replacing the manually-based optimization by a fully-automated procedure and is proven – using rigorous mathematical arguments – to provide with safe and reliable, efficient and rapid optimization of general LSTCSs. Simulations results demonstrate the efficiency of the proposed approach when applied to the simultaneous fine-tuning of two mutually-interacting LSTCS control modules.

[1]  R. Burnett.  Application of stochastic optimization to collision avoidance , 2004, Proceedings of the 2004 American Control Conference.

[2]  Li Lin,et al.  Implementation of traffic lights control based on Petri nets , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[3]  Markos Papageorgiou,et al.  Extensions and New Applications of the Traffic-Responsive Urban Control Strategy: Coordinated Signal Control for Urban Networks , 2003 .

[4]  S. D. Hill,et al.  SPSA/SIMMOD optimization of air traffic delay cost , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[5]  Elias B. Kosmatopoulos,et al.  An adaptive optimization scheme with satisfactory transient performance , 2009, Autom..

[6]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[7]  J. Spall.  Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[8]  Ron Meir,et al.  Approximation bounds for smooth functions in C(Rd) by neural and mixture networks , 1998, IEEE Trans. Neural Networks.

[9]  Markos Papageorgiou,et al.  Adaptive Fine-Tuning of Nonlinear Control Systems With Application to the Urban Traffic Control Strategy TUC , 2007, IEEE Transactions on Control Systems Technology.

[10]  Mark Hansen,et al.  Scenario-based air traffic flow management: From theory to practice , 2008 .

[11]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[12]  Elias B. Kosmatopoulos,et al.  Large Scale Nonlinear Control System Fine-Tuning Through Learning , 2009, IEEE Transactions on Neural Networks.

[13]  Francisco Javier Díaz Pernas,et al.  Intelligent system for dynamic transport fleet management , 2005, 2005 IEEE Conference on Emerging Technologies and Factory Automation.

[14]  James C. Spall,et al.  Adaptive stochastic approximation by the simultaneous perturbation method , 2000, IEEE Trans. Autom. Control..

[15]  Markos Papageorgiou,et al.  A multivariable regulator approach to traffic-responsive network-wide signal control , 2000 .

[16]  Javier J. Sánchez Medina,et al.  Applying a Traffic Lights Evolutionary Optimization Technique to a Real Case: “Las Ramblas” Area in Santa Cruz de Tenerife , 2008, IEEE Transactions on Evolutionary Computation.

[17]  James C. Spall,et al.  TRAFFIC-RESPONSIVE SIGNAL TIMING FOR SYSTEM-WIDE TRAFFIC CONTROL , 1997 .

[18]  Markos Papageorgiou,et al.  EXTENSIONS AND NEW APPLICATIONS OF THE TRAFFIC SIGNAL CONTROL STRATEGY TUC , 2003 .

[19]  Petros A. Ioannou,et al.  CONTAINER MOVEMENT BY TRUCKS IN METROPOLITAN NETWORKS: MODELING AND OPTIMIZATION , 2005 .

[20]  Manolis A. Christodoulou,et al.  Dynamical Neural Networks that Ensure Exponential Identification Error Convergence , 1997, Neural Networks.

[21]  Elias B. Kosmatopoulos,et al.  Adaptive Control Design Based on Adaptive Optimization Principles , 2008, IEEE Transactions on Automatic Control.

[22]  R H Smith,et al.  NETWORKWIDE APPROACH TO OPTIMAL SIGNAL TIMING FOR INTEGRATED TRANSIT VEHICLE AND TRAFFIC OPERATIONS , 1997 .

[23]  Dipti Srinivasan,et al.  Neural Networks for Continuous Online Learning and Control , 2006, IEEE Transactions on Neural Networks.

[24]  Michael C. Fu,et al.  Transfer optimization via simultaneous perturbation stochastic approximation , 1995, WSC '95.