Neural Network Predictive Control Based on Particle Swarm Optimization for Urban Expressway

A neural network predictive control method based on particle swarm optimization (PSO) for the urban expressway is proposed. A series of serial-parallel structure radial basis function neural networks are used to identify the dynamic traffic flow model of the expressway. A non-linear predictive control algorithm with the constraint conditions is presented, and an on-line optimization algorithm based on PSO is also proposed. The simulation results show that this control algorithm has strong robustness and good control effect. The effectiveness of the on-line optimization based on PSO algorithm is also verified

[1]  T. Ray,et al.  A swarm with an effective information sharing mechanism for unconstrained and constrained single objective optimisation problems , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[2]  Russell C. Eberhart,et al.  Tracking and optimizing dynamic systems with particle swarms , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[3]  P. J. Angeline,et al.  Using selection to improve particle swarm optimization , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[4]  Yuhui Shi,et al.  Particle swarm optimization: developments, applications and resources , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[5]  Markos Papageorgiou,et al.  COORDINATED AND INTEGRATED CONTROL OF MOTORWAY NETWORKS VIA NON-LINEAR OPTIMAL CONTROL , 2002 .

[6]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[7]  Yoshikazu Fukuyama,et al.  A particle swarm optimization for reactive power and voltage control in electric power systems , 1999, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).