Adaptive Iterative Learning Control for Freeway Traffic Flow Systems Using Improved Bacterial Foraging Optimized Desired Traffic Densities Planning

In this paper, we propose a discrete fuzzy-neural adaptive iterative learning control (AILC) for freeway traffic flow systems with random initial resetting errors, iteration-varying desired traffic densities, and random bounded off-ramp traffic volumes using traffic densities, space mean speeds, and on-ramp waiting queues design. It is assumed that the system nonlinear functions and input gains are unknown for controller design. An adaptive fuzzy-neural network controller and an adaptive robust controller are applied to compensate for the unknown system nonlinearities and input gains, respectively. Moreover, to deal with the disturbances from random bounded off-ramp traffic volumes, a dead-zone like auxiliary error with a time-varying boundary layer is introduced as a bounding parameter. This proposed auxiliary error is also utilized to construct the adaptive laws without using the bound of the input gain. The traffic density tracking error is shown to converge along the axis of learning iteration to a residual set whose level of magnitude depends on the width of boundary layer. Besides, since the nice desired traffic densities designed for the coordinated control objective of the AILC for freeway traffic flow systems are generally unknown, the improved bacterial forging optimization (IBFO) algorithm is used to optimize the fitness function, which is constructed by the coordinated control objective including (1) minimum total travel time, (2) minimum on-ramp average waiting time, and (3) minimum changes of desired traffic densities. Finally, a computer simulation example is used to verify the learning performance of the proposed fuzzy-neural AILC for freeway traffic flow systems using IBFO-based desired traffic densities planning.