An iterative learning approach for local ramp metering

In this work, we apply the iterative learning control approach to address the ramp metering in a macroscopic level freeway environment. By formulating the original ramp metering problem into an output tracking and disturbance rejection problem, iterative learning control method can greatly improve the traffic response. The learning mechanism is further combined with well-known ALINEA in a complementary and modular manner and is able to achieve the desired control performance. The effectiveness of the new approach is verified through rigorous theoretical analysis and simulations.