The freeway congestion problem can be addressed employing a lot of different measures. Ramp metering is the most widely used control measures which is a direct and efficient way to control and upgrade freeway traffic by regulating the number of vehicles entering the freeway. This paper proposes two ramp metering algorithms in which the neuron adaptive control algorithms are applied to tune the rate of metering on-line in real time. Compared to traditional method of feedback ramp metering, these two new methods effectively reduce the oscillator of traffic density and the ramp metering, have stronger robustness, better instant response and better control precision at the same time. With rigorous analysis, it is shown that the proposed learning identification scheme can guarantee the convergence and robustness. A number of simulation results are provided to demonstrate that these two new algorithms are capable of meeting the requirements of both reliability and real-time performance.
[1]
Pravin Varaiya.
Reducing Highway Congestion: An Empirical Approach
,
2005,
Eur. J. Control.
[2]
Markos Papageorgiou,et al.
Series of New Local Ramp Metering Strategies: Emmanouil Smaragdis and Markos Papageorgiou
,
2003
.
[3]
M J Lighthill,et al.
On kinematic waves II. A theory of traffic flow on long crowded roads
,
1955,
Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.
[4]
Markos Papageorgiou,et al.
ALINEA: A LOCAL FEEDBACK CONTROL LAW FOR ON-RAMP METERING
,
1990
.
[5]
Markos Papageorgiou,et al.
SERIES OF NEW LOCAL RAMP METERING STRATEGIES
,
2003
.