Signal Control for Urban Traffic Networks with Unknown System Parameters

摘要: Among the several signal control strategies that have been proposed in literature, a key assumption is system parameters including network service rates and demands are known. However, it envisaged next generation of transportation networks with mixed autonomy, such as may vary autonomous vehicle penetration rate changes. Aligned this, we propose strategy which, unlike previous approaches, can handle both unknown mean rates. To this end, use stochastic gradient projection to develop cyclic iterative control, where at every cycle, timing plan signals updated. At each iteration, update rule based on measured changes queue lengths. If arrival assumed be constant, guaranteed converge an optimal solution. We describe intuition behind our algorithm, further demonstrate through simulation studies scheme successfully stabilize system.