Abstract:

With the increasing application of Connected and Autonomous Vehicle (CAV) technologies in active traffic management, Variable Speed Limit (VSL) strategies have become crucial for improving traffic flow efficiency and safety. Aiming to relieve the traffic conflicts in urban expressway merging areas that lead to reduced capacity and abrupt speed variations, this paper proposes a coordinated variable speed limit control strategy for expressway mainline and on-ramp in a vehicular network environment. First, a mainline traffic flow prediction model based on METANET is adopted, constructing a bi-objective function to minimize the total travel time and distance, using Model Predictive Control (MPC). Then, the variable speed limit control problem is modelled as a Markov decision process, with a composite reward function based on average speed, throughput, and vehicle delay. By introducing Deep Q-network (DQN), the optimal on-ramp speed limits under different traffic flow conditions are calculated and disseminated to CAVs through Vehicle-to-Infrastructure (V2I) communication. Finally, the proposed coordinated control strategy is simulated and tested using the North Third Ring Expressway in Xuzhou, China as a case study. The empirical results based on SUMO microsimulation demonstrate that the proposed strategy, compared to the scenario with speed control only on the mainline, reduces the total travel time of network vehicles by 3.75%, increases the average speed by 14.49%, and reduces traffic density fluctuations by 14.81%. This confirms that the strategy effectively improves merging area traffic throughput, reduces speed differentials between mainline and ramp vehicles, narrows the spatiotemporal scope of traffic congestion, which consequently enhances traffic flow stability in a vehicular network environment.

Key words: intelligent transportation, variable speed limit; deep Q-network, urban expressway, on-ramp control, METANET