Dynamic Coordinated Speed Control and Synergistic Performance Evaluation in Connected and Automated Vehicle Environment

Due to inherent restrictions in human driving behavior and information access, freeway congestion and stop-and-go behavior are nearly unavoidable. The adverse impacts include increased safety risks, longer travel times, and excessive fuel consumption. Various techniques (e.g., Variable Speed Limit (VSL), which is also known as Dynamic Speed Harmonization (DSH)), have been proposed to dampen traffic oscillation and smooth traffic speed. However, the effectiveness of the VSL is related to the compliance rates of drivers. In addition, there are delays in the collection of information, and control strategies can only affect a small area. Fortunately, new opportunities are emerging with the development of Connected and Automated Vehicles (CAVs) that can completely comply with the control system. Numerous CAV applications are explored as part of the Intelligent Transportation Systems (ITS) to enhance a range of Measures of Effectiveness (MOEs), such as safety, mobility, and environmental sustainability. The objective of this study is to investigate the effects of coordinated speed control in mixed traffic flow involving Human-Driven Vehicles (HDVs) and CAVs on the freeway. Therefore, a dynamic two-phase strategy based on Deep Reinforcement learning (DRL) is developed to better understand how CAVs can improve operational performance. To evaluate and quantify the impact, a comprehensive performance framework is formulated. A series of numerical experiments will be conducted under different traffic demands and market penetration rates (MPRs) under various simulated scenarios. The overall intent of this study is to inform practitioners about the potential interactions between MOEs in implementing specific control strategies in CAV environment.