Mitigating Metropolitan Carbon Emissions with Dynamic Eco-driving at Scale

2024-08-10

arXiv.org

AI Summary

Urban transportation systems in major metropolitan areas suffer from high carbon emissions and severe stop-and-go congestion. Method: This study proposes a dynamic eco-driving strategy leveraging semi-autonomous vehicles, implemented via a multi-task deep reinforcement learning framework with network decomposition architecture, evaluated at scale in the SUMO simulation platform across three U.S. metropolitan regions, 6,011 signalized intersections, and over one million traffic scenarios. Contribution/Results: The approach achieves system-wide emission reductions of 25%–50% with only 10% vehicle penetration; 70% of benefits concentrate at 20% critical intersections. Intersection-level CO₂ emissions decrease by 11%–22%, yielding annual reductions equivalent to the total national emissions of Israel or Nigeria. Crucially, the strategy maintains—without compromising—traffic throughput and safety, and exhibits strong synergy with vehicle electrification pathways.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search
• Application Domains: Transportation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

The sheer scale and diversity of transportation make it a formidable sector to decarbonize. Here, we consider an emerging opportunity to reduce carbon emissions: the growing adoption of semi-autonomous vehicles, which can be programmed to mitigate stop-and-go traffic through intelligent speed commands and, thus, reduce emissions. But would such dynamic eco-driving move the needle on climate change? A comprehensive impact analysis has been out of reach due to the vast array of traffic scenarios and the complexity of vehicle emissions. We address this challenge with large-scale scenario modeling efforts and by using multi-task deep reinforcement learning with a carefully designed network decomposition strategy. We perform an in-depth prospective impact assessment of dynamic eco-driving at 6,011 signalized intersections across three major US metropolitan cities, simulating a million traffic scenarios. Overall, we find that vehicle trajectories optimized for emissions can cut city-wide intersection carbon emissions by 11-22%, without harming throughput or safety, and with reasonable assumptions, equivalent to the national emissions of Israel and Nigeria, respectively. We find that 10% eco-driving adoption yields 25%-50% of the total reduction, and nearly 70% of the benefits come from 20% of intersections, suggesting near-term implementation pathways. However, the composition of this high-impact subset of intersections varies considerably across different adoption levels, with minimal overlap, calling for careful strategic planning for eco-driving deployments. Moreover, the impact of eco-driving, when considered jointly with projections of vehicle electrification and hybrid vehicle adoption remains significant. More broadly, this work paves the way for large-scale analysis of traffic externalities, such as time, safety, and air quality, and the potential impact of solution strategies.

Problem

• Mitigating urban carbon emissions via dynamic eco-driving strategies
• Assessing large-scale impact of semi-autonomous vehicles on traffic emissions
• Optimizing intersection-level emissions without compromising traffic throughput

Innovation

• Dynamic eco-driving with intelligent speed commands
• Multi-task deep reinforcement learning for modeling
• Large-scale scenario modeling at signalized intersections