Assessment of Path Reservation in Distributed Real-Time Vehicle Guidance
Sebastian Senge

TL;DR
This paper evaluates the effectiveness of path reservation in a distributed real-time vehicle guidance system, demonstrating that incorporating current travel times enhances performance at higher market penetration levels.
Contribution
It introduces a modified reservation process that uses real-time travel times, improving guidance system performance in mixed market penetration scenarios.
Findings
Naive reservation only helps at full market penetration.
Incorporating current travel times improves performance at 40% market penetration.
Real-time link load measurements are crucial for effective reservation.
Abstract
In this paper we assess the impact of path reservation as an additional feature in our distributed real-time vehicle guidance protocol BeeJamA. Through our microscopic simulations we show that na\"{\i}ve reservation of links without any further measurements is only an improvement in case of complete market penetration, otherwise it even reduces the performance of our approach based on real-time link loads. Moreover, we modified the reservation process to incorporate current travel times and show that this improves the results in our simulations when at least 40% market penetration is possible.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
