Predictive Traffic Signal Control under Uncertainty
Analyzing and Reducing the Impact of Prediction Errors
M.C. Verkaik-Poelman (TU Delft - Traffic Systems Engineering)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Predictive traffic signal control pro-actively adapts control decisions to individual vehicle patterns and has the potential to efficiently control traffic in a network reducing congestion. However, in real life, prediction errors will be present, which may influence control performance significantly. Therefore, in this thesis, the performance loss due to prediction errors is analyzed, and robust methods are designed to reduce the impact of prediction uncertainties, improving the real-life applicability of predictive traffic signal control systems.