Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This work investigates the benefits of a two-layer adaptive signal control framework combining multi-region perimeter control (PC) with distributed Max Pressure (MP) control in selected network intersections. Motivated by MP’s questionable performance in over-saturated traffic conditions and the importance of traffic homogeneity in the effectiveness of MFD-based PC, the concept of parallel application of the two strategies, acting in different network nodes but in a parallel scheme, is expected to increase overall system performance due to the controllers’ complementary nature. A method to identify critical nodes for MP control is developed, in order to allow partial MP application in fractions instead of all network nodes. Modified Store-and-forward dynamic traffic paradigm is used to test different control configurations for a real large-scale network. Results show the combined scheme more effective compared to separate controller applications while MP node selection method appears capable of increasing MP efficiency and applicability.
Nikolaos Geroliminis, Dimitrios Tsitsokas, Anastasios Kouvelas