Spatiotemporal Partitioning of Transportation Network Using Travel Time Data

Abstract

Nowadays, the deployment of sensing technology permits to collect massive spatio-temporal data in urban 1 cities. These data can provide comprehensive traffic state conditions for an urban network and for a particular day. 2 However, they are often too numerous and too detailed to be of direct use, particularly for applications like delivery 3 tour planning, trip advisors and dynamic route guidance. A rough estimation of travel times and their variability may 4 be sufficient if the information is available at the full city scale. The concept of spatio-temporal speed cluster map is 5 a promising avenue for these applications. However, the data preparation for creating these maps is a challenging 6 and rarely discussed topic. In this paper, we address this challenge by introducing generic methodologies for 7mapping the data to a Geographic Information System (GIS) network, coarsening the network for reducing the 8 network complexity at the city scale and also estimating the speed from the travel time data, including missing data. 9We demonstrate this on a large scale urban network of Amsterdam with real travel time data. The preprocessed data 10 is used to build the spatio-temporal speed cluster using three partitioning techniques -Normalized cut, DBSCAN 11and Growing Neural Gas (GNG). A new post-treatment methodology is introduced for DBSCAN and GNG, which 12 are based on data point clustering, to generate connected zones. A preliminary cross comparison of the clustering 13 techniques shows that GNG performs best in generating zones with minimum internal variance, Normalized Cut 14 computes 3D zones with the best inter-cluster dissimilarity and GNG has the faster computation time. 15 16

Sliding Mode Network Perimeter Control

“…where is a strictly positive real number. The sliding surface S is defined in Equation (13). This leads to the relationship ( ) + ( ) = 0.…”

Heuristic Coarsening for Generating Multiscale Transport Networks

“…Based on the simplicity and success of CHs, we propose a heuristic approach with some of the building blocks of CHs-node ordering and node contraction. In [17], we briefly show how a constrained version of CHs can be easily used for network complexity reduction for traffic predictions. In the current contribution we further develop, formalize, apply and test the proposed approach to provide a more generic heuristic framework based on CHs that can be deployed in various applications.…”

“…The difference between this and the first application is that now the edge weights used for the coarsening are aggregates of dynamic quantities. This can be useful for real time predictions for large scale networks where the complexity increases with the size of the network, as time-dependent networks are used for this purpose [17]. We used speed per link as the weights for coarsening the network for this application.…”

“…The sub-network has 7512 links and 6528 nodes and it is a single connected component. The data preparation and conversion of travel time to speed per link is described in detail in [17]. The traffic state of Amsterdam at time 16:00 for one particular day is shown in Figure 7 To preserve the change in speed or road class, the minimum ρ is set to 0.…”

“…To this end, we propose a heuristic coarsening technique based on topological and/or data-driven information of the directed graphs. A constrained version of this coarsening approach using data-driven parameter is briefly noted in [17].…”