Generation of coordinated control regions for road network using hypergraph models

It is proven that the efficiency of traffic systems can be improved by the regional coordination control. However, questions still arise on when to coordinate the intersections and how to generate the control regions. In this paper, a method is proposed to solve these two problems by subdividing the road network into control regions using a hypergraph-based model. In this method, the road network is mapped to a hypergraph with each vertex representing an intersection and each hyperedge representing a subset of related intersections. The association rule mining algorithm is employed to determine which vertices should be grouped as a hyperedge. A widely used hypergraph partitioning algorithm HMETIS is employed to subdivide the hypergraph into partitions which correspond to the coordinated control regions. Finally, a case study based on the actual road network and practical traffic data is presented to demonstrate the effectiveness of our model.