Towards Scalable Graph Analytics on Time Dependent Graphs

Edge parameters in time dependent graphs vary as a function of time. Graph analytics in such context takes into consideration the fact that the actual view of the graph changes with time. As an example, single source shortest path (SSSP) in time dependent graphs analyses optimal arrival time with varying start time of graph traversal and/or varying waiting time at each node during traversal. Analytics in time dependent graphs have been applied mostly sequentially in various applications[1, 2]. In this work, we evaluate the graph analytics in large distributed graphs on HPC systems.

[1]  Nancy M. Amato,et al.  Faster Parallel Traversal of Scale Free Graphs at Extreme Scale with Vertex Delegates , 2014, SC14: International Conference for High Performance Computing, Networking, Storage and Analysis.

[2]  Nancy M. Amato,et al.  Multithreaded Asynchronous Graph Traversal for In-Memory and Semi-External Memory , 2010, 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis.

[3]  Hani S. Mahmassani,et al.  Time dependent, shortest-path algorithm for real-time intelligent vehicle highway system applications , 1993 .

[4]  Ariel Orda,et al.  Shortest-path and minimum-delay algorithms in networks with time-dependent edge-length , 1990, JACM.