Towards a Performance-Aware Partitioning Algorithm for Cloud-Based Microscopic Vehicle Traffic Simulations

Distributed computing is one of the ways to scale up agent-based microscopic vehicle traffic simulations. A key factor for performance is the partitioning of the road network providing computation load balancing and minimizing communication cost. Many approaches use the number of agents as proxy to estimate the computational and communication costs, assuming a direct relation. However this assumption does not hold in a heterogeneous computing environment, e.g. on the cloud. This work discusses a novel proposal to improve the prediction of the computational and communication costs by using information of the simulation's run-time environment. Preliminary evidence indicates that making the partitioning performance-aware results in higher performance.