Improving Smart City Simulation Performance with SimEDaPE and Parallelism

Abstract

In the context of smart cities, the use of simulators such as the InterSCSimulator to study urban mobility problems is increasingly frequent. However, InterSCimulator has limitations in its performance to test large scenarios such as the city of São Paulo. SimEDaPE was proposed to improve the performance of this simulator, but there are still some performance bottlenecks, such as the mapping step, that could be tackled. This work proposes two parallel implementations to improve the performance of this step. Experimental results show that the best parallel approach using 8 cores results in a 3× speedup when compared to the best sequential implementation.