Coping with Randomness in Highly Complex Sys-tems Using the Example of Quantum-Inspired Traffic Flow Optimization

Abstract

Developing new solutions to complicated large-scale problems typically requires large-scale numerical simulation. Therefore, traffic simulations often run against randomized simulations instead of real-world traffic situations. This paper demonstrates a method to calculate the statistical significance of numerical simulations and optimizations in the presence of numerous random variables in complex systems using one-sided paired t-tests. While the paper covers a specific Fujitsu traffic-optimization project which uses SUMO for simulating the traffic situation, the method can be applied to many similar projects where a complete investigation of the solution space is not feasible due to the size of the solution space.