Torus AI, Toulouse, France
February 23rd, 2023
Resource allocation algorithms in wireless networks can require solving complex optimization problems at every decision epoch. For large scale networks, when decisions need to be taken on time scales of milliseconds, using standard convex optimization solvers for computing the optimum can be a time-consuming affair that may impair real-time decision making. In this paper, we propose to use Data-driven and Deep Neural Networks for learning the relation between the inputs and the outputs of two such resource allocation algorithms. Our simulation is based on SUMO - a start of the art simulation for traffic simulation, that allows modeling of intermodal traffic systems including road vehicles, public transport and pedestrians. On numerical examples with realistic mobility patterns, we show that the learning algorithm yields an approximate yet satisfactory solution with much less computation time.
Paper 1: https://www.sciencedirect.com/science/article/abs/pii/S1389128622000780
Paper 2: https://www.sciencedirect.com/science/article/pii/S0166531623000019