2020/03/03 by Juno V. Saraiva, Saraiva, Juno V., Iran M. Braga +11
Computer Science · Engineering · #Advanced MIMO Systems Optimization #FOS: Computer and information sciences #FOS: Electrical engineering #ICT Impact and Policies #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Signal Processing (eess.SP) #Wireless Networks and Protocols #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2003.02643
openalex publication_date 2020/03/03 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In this article, we study a Radio Resource Allocation (RRA) that was\nformulated as a non-convex optimization problem whose main aim is to maximize\nthe spectral efficiency subject to satisfaction guarantees in multiservice\nwireless systems. This problem has already been previously investigated in the\nliterature and efficient heuristics have been proposed. However, in order to\nassess the performance of Machine Learning (ML) algorithms when solving\noptimization problems in the context of RRA, we revisit that problem and\npropose a solution based on a Reinforcement Learning (RL) framework.\nSpecifically, a distributed optimization method based on multi-agent deep RL is\ndeveloped, where each agent makes its decisions to find a policy by interacting\nwith the local environment, until reaching convergence. Thus, this article\nfocuses on an application of RL and our main proposal consists in a new deep RL\nbased approach to jointly deal with RRA, satisfaction guarantees and Quality of\nService (QoS) constraints in multiservice celular networks. Lastly, through\ncomputational simulations we compare the state-of-art solutions of the\nliterature with our proposal and we show a near optimal performance of the\nlatter in terms of throughput and outage rate.\n