2021/02/22 by Mital Raithatha, Raithatha, Mital, Aizaz U. Chaudhry +5
Engineering · #Advanced MIMO Systems Optimization #Advanced Photonic Communication Systems #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Millimeter-Wave Propagation and Modeling #Networking and Internet Architecture (cs.NI) #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.2103.08408
openalex publication_date 2021/02/22 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
In 5G Ultra-Dense Networks, a distributed wireless backhaul is an attractive\nsolution for forwarding traffic to the core. The macro-cell coverage area is\ndivided into many small cells. A few of these cells are designated as gateways\nand are linked to the core by high-capacity fiber optic links. Each small cell\nis associated with one gateway and all small cells forward their traffic to\ntheir respective gateway through multi-hop mesh networks. We investigate the\ngateway location problem and show that finding near-optimal gateway locations\nimproves the backhaul network capacity. An exact p-median integer linear\nprogram is formulated for comparison with our novel K-GA heuristic that\ncombines a Genetic Algorithm (GA) with K-means clustering to find near-optimal\ngateway locations. We compare the performance of KGA with six other approaches\nin terms of average number of hops and backhaul network capacity at different\nnode densities through extensive Monte Carlo simulations. All approaches are\ntested in various user distribution scenarios, including uniform distribution,\nbivariate Gaussian distribution, and cluster distribution. In all cases K-GA\nprovides near-optimal results, achieving average number of hops and backhaul\nnetwork capacity within 2% of optimal while saving an average of 95% of the\nexecution time.\n