2021/07/20 by Mohanad Odema, Odema, Mohanad, Nafiul Rashid +5 · 2 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #Advanced Neural Network Applications #Distributed #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Parallel #and Cluster Computing (cs.DC)
paper · pdf · doi:10.48550/arxiv.2107.09309
openalex publication_date 2021/07/20 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Edge-Cloud hierarchical systems employing intelligence through Deep Neural\nNetworks (DNNs) endure the dilemma of workload distribution within them.\nPrevious solutions proposed to distribute workloads at runtime according to the\nstate of the surroundings, like the wireless conditions. However, such\nconditions are usually overlooked at design time. This paper addresses this\nissue for DNN architectural design by presenting a novel methodology, LENS,\nwhich administers multi-objective Neural Architecture Search (NAS) for\ntwo-tiered systems, where the performance objectives are refashioned to\nconsider the wireless communication parameters. From our experimental search\nspace, we demonstrate that LENS improves upon the traditional solution's Pareto\nset by 76.47% and 75% with respect to the energy and latency metrics,\nrespectively.\n