2020/04/27 by Duong Tung Nguyen, Nguyen, Duong Tung, Hieu Trung Nguyen +5 · 1 citation
Computer Science · #Age of Information Optimization #Cognitive Radio Networks and Spectrum Sensing #Distributed #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Parallel #and Cluster Computing (cs.DC)
paper · pdf · doi:10.48550/arxiv.2004.13218
openalex publication_date 2020/04/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Edge computing has emerged as a key technology to reduce network traffic,\nimprove user experience, and enable various Internet of Things applications.\nFrom the perspective of a service provider (SP), how to jointly optimize the\nservice placement, sizing, and workload allocation decisions is an important\nand challenging problem, which becomes even more complicated when considering\ndemand uncertainty. To this end, we propose a novel two-stage adaptive robust\noptimization framework to help the SP optimally determine the locations for\ninstalling their service (i.e., placement) and the amount of computing resource\nto purchase from each location (i.e., sizing). The service placement and sizing\nsolution of the proposed model can hedge against any possible realization\nwithin the uncertainty set of traffic demand. Given the first-stage robust\nsolution, the optimal resource and workload allocation decisions are computed\nin the second-stage after the uncertainty is revealed. To solve the two-stage\nmodel, in this paper, we present an iterative solution by employing the\ncolumn-and-constraint generation method that decomposes the underlying problem\ninto a master problem and a max-min subproblem associated with the second\nstage. Extensive numerical results are shown to illustrate the effectiveness of\nthe proposed two-stage robust optimization model.\n