Stochastic Resource Optimization for Wireless Powered Hybrid Coded Edge Computing Networks

• Published in: IEEE transactions on mobile computing 2024-03, Vol.23 (3), p.2022-2038
• Main Authors: Ng, Wei Chong, Lim, Wei Yang Bryan, Xiong, Zehui, Niyato, Dusit, Poor, H. Vincent, Shen, Xuemin Sherman, Miao, Chunyan
• Format: Magazinearticle
• Language: English
• Subjects: Artificial intelligence; Benders decomposition; Computational modeling; Cost analysis; Data processing; Edge computing; Encoding; End user training; End users; Integer programming; Internet of Things; multi-tier computing; network economics; Optimization; resource management; Sensitivity analysis; Servers; stochastic integer programming; Stochastic processes; Task analysis; Wireless communication; Wireless communications; Wireless networks; Wireless power transmission
• ISSN: 1536-1233; 1558-0660
• DOI: 10.1109/TMC.2023.3246994

To enable ubiquitous Artificial Intelligence (AI) in the next-generation wireless communications networks, computation-intensive tasks such as data processing and model training have to be performed by energy-constrained end users. In this paper, we present a hybrid coded edge computing network whereby users can choose to complete their computation task through: i) local computation with the wireless power transfer derived from base stations, ii) coded edge offloading, or iii) hybrid computation involving edge offloading and local computation. To minimize the overall network cost, we propose a stochastic resource optimization approach. Given the stochastic nature of wireless charging efficiency and edge servers computation capacities, which can only be observed ex-post , a computation strategy for each user is determined using the two-stage stochastic integer programming (SIP). To address the complexity of the SIP problem which scales with the size of the network, we introduce the efficient computation methods of Benders' decomposition and sample average approximation. Besides, we present a special case of z z -stage stochastic offloading optimization that is applicable when the corrective edge offloading action can be executed in multiple stages, e.g., for non-time-sensitive tasks that do not need to be completed by stage two. Finally, we provide extensive sensitivity analyses to evaluate the performance of the proposed cost minimization approach amid varying network parameters. We demonstrate that our approach outperforms deterministic optimization approaches for in-network cost minimization.