2021/03/20 by Hoon Lee, Lee, Hoon, Junbeom Kim +3 · 1 citation
Engineering · #Advanced MIMO Systems Optimization #Advanced Wireless Communication Technologies #FOS: Computer and information sciences #Information Theory (cs.IT) #Machine Learning (cs.LG) #Millimeter-Wave Propagation and Modeling
paper · pdf · doi:10.48550/arxiv.2103.11284
openalex publication_date 2021/03/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Fog radio access networks (F-RANs), which consist of a cloud and multiple\nedge nodes (ENs) connected via fronthaul links, have been regarded as promising\nnetwork architectures. The F-RAN entails a joint optimization of cloud and edge\ncomputing as well as fronthaul interactions, which is challenging for\ntraditional optimization techniques. This paper proposes a Cloud-Enabled\nCooperation-Inspired Learning (CECIL) framework, a structural deep learning\nmechanism for handling a generic F-RAN optimization problem. The proposed\nsolution mimics cloud-aided cooperative optimization policies by including\ncentralized computing at the cloud, distributed decision at the ENs, and their\nuplink-downlink fronthaul interactions. A group of deep neural networks (DNNs)\nare employed for characterizing computations of the cloud and ENs. The\nforwardpass of the DNNs is carefully designed such that the impacts of the\npractical fronthaul links, such as channel noise and signling overheads, can be\nincluded in a training step. As a result, operations of the cloud and ENs can\nbe jointly trained in an end-to-end manner, whereas their real-time inferences\nare carried out in a decentralized manner by means of the fronthaul\ncoordination. To facilitate fronthaul cooperation among multiple ENs, the\noptimal fronthaul multiple access schemes are designed. Training algorithms\nrobust to practical fronthaul impairments are also presented. Numerical results\nvalidate the effectiveness of the proposed approaches.\n