Print Email Facebook Twitter EdgeBOL Title EdgeBOL: A Bayesian Learning Approach for the Joint Orchestration of vRANs and Mobile Edge AI Author Ayala-Romero, Jose A. (NEC Laboratories Europe) Garcia-Saavedra, Andres (NEC Laboratories Europe) Costa-Perez, Xavier (NEC Laboratories Europe; i2CAT Foundation and ICREA) Iosifidis, G. (TU Delft Networked Systems) Date 2023 Abstract Future mobile networks need to support intelligent services which collect and process data streams at the network edge, so as to offer real-time and accurate inferences to users. However, the widespread deployment of these services is hindered by the unprecedented energy cost they induce to the network, and by the difficulties in optimizing their end-to-end operation. To address these challenges, we propose a Bayesian learning framework for jointly configuring the service and the Radio Access Network (RAN), aiming to minimize the total energy consumption while respecting accuracy and latency service requirements. Using a fully-fledged prototype with a software-defined base station (vBS) and a GPU-enabled edge server, we profile a typical video analytics service and identify new performance trade-offs and optimization opportunities. Accordingly, we tailor the proposed learning framework to account for the (possibly varying) network conditions, user needs, and service metrics, and apply it to a range of experiments with real traces. Our findings suggest that this approach effectively adapts to different hardware platforms and service requirements, and outperforms state-of-the-art benchmarks based on neural networks. Subject Base stationsBayes methodsBayesian online learningCostsedge computingEnergy efficiencymachine learningnetwork virtualizationOptimizationPerformance evaluationPower demandServerswireless testbeds To reference this document use: http://resolver.tudelft.nl/uuid:ffa6c914-c6c1-4391-8fb7-dbb4870ae353 DOI https://doi.org/10.1109/TNET.2023.3268981 Embargo date 2024-01-04 ISSN 1063-6692 Source IEEE - ACM Transactions on Networking, 31 (6), 2978 - 2993 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2023 Jose A. Ayala-Romero, Andres Garcia-Saavedra, Xavier Costa-Perez, G. Iosifidis Files PDF EdgeBOL_A_Bayesian_Learni ... dge_AI.pdf 5.8 MB Close viewer /islandora/object/uuid:ffa6c914-c6c1-4391-8fb7-dbb4870ae353/datastream/OBJ/view