Print Email Facebook Twitter EdgeBOL Title EdgeBOL: Automating energy-savings for mobile edge AI Author Ayala-Romero, Jose A. (Huawei Ireland Research Center) Garcia-Saavedra, Andres (NEC Laboratories Europe) Costa-Perez, Xavier (i2CAT Foundation and ICREA) Iosifidis, G. (TU Delft Embedded and Networked Systems) Date 2021 Abstract Supporting Edge AI services is one of the most exciting features of future mobile networks. These services involve the collection and processing of voluminous data streams, right at the network edge, so as to offer real-time and accurate inferences to users. However, their widespread deployment is hampered by the energy cost they induce to the network. To overcome this obstacle, 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 desirable accuracy and latency thresholds. Using a fully-fledged prototype with a software-defined base station (BS) and a GPU-enabled edge server, we profile a state-of-the-art video analytics AI service and identify new performance trade-offs. Accordingly, we tailor the optimization framework to account for the network context, the user needs, and the service metrics. The efficacy of our proposal is verified in a series of experiments and comparisons with neural network-based benchmarks. Subject Energy efficiencyMobile networksO-RANQoS To reference this document use: http://resolver.tudelft.nl/uuid:661c874d-62e7-46a7-bcab-9fc76900e567 DOI https://doi.org/10.1145/3485983.3494849 Publisher Association for Computing Machinery (ACM) Embargo date 2022-06-01 ISBN 978-1-4503-9098-9 Source CoNEXT 2021 - Proceedings of the 17th International Conference on emerging Networking EXperiments and Technologies Event 17th ACM International Conference on emerging Networking EXperiments and Technologies, CoNEXT 2021, 2021-12-07 → 2021-12-10, Virtual, Online, Germany Series CoNEXT 2021 - Proceedings of the 17th International Conference on emerging Networking EXperiments and Technologies 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 conference paper Rights © 2021 Jose A. Ayala-Romero, Andres Garcia-Saavedra, Xavier Costa-Perez, G. Iosifidis Files PDF 3485983.3494849_1.pdf 1.59 MB Close viewer /islandora/object/uuid:661c874d-62e7-46a7-bcab-9fc76900e567/datastream/OBJ/view