Preprint Open Access

EdgeBOL: Automating Energy-savings for Mobile Edge AI

Jose A. Ayala-Romero; Andres Garcia-Saavedra; Xavier Costa-Perez; George Iosifidis

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.

Files (2.7 MB)
Name Size
conext21-final106.pdf
md5:a6d51d30ccd1187a9a743a6354a65083
2.7 MB Download
241
144
views
downloads
All versions This version
Views 241197
Downloads 144122
Data volume 324.3 MB324.2 MB
Unique views 208180
Unique downloads 130116

Share

Cite as