We propose a dynamic resource allocation algorithm in the context of future wireless networks endowed with edge computing, to enable accurate energy efficient classification with end-to-end delay guarantees. In our scenario, sensor devices continuously upload data to an Edge Server (ES) for classification purposes. Merging Lyapunov stochastic optimization and ensemble inference, we propose DEsIreE, a low-complexity method that dynamically selects the data quantization level, the device transmit power, and the ES's CPU scheduling, without any prior knowledge of the statistics of wireless channels and data arrivals. Numerical simulations run on two real datasets assess the effectiveness of our algorithm in optimizing sensors' energy consumption and classification accuracy, with the ensemble yielding considerable gain.
Dynamic Ensemble Inference at the Edge / Merluzzi, M.; Martino, A.; Costanzo, F.; Di Lorenzo, P.; Barbarossa, S.. - (2021), pp. 1-6. (Intervento presentato al convegno 2021 IEEE Global Communications Conference, GLOBECOM 2021 tenutosi a Trade Fair Institution of Madrid (IFEMA), esp) [10.1109/GLOBECOM46510.2021.9685597].
Dynamic Ensemble Inference at the Edge
Merluzzi M.;Martino A.;Costanzo F.;Di Lorenzo P.;Barbarossa S.
2021
Abstract
We propose a dynamic resource allocation algorithm in the context of future wireless networks endowed with edge computing, to enable accurate energy efficient classification with end-to-end delay guarantees. In our scenario, sensor devices continuously upload data to an Edge Server (ES) for classification purposes. Merging Lyapunov stochastic optimization and ensemble inference, we propose DEsIreE, a low-complexity method that dynamically selects the data quantization level, the device transmit power, and the ES's CPU scheduling, without any prior knowledge of the statistics of wireless channels and data arrivals. Numerical simulations run on two real datasets assess the effectiveness of our algorithm in optimizing sensors' energy consumption and classification accuracy, with the ensemble yielding considerable gain.File | Dimensione | Formato | |
---|---|---|---|
Merluzzi_Dynamic_2021.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
840.47 kB
Formato
Adobe PDF
|
840.47 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.