A4 Article in conference proceedings

User-centric Resource Management for Embedded Multi-core Processors




List of Authors: Elham Shamsa, Anil Kanduri, Nima TaheriNejad, Alma Probstl, Samarjit Chakraborty, Amir M. Rahmani, Pasi Liljeberg

Conference name: International Conference On VLSI Design

Publication year: 2020

Journal: VLSI Design

Book title *: 2020 33rd International Conference on VLSI Design and 2020 19th International Conference on Embedded Systems (VLSID)

ISBN: 978-1-7281-5702-3

eISBN: 978-1-7281-5701-6

ISSN: 2380-6923

DOI: http://dx.doi.org/10.1109/VLSID49098.2020.00025


Abstract

Modern battery powered Embedded Systems (ES)
must provide a high performance with minimal energy consumption to enhance the user experience. However, these two are
often conflicting objectives. In current ES resource management
techniques, user behavior and preferences are only indirectly
or not at all considered. In this paper, we present a novel
user- and battery-aware resource management framework for
multi-processor architectures that considers these conflicting
requirements and dynamic unknown workloads at run-time to
maximize user satisfaction. Proposed technique learns user’s
habits to dynamically adjust the resource management schemes
based on the data it collects regarding user’s plug-in behavior,
battery charge status, and workloads variability at run-time. This
information is used to improve the balance between performance
and energy consumption, and thus optimize the Quality of Experience (QoE). Our evaluation results show that our framework
enhances the user experience by 22% in comparison with the
existing state-of-the-art.


Downloadable publication

This is an electronic reprint of the original article.
This reprint may differ from the original in pagination and typographic detail. Please cite the original version.




Last updated on 2021-24-06 at 08:56