Toggle Main Menu Toggle Search

Open Access padlockePrints

Selective policies for efficient state retention in transiently-powered embedded systems: Exploiting properties of NVM technologies

Lookup NU author(s): Dr Domenico Balsamo



This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


Transiently-powered embedded systems are emerging to enable computation to be sustained during intermittent supply, without the need for large energy buffers such as batteries or supercapacitors. To deal with the intermittent nature of the input source, these systems save the system state (i.e. registers and main memory) to Non-Volatile Memory (NVM) before a power failure, and restore it when the power supply recovers. Existing approaches normally save the entire state of the system upon power failure, but this is both energy and time consuming. In this paper, we analyse existing approaches to identify their inefficiency when used with specific NVM technologies, and propose novel selective policies for efficiently retaining the system state by exploiting properties of different NVM technologies. These policies are based on (1) concatenating multiple images into the available NVM before erasing, and (2) efficiently selecting only the system state that has changed since last saving. The existing and proposed policies are experimentally validated on two embedded platforms featuring different NVM technologies (Flash and FRAM), depending on their characteristics, in order to identify the most energy efficient policy/platform combination. Results show a reduction in energy and time overhead of up to 90.6% for Flash memory using a novel policy, and 86.2% for FRAM, compared to the typical approach of saving the entire system state.

Publication metadata

Author(s): Verykios TD, Balsamo D, Merrett GV

Publication type: Article

Publication status: Published

Journal: Sustainable Computing: Informatics and Systems

Year: 2019

Volume: 22

Pages: 167-178

Print publication date: 01/06/2019

Online publication date: 25/07/2018

Acceptance date: 11/07/2018

Date deposited: 20/06/2019

ISSN (print): 2210-5379

ISSN (electronic): 2210-5387

Publisher: Elsevier


DOI: 10.1016/j.suscom.2018.07.003


Altmetrics provided by Altmetric


Find at Newcastle University icon    Link to this publication