Ageing Analysis of Embedded SRAM on a Large-Scale Testbed Using Machine Learning

TL;DR

This study uses machine learning on large-scale IoT testbed data to analyze SRAM ageing, enabling effective prediction of device wear-out and operational age with high accuracy.

Contribution

It provides the first large-scale empirical analysis of SRAM ageing in IoT devices using machine learning for failure prediction.

Findings

SRAM ageing indicators can predict device age with an R^2 of 0.77.

Machine learning classifiers achieve F1 scores above 0.6 for six-month ageing resolution.

The approach enables proactive maintenance in large IoT deployments.

Abstract

Ageing detection and failure prediction are essential in many Internet of Things (IoT) deployments, which operate huge quantities of embedded devices unattended in the field for years. In this paper, we present a large-scale empirical analysis of natural SRAM wear-out using 154 boards from a general-purpose testbed. Starting from SRAM initialization bias, which each node can easily collect at startup, we apply various metrics for feature extraction and experiment with common machine learning methods to predict the age of operation for this node. Our findings indicate that even though ageing impacts are subtle, our indicators can well estimate usage times with an $R^2$ score of 0.77 and a mean error of 24% using regressors, and with an F1 score above 0.6 for classifiers applying a six-months resolution.