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

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.

[1]  T. Schmidt,et al.  PUF for the Commons: Enhancing Embedded Security on the OS Level , 2023, IEEE Transactions on Dependable and Secure Computing.

[2]  H. Schlarb,et al.  A Review of Techniques for Ageing Detection and Monitoring on Embedded Systems , 2023, ArXiv.

[3]  Harrison Williams,et al.  Silicon Dating , 2020, ArXiv.

[4]  Thomas C. Schmidt,et al.  A Guideline on Pseudorandom Number Generation (PRNG) in the IoT , 2020, ACM Comput. Surv..

[5]  Johannes L. Schönberger,et al.  SciPy 1.0: fundamental algorithms for scientific computing in Python , 2019, Nature Methods.

[6]  Ujjwal Guin,et al.  Detecting Recycled SoCs by Exploiting Aging Induced Biases in Memory Cells , 2019, 2019 IEEE International Symposium on Hardware Oriented Security and Trust (HOST).

[7]  Domenic Forte,et al.  SCARe: An SRAM-Based Countermeasure Against IC Recycling , 2018, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[8]  Thomas C. Schmidt,et al.  RIOT: An Open Source Operating System for Low-End Embedded Devices in the IoT , 2018, IEEE Internet of Things Journal.

[9]  Mark Mohammad Tehranipoor,et al.  A zero-cost approach to detect recycled SoC chips using embedded SRAM , 2016, 2016 IEEE International Symposium on Hardware Oriented Security and Trust (HOST).

[10]  Eric Fleury,et al.  FIT IoT-LAB: A large scale open experimental IoT testbed , 2015, 2015 IEEE 2nd World Forum on Internet of Things (WF-IoT).

[11]  C. Spearman The proof and measurement of association between two things. , 2015, International journal of epidemiology.

[12]  Hamid Reza Naji,et al.  Adaptive Technique for Overcoming Performance Degradation Due to Aging on 6T SRAM Cells , 2014, IEEE Transactions on Device and Materials Reliability.

[13]  M. Mukaka,et al.  Statistics corner: A guide to appropriate use of correlation coefficient in medical research. , 2012, Malawi medical journal : the journal of Medical Association of Malawi.

[14]  Amir Rahmati,et al.  TARDIS: Time and Remanence Decay in SRAM to Implement Secure Protocols on Embedded Devices without Clocks , 2012, USENIX Security Symposium.

[15]  Amir Rahmati,et al.  DRV-Fingerprinting: Using Data Retention Voltage of SRAM Cells for Chip Identification , 2012, RFIDSec.

[16]  M. Nelhiebel,et al.  The Paradigm Shift in Understanding the Bias Temperature Instability: From Reaction–Diffusion to Switching Oxide Traps , 2011, IEEE Transactions on Electron Devices.

[17]  Dieter K. Schroder,et al.  Negative bias temperature instability: What do we understand? , 2007, Microelectron. Reliab..

[18]  Jan M. Rabaey,et al.  SRAM leakage suppression by minimizing standby supply voltage , 2004, International Symposium on Signals, Circuits and Systems. Proceedings, SCS 2003. (Cat. No.03EX720).

[19]  L. Breiman Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[20]  Ogawa,et al.  Generalized diffusion-reaction model for the low-field charge-buildup instability at the Si-SiO2 interface. , 1995, Physical review. B, Condensed matter.

[21]  Dastan Hussen Maulud,et al.  A Review on Linear Regression Comprehensive in Machine Learning , 2020 .

[22]  Martyn Shuttleworth,et al.  Correlation and Causation , 1937, Wilmott.

[23]  Neha Mehra,et al.  Survey on Multiclass Classification Methods , 2013 .

[24]  Thomas Weiland,et al.  XFEL: The European X-Ray Free-Electron Laser - Technical Design Report , 2006 .

[25]  S. Tucker Taft,et al.  Information technology — Programming Languages — Ada , 2001 .

[26]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.