Predicting IoT failures with Bayesian workflow

Jerzy Baranowski

doi:10.17531/ein.2022.2.6

Abstract

IoT networks are so voluminous that they cannot be treated as individual devices, but as populations. Main aim of the paper is to create a comprehensive method for predicting failures taking device variance into consideration. We propose using data fusion of happenstance observations (resets and failures) to better estimate device parameters. We propose using methods of population analysis in Bayesian statistics to estimate failure times investigating only a part of the population. For this purpose, we use multilevel hierarchical Bayesian model and provide it with post stratification. We propose model assumptions, construct the model and evaluate it, and perform computations using Hamiltonian Monte Carlo. This method is known as the Bayesian workflow. We have analyzed three different models showing that, in case of small device variance, it can be ignored, or at least compensated, while significant differences require hierarchical modeling. We also show that hierarchical model shows significant robustness to a small amount of data. We have shown attractiveness of Bayesian approach to modeling failures of IoT devices. Ability to diagnose and tune models, and assure their computational fidelity is a great advantage of Bayesian workflow.

Highlights

The machines and devices diagnostics, their maintenance and methods of preventing failures with the use of IoT relate to various fields such as Industry 4.0, management of transport devices or medical devices
We will cover the basics of so called Bayesian workflow (Gelman et al [13]), which is a collection of practices allowing principled and responsible modeling of phenomena
We provide a case study covering an extended network of 1000 similar IoT devices

Summary

Introduction

That Internet-of-Things (IoT) devices have become a ubiquitous aspect of current industry and life. Main applications of IoT devices include on-line monitoring and predictive maintenance of industrial equipment. Their use provides both process monitoring for constant quality assurance, and condition monitoring in order to prevent unplanned downtimes. The machines and devices diagnostics, their maintenance and methods of preventing failures with the use of IoT relate to various fields such as Industry 4.0, management of transport devices or medical devices. IoT device failures introduce difficulties in energy management, while they are usually low power solutions, their number complicates matters. This is even more troublesome for battery operated devices

Objectives

Methods

Findings

Conclusion