Litcius/Paper detail

Using log analytics and process mining to enable self-healing in the Internet of Things

Prasannjeet Singh, Mehdi Saman Azari, Francesco Vitale, Francesco Flammini, Nicola Mazzocca, Mauro Caporuscio, Johan Thornadtsson

2022Environment Systems & Decisions26 citationsDOIOpen Access PDF

Abstract

Abstract The Internet of Things (IoT) is rapidly developing in diverse and critical applications such as environmental sensing and industrial control systems. IoT devices can be very heterogeneous in terms of hardware and software architectures, communication protocols, and/or manufacturers. Therefore, when those devices are connected together to build a complex system, detecting and fixing any anomalies can be very challenging. In this paper, we explore a relatively novel technique known as Process Mining, which—in combination with log-file analytics and machine learning—can support early diagnosis, prognosis, and subsequent automated repair to improve the resilience of IoT devices within possibly complex cyber-physical systems. Issues addressed in this paper include generation of consistent Event Logs and definition of a roadmap toward effective Process Discovery and Conformance Checking to support Self-Healing in IoT.

Topics & Concepts

AnalyticsComputer scienceProcess (computing)Internet of ThingsResilience (materials science)Process miningEvent (particle physics)Data scienceThe InternetComputer securityWorld Wide WebWork in processEngineeringOperating systemBusiness processPhysicsThermodynamicsQuantum mechanicsOperations managementBusiness process modelingSoftware System Performance and ReliabilityBusiness Process Modeling and AnalysisService-Oriented Architecture and Web Services