Lookup NU author(s): Professor Raj Ranjan,
Professor Alexander Romanovsky,
This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by IEEE , 2019.
For re-use rights please refer to the publisher's terms and conditions.
Osmotic computing is a new IoT application programmingparadigm that is driven by the significant increase inresource capacity/capability at the network edge, along withsupport for data transfer protocols that enable such resourcesto interact more seamlessly with Cloud-based services. Muchof the difficulty in QoS and performance monitoring of IoTapplications in an Osmotic computing environment is due tothe massive scale and heterogeneity (IoT + Edge + Cloud) ofcomputing environments. To, this end, this work presents anintegrated monitoring system for monitoring IoT applicationsdecomposed as microservices and executed in an Osmotic computingenvironment. A real-world smart parking IoT applicationis used for an experimental evaluation and for demonstratingthe effectiveness of the proposed approach. Through rigorousexperimental evaluation, we validate the Osmotic monitoringsystem ability to holistically identify variation in CPU, memory,and network latency of microservices deployed across Cloud andnEdge layers.
Author(s): Souza A, Cacho N, Jayaraman PP, Ranjan R, Romanovsky A, Noor A
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)
Year of Conference: 2019
Online publication date: 24/01/2019
Acceptance date: 19/04/2017
Date deposited: 24/05/2018