Petri Net-Based Model of Peer-to-Peer Dataset Replication in Big Data

Ilija Hristoski, St Kliment Ohridski University –Bitola and Tome Dimovski, St Kliment Ohridski University –Bitola (2021) Petri Net-Based Model of Peer-to-Peer Dataset Replication in Big Data. 3rd Virtual International Conference Path to a Knowledge Society-Managing Risks and Innovation PaKSoM 2021, 1 (3). pp. 191-198. ISSN 978-86-80593-72-2

Full text not available from this repository.
Official URL: https://paksom.cosrec.org/

Abstract

In the contemporary business landscape, the Big Data paradigm helps companies harness their abundant data in their ever-lasting pursuit for new opportunities. Keeping Big Data infrastructure highly performant, scalable, dependable, and available is the key challenge such companies face with. All of these aspects are usually addressed by deploying fault-tolerant systems. Dataset replication is just one of the crucial operations that has to be carried out regularly to improve system resilience. The paper aims at proposing performance models of the execution of reading and writing operations found in one of the main architectures involved in dataset replication: the Peer-to-Peer architecture, based on the utilization of the class of Generalized Stochastic Petri Nets. Such models can be utilized for simulation purposes to obtain various performance metrics vis-à-vis different working scenarios including different input parameters.

Item Type: Article
Subjects: Scientific Fields (Frascati) > Engineering and Technology > Electrical engineering, electronic engineering,information engineering
Divisions: Faculty of Information and Communication Technologies
Depositing User: Prof. d-r. Tome Dimovski
Date Deposited: 21 Jan 2022 09:20
Last Modified: 21 Jan 2022 09:20
URI: http://eprints.uklo.edu.mk/id/eprint/6748

Actions (login required)

View Item View Item