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

Hristoski, Ilija and Dimovski, Tome (2021) Petri Net-Based Model of Peer-to-Peer Dataset Replication in Big Data. Proceedings of the 3rd Virtual International Conference “Path to a Knowledge Society - Managing Risks and Innovation” (PaKSoM 2021). pp. 191-198.

Text PaKSoM_2021_Proceedings_pp_191-198.pdf Download (513kB)

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) > Natural sciences > Computer and information sciences
Divisions:	Faculty of Economics Faculty of Information and Communication Technologies
Depositing User:	Prof. Dr. Ilija Hristoski
Date Deposited:	08 Mar 2023 09:06
Last Modified:	08 Mar 2023 09:06
URI:	https://eprints.uklo.edu.mk/id/eprint/7768

Actions (login required)

View Item