Title: Using association rules mining, multi-level data representation and cross-layer operations for data management in mobile ad hoc network
Authors: Noman Islam; Ghazala Shafi Sheikh; Zubair Ahmed Shaikh
Addresses: Department of Computer Science, Iqra University, Karachi 75500, Pakistan ' Department of Computer Science, Iqra University, Karachi 75500, Pakistan ' Department of Computer Science, Muhammad Ali Jinnah University, Karachi 75400, Pakistan
Abstract: This paper presents a data management framework for mobile ad hoc network called association rules based network layer data and information management (ALADIN). Despite the extensive research on data management during last few years, there has been a shortage of a comprehensive data management framework for ad hoc networks. The proposed framework addresses the core issues of data management i.e. data discovery, representation, caching, data replication and security, etc. It uses association rules mining, multi-level data representation, and cross-layer operations for presenting a comprehensive data management framework for ad hoc network. The proposed framework has been implemented in JIST/SWANS simulator. Different experiments have been performed to analyse individual components of the framework. The results show improved latency, hit ratio, data accessibility, scalability, and security of various data management operations. The results have been compared with MoGATU framework that shows improvement in more than 25% in latency and hit ratio of the data discovery process.
Keywords: ALADIN; association rules mining; cross-layer design; data management; multilevel data representation.
International Journal of Intelligent Engineering Informatics, 2021 Vol.9 No.3, pp.229 - 259
Received: 20 Sep 2020
Accepted: 12 Jan 2021
Published online: 12 Oct 2021 *