HANDY: A Hybrid Association Rules Mining Approach for Network Layer Discovery of Services for Mobile Ad hoc Network
This addresses the challenge of efficient service discovery for users in infrastructure-less mobile networks, but it appears incremental as it builds on existing association rules and optimization techniques.
The paper tackles service discovery in Mobile Ad hoc Networks (MANETs) by proposing HANDY, a hybrid framework that uses cross-layer optimization, multi-level ontologies, and association rules, resulting in improved hit ratio and reduced latency in simulations.
Mobile Ad hoc Network (MANET) is an infrastructure-less network formed between a set of mobile nodes. The discovery of services in MANET is a challenging job due to the unique properties of network. In this paper, a novel service discovery framework called Hybrid Association Rules Based Network Layer Discovery of Services for Ad hoc Networks (HANDY) has been proposed. HANDY provides three major research contributions. At first, it adopts a cross-layer optimized design for discovery of services that is based on simultaneous discovery of services and corresponding routes. Secondly, it provides a multi-level ontology-based approach to describe the services. This resolves the issue of semantic interoperability among the service consumers in a scalable fashion. Finally, to further optimize the performance of the discovery process, HANDY recommends exploiting the inherent associations present among the services. These associations are used in two ways. First, periodic service advertisements are performed based on these associations. In addition, when a response of a service discovery request is generated, correlated services are also attached with the response. The proposed service discovery scheme has been implemented in JIST/SWANS simulator. The results demonstrate that the proposed modifications give rise to improvement in hit ratio of the service consumers and latency of discovery process.