Cloud Render Farm Services Discovery Using NLP And Ontology Based Knowledge Graph

TL;DR

This paper introduces RenderSelect, an ontology-based engine that improves discovery of cost-effective cloud render farm services by semantically matching functional requirements, outperforming traditional search methods.

Contribution

It presents a novel ontology and reasoning algorithms for semantic service discovery tailored to cloud render farms, enhancing accuracy and efficiency.

Findings

Ontology-based discovery outperforms non-ontology methods

Semantic reasoning improves service matching accuracy

Engine effectively identifies suitable render farm services

Abstract

Cloud render farm services are the animation domain specific cloud services Platform-as-a-Service (PaaS) type of cloud services that provides a complete platform to render the animation files. However, identifying the render farm services that is cost effective and also matches the functional requirements that changes for almost every project like the animation software, plug-ins required etc., is a challenge. This research work proposes an ontology-based service discovery engine named RenderSelect for the cloud render farm services. The cloud render farm ontology semantically defines the relationship among the cloud render farm services. The knowledge-based reasoning algorithms namely, the Concept similarity reasoning, Equivalent reasoning and the Numerical similarity reasoning have been applied to determine the similarity among the cloud services. The service discovery engine was evaluated for finding the services under three different scenarios namely a) with help of the ontology, b) without the help of the ontology and c) using a common search engine on the internet. The results show that the proposed service discovery engine which is specifically designed for the cloud render farm services using the ontology performs significantly better than the other two.