Ranking cloud render farm services for a multi criteria recommender system

Abstract

Recommender systems that recommend ideal services or items to the online users are a very useful tool for both the users and the businesses. Usually for recommending services, multiple attributes of the services are evaluated and these types of recommender systems that evaluate multiple attributes are called multi criteria recommender systems. In these types of multi criteria recommender systems the ranking of services plays a major role. This work is focused on ranking the cloud render farm services which are of the PaaS (Platform-as-a-Service) type of cloud services that provide the entire platform for the animators to render the files using the cloud resources. This work identifies the Quality of Service (QoS) attributes that are important for the animators for selecting a cloud render farm service. The QoS values of four different real time cloud render farm services were collected by conducting real time experiments using the files of the “Big Buck Bunny”, an open-source animated film project and were ranked using three Multi-Criteria Decision Making (MCDM) methods, namely the AHP (Analytical Hierarchical Process), TOPSIS (Technique for Order Preference by Similarity to the Ideal Solution) and SAW (Simple Additive Weighting). The analysis of the ranks obtained using the three different MCDM methods provide many useful insights and conclusions.