cc 18: e4

Research Article

A Hybrid Service Ranking Based Collaborative Filtering Model on Cloud Web Service Data

Download30 downloads
  • @ARTICLE{10.4108/eai.26-10-2021.171599,
        author={Suvarna S. Pawar and Y. Prasanth},
        title={A Hybrid Service Ranking Based Collaborative Filtering  Model on Cloud Web Service Data},
        journal={EAI Endorsed Transactions on Collaborative Computing: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={CC},
        year={2021},
        month={10},
        keywords={Cloud web services, service ranking, collaborative filtering},
        doi={10.4108/eai.26-10-2021.171599}
    }
    
  • Suvarna S. Pawar
    Y. Prasanth
    Year: 2021
    A Hybrid Service Ranking Based Collaborative Filtering Model on Cloud Web Service Data
    CC
    EAI
    DOI: 10.4108/eai.26-10-2021.171599
Suvarna S. Pawar1,*, Y. Prasanth1
  • 1: Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation Vaddeswaram - 522502, Guntur District, Andhra Pradesh, India
*Contact email: sspawar.scoe@sinhgad.edu

Abstract

INTRODUCTION: Trust is an important indicator in the cloud computing environment for service selection and recommendation. It is a difficult task to create a composite value-added service from several candidate services for the desired objectives due to the dramatic growth in services that have similar functionalities.

OBJECTIVES: This research aims to design a hybrid service feature ranking; cloud service ranking are computed using the advanced contextual service ranking measures. A hybrid collaborative approach is totally based on confidence to the QoS web service prediction.

METHODS: A new service ranking similarity computation is optimized for the cloud-based service selection. This collaborative filtering measure is used to check the top k customer selection by performing the top-k customer selection estimation on the cloud service ranking.

RESULTS: The proposed method is useful in the prediction of QoS values and helps with optimal service ranking. As a result, similar/ relating cloud services are increasing, making it extremely complex to select the best cloud service among the relevant / similar services available.

CONCLUSION: The state-of the-art approaches are proposed and tested on a mathematical QoS-Aware assessment framework. The use of semantic matching technique and QoS for web service ranking satisfies user requirements for web service recommendations. In addition, users require a web service not only based on functionality, but also based on high quality.