Time-aware trustworthiness ranking prediction for cloud services using interval neutrosophic set and ELECTRE

摘要

The imprecise quality of service (QoS) evaluations from consumers may lead to the inappropriate prediction for the trustworthiness of cloud services in an uncertain cloud environment. The service ranking prediction is a promising idea to overcome this deficiency of values prediction approaches by probing the ordering relations between cloud services concealed in the imprecise evaluations. To address the challenges for trustworthy service selection resulting from fluctuating QoS, flexible service pricing and complicated potential risks, this paper proposes a time-aware approach to predict the trustworthiness ranking of cloud services, with the tradeoffs between performance-cost and potential risks in multiple periods. In this approach, the interval neutrosophic set (INS) theory is utilized to describe and assess the performance-costs and potential risks of cloud services: (1) the original evaluation data about cloud services are preprocessed into the trustworthiness interval neutrosophic numbers (INNs); (2) the new INS operators are proposed with the theoretical proofs to calculate the possibility degree and the ranking values of trustworthiness INNs, contributing to the identification of the neighboring users based on the Kendall rank correlation coefficient (KRCC). The problem of time-aware trustworthiness ranking prediction is formulated as a multi-criterion decision-making (MCDM) problem of creating a ranked services list using INS, and an improved ELECTRE method is developed to solve it. The proposed approach is verified by experiments based on an appropriate baseline for comparative analysis. The experimental results demonstrate that the proposed approach can achieve a better prediction quality than the existing approach. The results also show that our approach works effectively in the risk-sensitive and performance cost-sensitive application scenarios and prevent the malignant price competition launched by low-quality services. (C) 2017 Elsevier B.V. All rights reserved.