Uncertain Big QoS Data-Driven Efficient SaaS Decision-Making Method

Abstract

Selecting the QoS-optimized software-as-a-service (SaaS) from a large number of services with the same functionality and different Quality of Service (QoS) is still a hot issue. Massive QoS feedback forms big QoS data, which exhibits ambiguity and randomness increasing the uncertainty of service selection. Starting from the characterization of big QoS data, the Uncertain Big QoS data-driven Efficient SaaS Decision Making Method (UBQoS_ESDM) is proposed. The method firstly utilizes cloud model to portray QoS in order to solve the problem of inaccurate description of uncertain big QoS data; then draws on the idea of Skyline query to establish uncertain service Skyline set, which reduces the search space and improves the efficiency of QoS-optimal SaaS selection; and draws on the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) to design two decision-making algorithms to evaluate alternative SaaSs, and to obtain the QoS-optimal SaaS that reflects user requirements. In addition, two types of backward QoS cloud generators are introduced to convert big QoS data to QoS cloud models, and the QoS cloud model adaptive adjustment mechanism is introduced too, which can adapt to the dynamic changes of QoS. Finally, theoretical proofs and experiments verify the superiority and efficiency of the method.