Interval-Valued Skyline Web Service Selection on Incomplete QoS
Yanjun Shu, Jianhang Zhang, Decheng Zuo, Quan Z. Sheng · 2022
To improve the efficiency of QoS-centric service selection, skyline query is often used to get small candidates from a large number of services. Recently, interval-valued skyline service selection attracts a lot of attention due to the QoS value fluctuation during execution. To simplify skyline computation, existing interval-valued skyline service selection methods assume the probability density function (PDF) of QoS intervals follows general mathematical distribution, such as the Uniform distribution or the Gaussian distribution, which leads to the inaccurate dominant relationship between QoS intervals. In addition to the impractical assumption of intervals, another problem of existing interval-valued skyline service selection methods is that they are all implemented for complete QoS and are not sufficient when some services’ QoS values are missing or invalid. To this end, we develop a new skyline service selection method on incomplete QoS, named ISkySel, which combines probabilistic skyline query and missing QoS prediction. ISkySel uses valid QoS values to build the PDF of QoS intervals and employs the early termination and sorting techniques to accelerate the probabilistic skyline computation. The experiments on the synthetic and real-world datasets show ISkySel has higher accuracy and efficiency compared to the state-of-the-art skyline service selection.