Data dependent web service selection
thesisposted on 23.05.2021, 12:21 authored by Navati Jain
Data mining applications and services are becoming increasingly important, especially in this age of Big Data. QoS (Quality of Service) properties such as latency, reliability, response time of such services can vary based on the characteristics of the dataset being processed. The existing QoS-based web service selection methods are not adequate for ranking these types of services since they do not consider these dataset characteristics. We have proposed a service selection methodology to predict the QoS values for data analytic services based on the attributes of the dataset involved by incorporating a meta-learning approach. Subsequently we rank the services according to the predicted QoS values. The outcome of our experiments proves the effectiveness of this approach with an improvement of above 20% in service ranking when compared to the traditional QoS selection approach.