A New Web Service Ranking Method Based on QoS Independent Components and ANN

In the Internet, many WS providers offer the same or similar services, and the QoS (quality of service) of WS has become an important method to evaluate and select the services. This paper focuses on providing a new method to rank the web service based on the QoS to get the best available web service. Firstly, the QoS attributes´ Independent Components(ICs) are computed to reduce their correlation and extract the user preference weight. And then in the ranking procedure, the user preference weight will be studied and justified through BP neural network, which provides an adaptive and objective way to recommend a web service. The experiment shows that this method can improve the accuracy of the web service ranking.