A novel intelligent service selection algorithm and application for ubiquitous web services environment

It is one of most important problems to choose a most appropriate service for user from all the useable services regardless of user’s location and heterogeneous architecture of underlying software and hardware infrastructure in ubiquitous computing. In order to overcome the shortcomings of blindness and randomicity in traditional service selection algorithm, we propose a novel ANN-based (Artificial Neural Network) service selection algorithm (called the ANNSS algorithm). We adopt a novel method that according to the earlier information of the cooperation between the devices and the context information, an ANN-based evaluation standard for the service quality of service provider is given out so that user can acquire an effective guidance and choose the most appropriate service. At the same time, we improved the traditional BP algorithm based on three-term method (called the TTMBP) consisting of a learning rate (LR), a momentum factor (MF) and a proportional factor (PF) in order to satisfy the requirements of time issue in real-time system. The convergence speed and stability were enhanced by adding the proportional factor. The self-adjusting architecture method is adopted so that a moderate scale of neural network can be obtained. We have implemented the ANNSS algorithm in an actual ubiquitous web services system and fulfilled various simulations. The results of simulation show that the proposed service selection scheme is not only scalable but also efficient, and that the novel BP algorithm based on three-term has high convergence speed and good convergence stability. The novel service selection scheme superior to the traditional service selection scheme without ANNSS. The novel algorithm can exactly choose a most appropriate service in ubiquitous web services environment.