Multi-objective service composition using reinforcement learning



Publication Details

Moustafa, A. & Zhang, M. (2013). Multi-objective service composition using reinforcement learning. Lecture Notes in Computer Science, 8274 298-312.


Web services have the potential to offer the enterprises with the ability to compose internal and external business services in order to accomplish complex processes. Service composition then becomes an increasingly challenging issue when complex and critical applications are built upon services with different QoS criteria. However, most of the existing QoS-aware compositions are simply based on the assumption that multiple criteria, no matter whether these multiple criteria are conflicting or not, can be combined into a single criterion to be optimized, according to some utility functions. In practice, this can be very difficult as utility functions or weights are not well known a priori. In this paper, a novel multi-objective approach is proposed to handle QoS-aware Web service composition with conflicting objectives and various restrictions on quality matrices. The proposed approach uses reinforcement learning to deal with the uncertainty characteristic inherent in open and decentralized environments. Experimental results reveal the ability of the proposed approach to find a set of Pareto optimal solutions, which have the equivalent quality to satisfy multiple QoS-objectives with different user preferences.

Please refer to publisher version or contact your library.



Link to publisher version (DOI)