Ity of problems increases the performance of these

Info icon This preview shows pages 13–15. Sign up to view the full content.

ity of problems increases, the performance of these EAs significantly deteriorates, since they cannot find a wide range of alternative solutions. In addition, MOGA and MOPSO cannot solve the optimization problems with concave Pareto fronts which are commonly encountered in the real world. In contrast, the proposed MORL based approach is able explore well the Pareto front of multi-objective service composition problems and deliver optimal solutions. On the other hand, EAs require a level of awareness of the problem domain to setup the initial population through encoding the available combinations as genomes. In contrast, the proposed MORL based approach can learn how to best select Web services in complex environments based on multiple QoS criteria
Image of page 13

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

Multi-Objective Service Composition Using Reinforcement Learning 311 without any prior knowledge regarding the nature or the dynamics of these environment. Up to our knowledge, this is the first approach that uses MORL to solve this problem. 6 Conclusion This paper proposes a novel approach to facilitate the QoS -aware service compo- sition problem. By using multi-objective reinforcement learning, we devise two algorithms to enable Web service composition considering multiple QoS objec- tives. The first algorithm addresses the single policy composition scenarios, while the second algorithm addresses the multiple policy composition scenarios. The simulation results have shown the ability of the proposed approach to efficiently compose Web services based on multiple QoS objectives, especially in scenar- ios where no prior knowledge of QoS data is available and no predefined user preferences are given. The future work is set to study the performance of the proposed approach in large scale service compositions scenarios. References 1. Berbner, R., Spahn, M., Repp, N., Heckmann, O., Steinmetz, R.: Heuristics for qos-aware web service composition. In: International Conference on Web Services, ICWS 2006, pp. 72–82 (2006) 2. Canfora, G., Di Penta, M., Esposito, R., Villani, M.L.: An approach for qos-aware service composition based on genetic algorithms. In: Proceedings of the 2005 Con- ference on Genetic and Evolutionary Computation GECCO 2005, pp. 1069–1075. ACM, New York (2005) 3. Cao, J., Sun, X., Zheng, X., Liu, B., Mao, B.: Efficient multi-objective services selection algorithm based on particle swarm optimization. In: 2010 IEEE Asia- Pacific Services Computing Conference (APSCC), pp. 603–608 (2010) 4. Chiu, D., Agrawal, G.: Cost and accuracy aware scientific workflow composition for service-oriented environments. IEEE Trans. Services Computing (2012) 5. Claro, D.B., Albers, P., Hao, J.K.: Selecting web services for optimal composition. In: SDWP 2005, pp. 32–45 (2005) 6. de Campos, A., Pozo, A.T.R., Vergilio, S.R., Savegnago, T.: Many-objective evolu- tionary algorithms in the composition of web services. In: 2010 Eleventh Brazilian Symposium on Neural Networks (SBRN), pp. 152–157 (2010) 7. Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Transactions on Evolutionary Computation 6(2), 182–197 (2002) 8. Dehousse, S., Faulkner, S., Herssens, C., Jureta, I.J., Saerens, M.: Learning opti-
Image of page 14
Image of page 15
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern