Abstract
We propose a novel Infrastructure-as-a-Service composition framework that selects an optimal set of consumer requests according to the provider’s qualitative preferences on long-term service provisions. Decision variables are included in the temporal conditional preference networks to represent qualitative preferences for both short-term and long-term consumers. The global preference ranking of a set of requests is computed using a k-d tree indexing-based temporal similarity measure approach. We propose an extended three-dimensional Q-learning approach to maximize the global preference ranking. We design the on-policy-based sequential selection learning approach that applies the length of request to accept or reject requests in a composition. The proposed on-policy-based learning method reuses historical experiences or policies of sequential optimization using an agglomerative clustering approach. Experimental results prove the feasibility of the proposed framework.
- Pegah Alizadeh, Aomar Osmani, Mohamed Essaid Khanouche, Abdelghani Chibani, and Yacine Amirat. 2021. Reinforcement learning for interactive QoS-aware services composition. IEEE Syst. J. 15, 1 (2021), 1098–1108. DOI:10.1109/JSYST.2020.2997069Google Scholar
Cross Ref
- Mohammad Alrifai and Thomas Risse. 2009. Combining global optimization with local selection for efficient QoS-aware service composition. In Proceedings of WWW. ACM, 881–890. Google Scholar
Digital Library
- Alexandr Andoni and Piotr Indyk. 2006. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. In Proceedings of FOCS. IEEE, 459–468. Google Scholar
Digital Library
- Pavel Berkhin. 2006. A survey of clustering data mining techniques. In Grouping Multidimensional Data. Springer, 25–71.Google Scholar
- Marko Bohanec, Antoine Messean, Sara Scatasta, Frederique Angevin, Bryan Griffiths, Paul Henning Krogh, Martin Žnidaršič, and Sašo Džeroski. 2008. A qualitative multi-attribute model for economic and ecological assessment of genetically modified crops. Ecol. Model. 215, 1 (2008), 247–261.Google Scholar
Cross Ref
- Athman Bouguettaya. 1996. On-line clustering. IEEE Trans. Knowl. Data Eng. 8, 2 (1996), 333–339. Google Scholar
Digital Library
- Athman Bouguettaya, Qi Yu, Xumin Liu, Xiangmin Zhou, and Andy Song. 2015. Efficient agglomerative hierarchical clustering. Expert Syst. Appl. 42, 5 (2015), 2785–2797. Google Scholar
Digital Library
- Craig Boutilier, Ronen I. Brafman, Carmel Domshlak, Holger H. Hoos, and David Poole. 2004. CP-nets: A tool for representing and reasoning with conditional ceteris paribus preference statements. J. Artific. Intell. Res. 21 (2004), 135–191. Google Scholar
Digital Library
- Sivadon Chaisiri, Bu-Sung Lee, and Dusit Niyato. 2012. Optimization of resource provisioning cost in cloud computing. IEEE Trans. Serv. Comput. 5, 2 (2012), 164–177. Google Scholar
Digital Library
- S. Chaisiri, D. Niyato, and B. Lee. 2014. Capacity planning for data center to support green computing. In Proceedings of JCSSE. 152–157.Google Scholar
- Jaihak Chung and Vithala R. Rao. 2012. A general consumer preference model for experience products: Application to internet recommendation services. J. Market. Res. 49, 3 (2012), 289–305.Google Scholar
Cross Ref
- Peijin Cong, Guo Xu, Tongquan Wei, and Keqin Li. 2020. A survey of profit optimization techniques for cloud providers. ACM Comput. Surveys 53, 2 (2020), 1–35. Google Scholar
Digital Library
- Cristina Cornelio, Judy Goldsmith, Nicholas Mattei, Francesca Rossi, and K. Brent Venable. 2013. Updates and uncertainty in CP-nets. In Proceedings of AI. Springer, 301–312. Google Scholar
Digital Library
- Debabrata Dash, Verena Kantere, and Anastasia Ailamaki. 2009. An economic model for self-tuned cloud caching. In Proceedings of ICDE. IEEE, 1687–1693. Google Scholar
Digital Library
- Marco Dorigo and L. M. Gambardella. 2016. Ant-Q: A reinforcement learning approach to the traveling salesman problem. In Proceedings of ICML. 252–260. Google Scholar
Digital Library
- Schahram Dustdar, Yike Guo, Benjamin Satzger, and Hong-Linh Truong. 2011. Principles of elastic processes. IEEE Internet Comput. 15, 5 (2011), 66–71. Google Scholar
Digital Library
- Sheik Mohammad Mostakim Fattah and Athman Bouguettaya. 2020. Event-based detection of changes in IaaS performance signatures. In Proceedings of SCC. IEEE, 210–217.Google Scholar
- Sheik Mohammad Mostakim Fattah, Athman Bouguettaya, and Sajib Mistry. 2018. A CP-net based qualitative composition approach for an IaaS provider. In Proceedings of WISE. Springer, 151–166.Google Scholar
- Sheik Mohammad Mostakim Fattah, Athman Bouguettaya, and Sajib Mistry. 2019. Long-term IaaS provider selection using short-term trial experience. In Proceedings of ICWS. IEEE, 304–311.Google Scholar
- Sheik Mohammad Mostakim Fattah, Athman Bouguettaya, and Sajib Mistry. 2020. Long-term IaaS selection using performance discovery. IEEE Trans. Services Comput. (2020). DOI:10.1109/TSC.2020.3036677Google Scholar
- Sheik Mohammad Mostakim Fattah, Athman Bouguettaya, and Sajib Mistry. 2020. Signature-based selection of IaaS cloud services. In Proceedings of ICWS. IEEE, 50–57.Google Scholar
- Alberto Fernández and Sergio Gómez. 2008. Solving non-uniqueness in agglomerative hierarchical clustering using multidendrograms. J. Classif. 25, 1 (2008), 43–65. Google Scholar
Digital Library
- Fernando Fernández and Manuela Veloso. 2006. Probabilistic policy reuse in a reinforcement learning agent. In Proceedings of AAMAS. ACM, 720–727. Google Scholar
Digital Library
- Siva Kumar Gavvala, Chandrashekar Jatoth, G. R. Gangadharan, and Rajkumar Buyya. 2019. QoS-aware cloud service composition using eagle strategy. Future Gen. Comput. Syst. 90 (2019), 273–290.Google Scholar
Cross Ref
- Adelina Gnanlet and Wendell G. Gilland. 2009. Sequential and simultaneous decision making for optimizing health care resource flexibilities. Decis. Sci. 40, 2 (2009), 295–326.Google Scholar
Cross Ref
- Íñigo Goiri, Jordi Guitart, and Jordi Torres. 2012. Economic model of a Cloud provider operating in a federated Cloud. Info. Syst. Front. 14 (2012), 827–843.Google Scholar
Cross Ref
- Anna Großwendt and Heiko Röglin. 2017. Improved analysis of complete-linkage clustering. Algorithmica 78, 4 (1 Aug 2017), 1131–1150. Google Scholar
Digital Library
- Kai Hwang, Xiaoying Bai, Yue Shi, Muyang Li, Wen-Guang Chen, and Yongwei Wu. 2015. Cloud performance modeling with benchmark evaluation of elastic scaling strategies. IEEE Trans. Parallel Distrib. Syst. 27, 1 (2015), 130–143. Google Scholar
Digital Library
- Sadeka Islam, Jacky Keung, Kevin Lee, and Anna Liu. 2012. Empirical prediction models for adaptive resource provisioning in the cloud. Future Gen. Comput. Syst. 28, 1 (2012), 155–162. Google Scholar
Digital Library
- You Jia, Jingdong Wang, Gang Zeng, Hongbin Zha, and Xian-Sheng Hua. 2010. Optimizing kd-trees for scalable visual descriptor indexing. In Proceedings of CVPR. IEEE, 3392–3399.Google Scholar
Cross Ref
- Wei Jiang, Dongwon Lee, and Songlin Hu. 2012. Large-scale longitudinal analysis of SOAP-based and RESTful web services. In Proc. of ICWS. 218–225. Google Scholar
Digital Library
- Yexi Jiang, Chang-shing Perng, Tao Li, and Rong Chang. 2011. Asap: A self-adaptive prediction system for instant cloud resource demand provisioning. In Proceedings of ICDM. IEEE, 1104–1109. Google Scholar
Digital Library
- Leslie Pack Kaelbling, Michael L. Littman, and Andrew W. Moore. 1996. Reinforcement learning: A survey. J. Artific. Intell. Res. 4 (1996), 237–285. Google Scholar
Digital Library
- Hisham A. Kholidy, Hala Hassan, Amany M. Sarhan, Abdelkarim Erradi, and Sherif Abdelwahed. 2014. Qos optimization for cloud service composition based on economic model. In Proceedings of GIoTS. Springer, 355–366.Google Scholar
- Sheryl E. Kimes and Gary M. Thompson. 2004. Restaurant revenue management: Determining the best table mix. Decis. Sci. 35, 3 (2004), 371–392.Google Scholar
Cross Ref
- Sven Koenig and Reid G. Simmons. 1993. Complexity analysis of real-time reinforcement learning. In Proceedings of AAAI. 99–107. Google Scholar
Digital Library
- Frank L. Lewis, Draguna Vrabie, and Kyriakos G. Vamvoudakis. 2012. Using natural decision methods to design optimal adaptive controllers. IEEE Control Syst. 32, 6 (2012), 76–105.Google Scholar
Cross Ref
- Sajib Mistry, Athman Bouguettaya, and Hai Dong. 2018. Economic Models for Managing Cloud Services. Springer. Google Scholar
Digital Library
- Sajib Mistry, Athman Bouguettaya, and Hai Dong. 2018. Long-term qualitative IaaS composition. In Economic Models for Managing Cloud Services. Springer, 77–110.Google Scholar
- Sajib Mistry, Athman Bouguettaya, Hai Dong, and Abdelkarim Erradi. 2016. Qualitative Economic Model for Long-Term IaaS Composition. Springer International Publishing, 317–332.Google Scholar
- Sajib Mistry, Athman Bouguettaya, Hai Dong, and Abdelkarim Erradi. 2017. Probabilistic qualitative preference matching in long-term IaaS composition. In Proceedings of ICSOC. Springer, 256–271.Google Scholar
- S. Mistry, A. Bouguettaya, H. Dong, and A. K. Qin. 2016. Metaheuristic optimization for long-term IaaS service composition. IEEE Trans. Serv. Comput.99 (2016), 1–1.Google Scholar
- Ahmed Moustafa and Minjie Zhang. 2013. Multi-objective service composition using reinforcement learning. In Proceedings of ICSOC. Springer, 298–312. Google Scholar
Digital Library
- Rémi Munos, Tom Stepleton, Anna Harutyunyan, and Marc Bellemare. 2016. Safe and efficient off-policy reinforcement learning. In Advances in Neural Information Processing Systems. MIT Press, 1054–1062. Google Scholar
Digital Library
- Fionn Murtagh and Pedro Contreras. 2012. Algorithms for hierarchical clustering: An overview. Wiley Interdisc. Rev.: Data Min. Knowl. Discov. 2, 1 (2012), 86–97.Google Scholar
Cross Ref
- Beomseok Nam and Alan Sussman. 2004. A comparative study of spatial indexing techniques for multidimensional scientific datasets. In Proceedings of SSDBM. IEEE, 171–180. Google Scholar
Digital Library
- Ranjan Pal and Pan Hui. 2013. Economic models for cloud service markets: Pricing and Capacity planning. Theoret. Comput. Sci. 496 (2013), 113–124. Google Scholar
Digital Library
- Edwin Pednault, Naoki Abe, and Bianca Zadrozny. 2002. Sequential cost-sensitive decision making with reinforcement learning. In Proceedings of SIGKDD. ACM, 259–268. Google Scholar
Digital Library
- Charles Reiss, John Wilkes, and Joseph L. Hellerstein. 2011. Google Cluster-usage Traces: Format + Schema. Technical Report. Google Inc., Mountain View, CA.Google Scholar
- John T. Robinson. 1981. The KDB-tree: A search structure for large multidimensional dynamic indexes. In Proceedings of ICMD. ACM, 10–18. Google Scholar
Digital Library
- G. R. Santhanam, S. Basu, and V. Honavar. 2009. Web service substitution based on preferences over non-functional attributes. In Proceedings of SCC. 210–217. Google Scholar
Digital Library
- Andrew J. Schaefer, Matthew D. Bailey, Steven M. Shechter, and Mark S. Roberts. 2005. Modeling medical treatment using Markov decision processes. In Operations Research and Health Care. Springer, 593–612.Google Scholar
- Timos K. Sellis, Nick Roussopoulos, and Christos Faloutsos. 1997. Multidimensional access methods: Trees have grown everywhere. In Proceedings of VLDB, Vol. 97. 13–14. Google Scholar
Digital Library
- Guy Shani, David Heckerman, and Ronen I. Brafman. 2005. An MDP-based recommender system. J. Mach. Learn. Res. 6(Sep.2005), 1265–1295. Google Scholar
Digital Library
- Bhanu Sharma, Ruppa K. Thulasiram, Parimala Thulasiraman, Saurabh K. Garg, and Rajkumar Buyya. 2012. Pricing cloud compute commodities: A novel financial economic model. In Proceedings of CCGRID. IEEE Computer Society, 451–457. Google Scholar
Digital Library
- Robert R. Sokal and F. James Rohlf. 1962. The comparison of dendrograms by objective methods. Taxon (1962), 33–40.Google Scholar
- Alireza Souri, Amir Masoud Rahmani, Nima Jafari Navimipour, and Reza Rezaei. 2020. A hybrid formal verification approach for QoS-aware multi-cloud service composition. Cluster Comput. 23, 4 (2020), 2453–2470.Google Scholar
Cross Ref
- T. Thanakornworakij, R. Nassar, C. B. Leangsuksun, and M. Paun. 2012. An economic model for maximizing profit of a cloud service provider. In Proceedings of ARES. 274–279. Google Scholar
Digital Library
- Hado Van Hasselt, Arthur Guez, and David Silver. 2016. Deep reinforcement learning with double q-learning. In Proceedings of AAAI. Google Scholar
Digital Library
- Blesson Varghese and Rajkumar Buyya. 2018. Next generation cloud computing: New trends and research directions. Future Gen. Comput. Syst. 79 (2018), 849–861. Google Scholar
Digital Library
- Hongbign Wang, Xin Chen, Qin Wu, Qi Yu, Xingguo Hu, Zibin Zheng, and Athman Bouguettaya. 2017. Integrating reinforcement learning with multi-agent techniques for adaptive service composition. ACM Trans. Auton. Adapt. Syst. 12, 2 (2017), 1–42. Google Scholar
Digital Library
- Hongbing Wang, Xingguo Hu, Qi Yu, Mingzhu Gu, Wei Zhao, Jia Yan, and Tianjing Hong. 2020. Integrating reinforcement learning and skyline computing for adaptive service composition. Info. Sci. 519 (2020), 141–160.Google Scholar
- Hongbing Wang, Shizhi Shao, Xuan Zhou, Cheng Wan, and Athman Bouguettaya. 2009. Web service selection with incomplete or inconsistent user preferences. In Proceedings of ICSOC. Springer, 83–98. Google Scholar
Digital Library
- Hongbing Wang, Jie Zhang, Wenlong Sun, Hongye Song, Guibing Guo, and Xiang Zhou. 2012. WCP-Nets: A weighted extension to CP-Nets for web service selection. In Proceedings of ICSOC. Springer. Google Scholar
Digital Library
- Hongbing Wang, Xuan Zhou, Xiang Zhou, Weihong Liu, Wenya Li, and Athman Bouguettaya. 2010. Adaptive service composition based on reinforcement learning. In Proceedings of ICSOC. Springer, 92–107.Google Scholar
- Xinyu Wang, Jianke Zhu, Zibin Zheng, Wenjie Song, Yuanhong Shen, and Michael R. Lyu. 2016. A spatial-temporal QoS prediction approach for time-aware web service recommendation. ACM Trans. Web 10, 1 (2016), 1–25. Google Scholar
Digital Library
- Christopher J. C. H. Watkins and Peter Dayan. 1992. Q-learning. Mach. Learn. 8, 3-4 (1992), 279–292.Google Scholar
Digital Library
- Hong Xu and Baochun Li. 2013. Dynamic cloud pricing for revenue maximization. IEEE Trans. Cloud Comput. 1, 2 (July 2013), 158–171. DOI:https://doi.org/10.1109/TCC.2013.15 Google Scholar
Digital Library
- Zhen Ye, Athman Bouguettaya, and Xiaofang Zhou. 2013. QoS-aware cloud service composition using time series. In Proceedings of ICSOC. Vol. 8274. 9–22. Google Scholar
Digital Library
- Zhen Ye, Athman Bouguettaya, and Xiaofang Zhou. 2014. Economic model-driven cloud service composition. ACM Trans. Internet Technol. 14, 2--3 (2014), 20. Google Scholar
Digital Library
- Z. Ye, S. K. Mistry, A. Bouguettaya, and H. Dong. 2014. Long-term QoS-aware cloud service composition using multivariate time series analysis. IEEE Trans. Serv. Comput. 99 (2014), 1–1.Google Scholar
- Qi Yu and Athman Bouguettaya. 2008. Framework for web service query algebra and optimization. ACM Trans. Web 2, 1 (2008), 1–35. Google Scholar
Digital Library
- Tao Yu, Yue Zhang, and Kwei-Jay Lin. 2007. Efficient algorithms for Web services selection with end-to-end QoS constraints. ACM Trans. Web 1, 1 (2007), 6–es. Google Scholar
Digital Library
- Sharrukh Zaman and Daniel Grosu. 2013. Combinatorial auction-based allocation of virtual machine instances in clouds. J. Parallel Distrib. Comput. 73, 4 (2013), 495–508. Google Scholar
Digital Library
- Huiyuan Zheng, Jian Yang, and Weiliang Zhao. 2016. Probabilistic QoS aggregations for service composition. ACM Trans. Web 10, 2 (2016), 1–36. Google Scholar
Digital Library
- Qian Zhu and Gagan Agrawal. 2010. Resource provisioning with budget constraints for adaptive applications in cloud environments. In Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing. ACM, 304–307. Google Scholar
Digital Library
- Guobing Zou, Qiang Lu, Yixin Chen, Ruoyun Huang, You Xu, and Yang Xiang. 2012. QoS-aware dynamic composition of web services using numerical temporal planning. IEEE Trans. Services Comput. 7, 1 (2012), 18–31. Google Scholar
Digital Library
Index Terms
Sequential Learning-based IaaS Composition
Recommendations
Qualitative Economic Model for Long-Term IaaS Composition
Service-Oriented ComputingAbstractWe propose a new qualitative economic model based optimization approach to compose an optimal set of infrastructure service requests over a long-term period. The economic model is represented as a temporal CP-Net to capture the provider’s dynamic ...
Probabilistic Qualitative Preference Matching in Long-Term IaaS Composition
Service-Oriented ComputingAbstractWe propose a qualitative similarity measure approach to select an optimal set of probabilistic Infrastructure-as-a-Service (IaaS) requests according to the provider’s probabilistic preferences over a long-term period. The long-term qualitative ...
Aggregating IaaS Service
SRII '11: Proceedings of the 2011 Annual SRII Global ConferenceInfrastructure-as-a-Service (IaaS) is the most acceptable Cloud Computing delivery model that CIO and IT managers are exploring as they relook at their IT infrastructure. However, the adoption of IaaS faces challenge/concerns such as provider lock-in, ...






Comments