A Study of Different QoS Management Techniques in Cloud Computing
Mandeep Devgan1, Kanwalvir Singh Dhindsa2
1Mandeep Devgan, Department of Information Technology, Chandigarh Engineering College, Landran, Mohali, India.
2Kanwalvir Singh Dhindsa, Department of CSE/IT, Baba Banda Singh Bahadur Engineering College, Fatehgarh Sahib.
Manuscript received on June 05, 2013. | Revised Manuscript received on June 29, 2013. | Manuscript published on July 05, 2013. | PP: 37-41 | Volume-3 Issue-3, July 2013. | Retrieval Number: C1611073313/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Cloud Services are becoming a major system for constructing distributed systems. Service-oriented architecture (SOA) is widely working in electronic business, electronic -government, automotive systems, multimedia services, process control, finance, and a lot of other domains. Quality-of-Service (QoS) is usually employed for describing the non-functional characteristics of Cloud services and employed as an important differentiating point of different Cloud services. With the prevalence of Cloud services on the Internet, Cloud service QoS management is becoming more and more important. This paper first study a distributed QoS evaluation technique for Cloud services. In this technique, users in different geographic locations collaborative with each other to evaluate the target Cloud services and share their observed Cloud service QoS information. Based on this Cloud service evaluation technique, several large-scale distributed evaluations are conducted on many real-world Cloud services and the detailed evaluation results are released for future research. Cloud service evaluation is time and resource consuming. Moreover, in some scenarios, Cloud service evaluation may not be possible (e.g., the Cloud service invocation is charged, too many service candidate, etc.). Therefore, Cloud service QoS prediction approaches are becoming more and more attractive. In order to prediction the Cloud service QoS as accurate as possible, this paper studies three prediction methods. The first prediction method employs the information of neighborhoods for making missing value prediction. The second method discusses matrix factorization techniques to enhance the prediction accuracy. The third method predicts the ranking of the target Cloud services instead of QoS values. The predicted Cloud service QoS values can be employed to build fault-tolerant service-oriented systems. In the area of service computing, the cost for developing multiple redundant components is greatly reduced, since the functionally equivalent Cloud services are provided by different organizations and are accessible via Internet. Hence, based on the predicted QoS values, this paper study two methods for building fault tolerance Cloud services. Firstly, this paper studies an adaptive fault tolerance strategy for Cloud services. Then, this paper presents an optimal fault tolerance strategy selection technique for Cloud services.
Keywords: QoS, Evaluation, Prediction, Active User, Ranking.