TY - GEN
T1 - Automated and dynamic application accuracy management and resource provisioning in a cloud environment
AU - Vijayakumar, Smita
AU - Zhu, Qian
AU - Agrawal, Gagan
PY - 2010
Y1 - 2010
N2 - The recent emergence of cloud computing is making the vision of utility computing realizable, i.e., computing resources and services from a cloud can be delivered, utilized, and paid for in the same fashion as utilities like water or electricity. This, however, creates new resource provisioning problems. Because of the pay-as-you-go model, resource provisioning should be performed carefully. Resource provisioning can be particularly challenging for adaptive applications, where there can be a tradeoff between the application Quality of Service (QoS), or accuracy, and the resource costs incurred. In this paper, we consider adaptive streaming applications where a user wants to achieve the minimum resource costs while maintaining a specified accuracy goal. We present a dynamic and automated framework which can adapt the adaptive parameters to meet the specific accuracy goal, and then dynamically converge to near-optimal resource allocation. Our solution can handle unexpected changes in the data distribution characteristics and/or rates. We evaluate our approach using two streaming applications and demonstrate the effectiveness of our framework.
AB - The recent emergence of cloud computing is making the vision of utility computing realizable, i.e., computing resources and services from a cloud can be delivered, utilized, and paid for in the same fashion as utilities like water or electricity. This, however, creates new resource provisioning problems. Because of the pay-as-you-go model, resource provisioning should be performed carefully. Resource provisioning can be particularly challenging for adaptive applications, where there can be a tradeoff between the application Quality of Service (QoS), or accuracy, and the resource costs incurred. In this paper, we consider adaptive streaming applications where a user wants to achieve the minimum resource costs while maintaining a specified accuracy goal. We present a dynamic and automated framework which can adapt the adaptive parameters to meet the specific accuracy goal, and then dynamically converge to near-optimal resource allocation. Our solution can handle unexpected changes in the data distribution characteristics and/or rates. We evaluate our approach using two streaming applications and demonstrate the effectiveness of our framework.
KW - Cloud computing
KW - Dynamic resource provisioning
KW - Streaming applications
UR - http://www.scopus.com/inward/record.url?scp=79951586903&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79951586903&partnerID=8YFLogxK
U2 - 10.1109/GRID.2010.5697963
DO - 10.1109/GRID.2010.5697963
M3 - Conference contribution
AN - SCOPUS:79951586903
SN - 9781424493487
T3 - Proceedings - IEEE/ACM International Workshop on Grid Computing
SP - 33
EP - 40
BT - Proceedings of the 2010 11th IEEE/ACM International Conference on Grid Computing, Grid 2010
T2 - 2010 11th IEEE/ACM International Conference on Grid Computing, Grid 2010
Y2 - 25 October 2010 through 29 October 2010
ER -