A proactive cloud management architecture for private clouds

Dapeng Dong, John Herbert

Research output: Contribution to journalConference articlepeer-review

1 Citation (Scopus)


Operation management for a private cloud infrastructure faces many challenges including efficient resource allocation, load-balancing, and quick response to real-time workload changes. Traditional manual IT operation management is inadequate for this highly dynamic and complex environment. This work presents a distributed service architecture which is designed to provide an automated, shared, off-site operation management service for private clouds. The service architecture incorporates important concepts such as: Metric Templates for minimising the network overhead for transmission of cloud metrics, a Cloud Snapshot that provides a global view of the current status of the cloud, supporting optimal decision making, and a Calendar-based Data Storage Model to reduce the storage required for cloud metric data and increase analysis performance. A proactive response to cloud events is generated based on statistical analysis of historical metrics and predicted usage. The architecture, functional components and operation management strategies are described. A prototype implementation of the proposed architecture was deployed as a service on the IBM SmartCloud. The effectiveness and usability of the proposed proactive operation management solution has been comprehensively evaluated using a simulated private cloud with dynamic workloads.

Original languageEnglish
Article number6676759
Pages (from-to)701-708
Number of pages8
JournalIEEE International Conference on Cloud Computing, CLOUD
Publication statusPublished - 2013
Externally publishedYes
Event2013 IEEE 6th International Conference on Cloud Computing, CLOUD 2013 - Santa Clara, CA, United States
Duration: 27 Jun 20132 Jul 2013


  • Architecture
  • Cloud
  • Operation Management


Dive into the research topics of 'A proactive cloud management architecture for private clouds'. Together they form a unique fingerprint.

Cite this