An Adaptive Multi-Agent-Based Framework for Computation Management on Hybrid Cloud Environments

• Main Authors: Yo-Ming Lo, 羅祐民
• Other Authors: Wei-Jen Wang
• Format: Others
• Language: zh-TW
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/12211488275037281673

碩士 === 國立中央大學 === 資訊工程研究所 === 100 === A typical hybrid cloud consists of a private data center and a portion of a public cloud. It can potentially scale up the computing pool of a private cloud on demand. Therefore, it can reduce the cost of building a private cloud (data center) and transfer the risk to the cloud service provider. In this work, we adopt the concepts of multi-agent systems and cloud computing systems, and develop a framework to support self-adaptability and dynamic load balancing in a self-provisioning cloud environment. In the case that the workload of the private data center is too high, the proposed framework creates more computing resources in the public cloud automatically, and moves the ultra-burden tasks to the public cloud in order to reduce the workload of the private data center. The proposed framework employs the multi-agent technique to manage all resources, to monitor applications, and to negotiate all actions in the hybrid cloud. We have designed different adaptive models for different types of applications in the proposed system architecture, including Hadoop-based applications, MPI-based applications, and web services. We have built a prototype of the proposed system architecture to demonstrate how it is able to perform self-adaptation and load balancing.