Decentralized coordination during planning and execution phase of MAPE-K for autonomic cloud environment / Ahmad Izzuddin Yusof

Managing coordination between Autonomic Managers in the autonomic cloud environment requires an effective control mechanism to handle issues, namely, the coordination conflict between Autonomic Managers during planning and execution phase of MAPE-K framework. This framework provides a primary control loop in managing automated adaptation process with multiple autonomic managers. Existing work have address autonomic managers being designed to address certain problem, but issue remains in coordinating the autonomic manager within decentralized environment for an appropriate and effective global self-adaptive management. The objective of this research is to show and prove that coordination between Autonomic Managers with negotiation and synchronization protocol during planning and execution phase respectively, able to resolve this issue and providing better overall control within the adaptation process. This research introduces a new specialty and novelty coordination model by combining negotiation and synchronization during planning and execution phase accordingly based on the MAPE-K control loop. Negotiation allows two parties to discuss to meet particular agreement while synchronization controls execution process according to agreed negotiation result. This new coordination model is evaluated by using the enhanced CloudSim simulator by integrating with a message broker. The result from the experiment shows that combination of negotiation and synchronization can manage coordination conflicts during a runtime adaptation.