A dynamic cloud service selection strategy using adaptive learning agents

Cloud service selection with multi-type cloud computing resources is a novel research and catching increasing attention. To help users efficiently select and integrate their desired cloud services, the agent-based computing paradigm has emerged. In this work, we propose an intermediary service agent model called ISAM which lets each intermediary service agent manage some clustered cloud services of the same type. And based on this model, a dynamic cloud service selection strategy named DCS is given. The core of DCS uses an adaptive learning mechanism consisting of the incentive and forgetting functions, which is devised to dynamically perform the optimising service selections and to return integrated solutions to users. A set of dynamic cloud service selection algorithms are also presented to implement our mechanism. The results of the simulation experiments show that our strategy has better overall performance and efficiency in obtaining a high quality services solution.