Selection of Cloud Computing Services Using Reinforcement Learning

ANA SOFÍA ZALAZAR; SILVIO GONNET; HORACIO LEONE

Naiguatá, Vargas

Conferencia; Conferencia Lationamericana en Informática (CLEI 2013); 2013

CLEI

Cloud computing is a new business paradigm managed through Internet, where different providers offer their services using scalable virtualization. Services selection depends of the service level agreement, which is a type of contract signed between providers and consumers, and it identifies functional and quality parameters of services. Because of the stochastic and dynamic nature of cloud contexts, there is not a simple procedure for composing web services of different providers. In this paper, we propose a mechanism for composing services using artificial intelligence, and we demonstrate that reinforcement learning principles and Q-learning algorithm can be applied for cloud environments, where specific purposes are not clearly specified and the controller must take action according to a mechanism of rewards and penalties.