Reinforcement Learning-based Dynamic Bandwidth Provisioning

This paper proposes an adaptive provisioning mechanism that determines at regular intervals the amount of bandwidth to provision for each PHB aggregate, based on traffic conditions and feedback received about the extent to which QoS is being met. The mechanism adjusts to minimize a penalty function that is based on the QoS requirements agreed upon in the service level agreement (SLA). The novel use of a continuous-space, gradient-descent reinforcement learning algorithm, enables the mechanism to require neither accurate traffic characterization nor any assumptions about the network model. Using ns-2 simulations, we show that our algorithm is able to converge to a policy that provisions bandwidth to meet QoS requirements. ###########- Continuous-space Reinforcement Learning, Adaptive bandwidth provisioning, Quality of Service, Differentiated Services. I.