SQLR: Short-Term Memory Q-Learning for Elastic Provisioning
This addresses cloud providers' need to efficiently manage resources for SaaS applications, though it appears incremental as it builds on reinforcement learning for a specific domain.
The paper tackles the problem of agile resource provisioning in cloud systems to meet Service Level Agreements while avoiding over-provisioning, achieving a 25% reduction in provisioned resources with less than 1% service unavailability and similar response times to an over-provisioned system.
As more and more application providers transition to the cloud and deliver their services on a Software as a Service (SaaS) basis, cloud providers need to make their provisioning systems agile enough to meet Service Level Agreements. At the same time they should guard against over-provisioning which limits their capacity to accommodate more tenants. To this end we propose SQLR, a dynamic provisioning system employing a customized model-free reinforcement learning algorithm that is capable of reusing contextual knowledge learned from one workload to optimize resource provisioning for other workload patterns. SQLR achieves results comparable to those where resources are unconstrained, with minimal overhead. Our experiments show that we can reduce the amount of provisioned resources by almost 25% with less than 1% overall service unavailability (due to blocking) while delivering similar response times as those of an over-provisioned system.