Reclaimer: A Reinforcement Learning Approach to Dynamic Resource Allocation for Cloud Microservices
This addresses resource inefficiency and QoS violations in cloud microservices, offering a practical improvement over existing solutions.
The paper tackles dynamic resource allocation for cloud microservices to minimize CPU usage while meeting QoS requirements, achieving reductions of 38.4% to 74.4% compared to industry standards and 27.5% to 58.1% versus state-of-the-art methods.
Many cloud applications are migrated from the monolithic model to a microservices framework in which hundreds of loosely-coupled microservices run concurrently, with significant benefits in terms of scalability, rapid development, modularity, and isolation. However, dependencies among microservices with uneven execution time may result in longer queues, idle resources, or Quality-of-Service (QoS) violations. In this paper we introduce Reclaimer, a deep reinforcement learning model that adapts to runtime changes in the number and behavior of microservices in order to minimize CPU core allocation while meeting QoS requirements. When evaluated with two benchmark microservice-based applications, Reclaimer reduces the mean CPU core allocation by 38.4% to 74.4% relative to the industry-standard scaling solution, and by 27.5% to 58.1% relative to a current state-of-the art method.