Online Machine Learning for Cloud Resource Provisioning of Microservice Backend Systems

Microservices are bundled and generating traffic on the backend systems that need to scale on demand. When microservices generate variant and unexpected, the challenge is to classify the workload on the backend systems and adjust the scaling policy to reflect the resource demand timely and accurately. In this paper, we propose a microservice architecture that encapsulates functions of monitoring metrics and learning workload pattern. Then this service architecture is used to predict the future workload for decision making on resource provisioning. We deploy two machine learning algorithms and predict the resource demand of the backend systems of microservices emulated by a Netflix workload benchmark application. This service architecture presents an integrated solution of implementing self-managing cloud data services under variant workload.