DeepScaler: Holistic Autoscaling for Microservices Based on Spatiotemporal GNN with Adaptive Graph Learning

TL;DR

DeepScaler is a novel deep learning-based autoscaling approach for microservices that models complex service dependencies using spatiotemporal graph neural networks, improving resource allocation and reducing SLA violations.

Contribution

It introduces an adaptive affinity matrix learning method and an attention-based GCN to better capture service dependencies for more effective autoscaling.

Findings

Reduces SLA violations by 41% on average.

Achieves more accurate resource allocation.

Adapts to dynamic service dependency changes.

Abstract

Autoscaling functions provide the foundation for achieving elasticity in the modern cloud computing paradigm. It enables dynamic provisioning or de-provisioning resources for cloud software services and applications without human intervention to adapt to workload fluctuations. However, autoscaling microservice is challenging due to various factors. In particular, complex, time-varying service dependencies are difficult to quantify accurately and can lead to cascading effects when allocating resources. This paper presents DeepScaler, a deep learning-based holistic autoscaling approach for microservices that focus on coping with service dependencies to optimize service-level agreements (SLA) assurance and cost efficiency. DeepScaler employs (i) an expectation-maximization-based learning method to adaptively generate affinity matrices revealing service dependencies and (ii) an attention-based graph convolutional network to extract spatio-temporal features of microservices by aggregating neighbors' information of graph-structural data. Thus DeepScaler can capture more potential service dependencies and accurately estimate the resource requirements of all services under dynamic workloads. It allows DeepScaler to reconfigure the resources of the interacting services simultaneously in one resource provisioning operation, avoiding the cascading effect caused by service dependencies. Experimental results demonstrate that our method implements a more effective autoscaling mechanism for microservice that not only allocates resources accurately but also adapts to dependencies changes, significantly reducing SLA violations by an average of 41% at lower costs.