Toward ML-centric cloud platforms

Abstract

contributed articles IMAGE BY MARCEL CLEMENS resource management using supervised learning techniques, such as gradient-boosted trees and neural networks, or reinforcement learning. We also discuss why ML is often preferable to traditional non-ML techniques. Public cloud providers are starting to explore ML-based resource management in production. 9,14 For example, Google uses neural networks to optimize fan speeds and other energy knobs. 14 In academia, researchers have proposed using collaborative filteringa common technique in recommender systems-in scheduling containers for reduced with in-server performance interference. 12 Others proposed using reinforcement learning to adjust the resources allocated to co-located VMs. 24 Later, we discuss other opportunities for ML-based management. Despite these prior efforts and opportunities, it is currently unclear how best to integrate ML into cloud resource management. In fact, prior approaches differ in multiple dimensions. For example, in some cases, the ML technique produces insights/ predictions about the workload or infrastructure; in others, it produces actual resource management actions. In some cases, the ML is deeply integrated with the resource manager; in others, it is completely separate. In all cases, the ML addresses a single management problem; a different problem requires CLOUD PLATFORMS, SUCH as Microsoft Azure, Amazon Web Services (AWS), and Google Cloud Platform, are tremendously complex. For example, the Azure Compute fabric governs all the physical and virtualized resources running in Microsoft's datacenters. Its main resource management systems include virtual machine (VM) and container (hereafter we refer to VMs and containers simply as "containers") scheduling, server and container health monitoring and repairs, power and energy management, and other management functions. Cloud platforms are also extremely expensive to build and operate, so providers have a strong incentive to optimize their use. A nascent approach is to leverage machine learning (ML) in the platforms'

Machine Learning-based Orchestration of Containers: A Taxonomy and Future Directions

“…With such fast-growing complexity of application management in cloud platforms, cloud service providers have a strong motivation to optimize their container orchestration policies by leveraging machine ML techniques [27].…”

“…Such applications could be initially easy to develop and maintain at a small scale. For example, Microsoft Azure [49] still supports automated single-containerbased application deployment for enterprise solutions where the business logic is not feasible for building complex multi-component models. However, the consistent development and enrichment of monolithic applications would inevitably lead to incremental application sizes and complexity [50].…”

Autonomous IoT Device Management Systems: Structured Review and Generalized Cognitive Model

“…Such modularization allows specialized subcomponents for a particular task. This enables a better understanding and control of the data flow and of the different states of the system, making it easier to integrate mechanisms into managers and to support black-box designs [72]. Another benefit is that modularity ensures that parts of the system can be replaced or extended independently if the requirements or the understanding of the problem change, which can reduce the risk of project failures due to high complexity.…”

Demonstration Paper: Monitoring Machine Learning Contracts with QoA4ML

“…Today, Machine Learning as a Service (MLaaS) has become a popular business model [1]. There is a strong demand for flexible ways to establish and monitor ML service contracts/agreements among multiple stakeholders, such as the ML customer, the ML provider, and the infrastructure provider.…”