The Cost Advantage of Virtual Machine Migrations: Empirical Insights into Amazon's EC2 Marketspace

2025-08-20

AI Summary

This paper addresses the cost-effectiveness of virtual machine (VM) portfolio optimization and runtime cross-market migration in multi-market cloud environments. To tackle Amazon EC2’s heterogeneous pricing structure, we propose an empirically grounded, dynamic migration–based cost-optimization strategy. Our approach integrates real-time EC2 spot pricing data with Bitbrains’ realistic VM workload traces to construct and comparatively analyze a cross-market cost model. Key contributions include: (1) demonstrating that heterogeneous VM portfolios significantly reduce total expenditure; (2) identifying runtime migration over horizons of 6 hours to 1 year as most cost-effective; and (3) revealing substantial optimization potential for long-term, low-utilization resources. Evaluated on two domain-specific datasets, our method achieves an average cost reduction of 18.7% through cross-market migration, establishing a practical, dynamic cost-optimization paradigm for elastic cloud resource scheduling.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Hardware-aware ML

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

In recent years, cloud providers have introduced novel approaches for trading virtual machines. For example, Virtustream introduced so-called muVMs to charge cloud computing resources while other providers such as Google, Microsoft, or Amazon re-invented their marketspaces. Today, the market leader Amazon runs six marketspaces for trading virtual machines. Consumers can purchase bundles of virtual machines, which are called cloud-portfolios, from multiple marketspaces and providers. An industry-relevant field of research is to identify best practices and guidelines on how such optimal portfolios are created. In the paper at hand, a cost analysis of cloud portfolios is presented. Therefore, pricing data from Amazon was used as well as a real virtual machine utilization dataset from the Bitbrains datacenter. The results show that a cost optimum can only be reached if heterogeneous portfolios are created where virtual machines are purchased from different marketspaces. Additionally, the cost-benefit of migrating virtual machines to different marketplaces during runtime is presented. Such migrations are especially cost-effective for virtual machines of cloud-portfolios which run between 6 hours and 1 year. The paper further shows that most of the resources of virtual machines are never utilized by consumers, which represents a significant future potential for cost optimization. For the validation of the results, a second dataset of the Bitbrains datacenter was used, which contains utility data of virtual machines from a different domain of application.

Problem

• Analyzing cost optimization strategies for cloud portfolios across marketplaces
• Evaluating cost benefits of migrating virtual machines during runtime
• Identifying underutilized resources in virtual machines for cost savings

Innovation

• Analyzing Amazon pricing and Bitbrains utilization data
• Creating heterogeneous cloud portfolios from multiple marketspaces
• Migrating VMs between marketspaces during runtime optimization