Understanding Cross-Cloud Interconnects: Hands-On Measurements and Cost Optimization

2026-05-31

AI Summary

This study addresses the challenges of cross-cloud data transfer, including traffic volatility, high fixed leasing costs, and multi-day provisioning delays, which collectively hinder cost optimization. The work presents the first systematic empirical investigation of Cross-Cloud Interconnect (CCI) services and introduces ToggleCCI, a dynamic cost optimization algorithm that intelligently switches between VPN and dedicated interconnects to cope with demand uncertainty and provisioning latency. ToggleCCI integrates sliding-window cost analysis with an online decision-making mechanism and offers theoretical guarantees of asymptotic optimality. Experiments based on real-world traffic traces between AWS and GCP demonstrate that ToggleCCI consistently approaches the performance of the optimal static strategy across diverse scenarios while significantly reducing data transfer costs.

Abstract

New services such as Google Cross-Cloud Interconnect (CCI) address the rise in fast and large-scale cross-cloud data transfers. CCI offers dedicated high-throughput links with low per-GB transfer costs, but also involves high fixed leasing fees and multi-day provisioning delays. This combination makes cost optimization difficult because traffic patterns are unpredictable. This paper presents the first comprehensive study of CCI-like services. We begin with an empirical characterization of CCI and its alternatives using direct measurements across AWS-GCP interconnects. We then introduce ToggleCCI, a new dynamic cost-optimization algorithm designed to handle provisioning delays and uncertainty in future demand. ToggleCCI adapts by switching between VPN and CCI based on cost trends observed over a sliding time window. We prove that ToggleCCI achieves asymptotic optimality under sustained high-demand or low-demand regimes. Finally, using real-world traffic traces, we show that ToggleCCI consistently tracks the best static policy for each scenario and delivers substantial cost savings.

Problem

• Cross-Cloud Interconnect
• cost optimization
• provisioning delay
• traffic unpredictability
• cloud data transfer

Innovation

• Cross-Cloud Interconnect
• Cost Optimization
• Dynamic Switching
• Provisioning Delay
• ToggleCCI