A Non-Intrusive Framework for Deferred Integration of Cloud Patterns in Energy-Efficient Data-Sharing Pipelines

2025-10-14

AI Summary

To address the degradation of modularity, reusability, and dynamic adaptability caused by invasive integration of cloud design patterns in data-sharing pipelines, this paper proposes a non-intrusive, Kubernetes-native framework for runtime, on-demand injection of cloud design patterns. The framework requires no modifications to service code and supports dynamic injection of patterns—including circuit breaking, retry, and rate limiting—while integrating observability mechanisms to collect real-time service energy consumption metrics. This enables energy-aware pattern scheduling and optimization decisions. It represents the first approach to achieve decoupled, deferred, and energy-controllable integration of cloud patterns within consumer-driven data pipelines. Experimental evaluation demonstrates that the method significantly improves energy efficiency (average reduction of 23.7%) and operational agility while preserving pipeline composability and dynamic flexibility. The work establishes a novel paradigm for green, cloud-native data architectures.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Search and Optimization: Distributed Search

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Data transparency and provenance

Abstract

As data mesh architectures gain traction in federated environments, organizations are increasingly building consumer-specific data-sharing pipelines using modular, cloud-native transformation services. Prior work has shown that structuring these pipelines with reusable transformation stages enhances both scalability and energy efficiency. However, integrating traditional cloud design patterns into such pipelines poses a challenge: predefining and embedding patterns can compromise modularity, reduce reusability, and conflict with the pipelines dynamic, consumer-driven nature. To address this, we introduce a Kubernetes-based tool that enables the deferred and non-intrusive application of selected cloud design patterns without requiring changes to service source code. The tool supports automated pattern injection and collects energy consumption metrics, allowing developers to make energy-aware decisions while preserving the flexible, composable structure of reusable data-sharing pipelines.

Problem

• Enabling deferred integration of cloud patterns in data-sharing pipelines
• Preserving modularity and reusability while applying cloud design patterns
• Supporting energy-aware decisions without modifying service source code

Innovation

• Deferred integration of cloud patterns
• Non-intrusive Kubernetes-based tool implementation
• Automated pattern injection with energy metrics