AI-Driven Self-Healing Container Orchestration Framework for Energy-Efficient Kubernetes Clusters

AI-driven orchestration Kubernetes energy efficiency self-healing systems predictive scaling carbon footprint reduction United States of America

Authors

  • Deepak Kaul Marriott International, Inc Country: United States of America., United States
Volume 2024
Articles
December 18, 2024

Downloads

The rising adoption of Kubernetes for container orchestration in cloud-native architectures has introduced significant challenges in balancing energy efficiency with system resilience, particularly in large-scale distributed environments. This research addresses these challenges by proposing an AI-Driven Self-Healing Container Orchestration Framework that optimizes energy usage while maintaining fault tolerance and high availability in Kubernetes clusters.

The framework employs advanced machine learning models for predictive fault detection, real-time anomaly detection, and automated recovery processes, reducing manual intervention and system downtime. It integrates energy optimization algorithms that dynamically adjust resource allocation based on workload demand, cluster utilization, and fault recovery requirements. These AI-driven capabilities enable the framework to not only self-heal from failures but also reduce energy consumption by optimizing resource provisioning and scaling decisions.

Key contributions of this work include:

  1. The design and implementation of a modular self-healing architecture that seamlessly integrates with Kubernetes.
  2. Development of AI models for fault prediction and anomaly detection tailored to the dynamic nature of containerized environments.
  3. A novel energy optimization strategy that reduces power consumption while maintaining system performance and reliability.
  4. Validation of the framework's effectiveness through extensive experiments, demonstrating improved energy efficiency, reduced recovery times, and enhanced fault tolerance compared to traditional approaches.

This study provides valuable insights for researchers and practitioners in the fields of AI, container orchestration, and energy-efficient computing. The proposed framework represents a significant step toward sustainable and resilient cloud-native systems, paving the way for future advancements in intelligent container management.