🤖 AI Summary
Traditional static data replication strategies in large-scale distributed systems struggle to adapt to dynamic workloads and sudden failures, resulting in low resource utilization and prolonged downtime. To address this, this paper proposes a machine learning–based adaptive replication mechanism that jointly optimizes failure prediction and replica placement using real-time monitoring data, integrating time-series forecasting with deep reinforcement learning. Its key innovation lies in the first end-to-end, fine-grained, online integration of predictive analytics and policy decision-making into a closed-loop self-evolving framework for replication strategy adaptation. Experimental evaluation demonstrates that the proposed approach reduces average downtime by 42.7% and improves storage resource utilization by 31.5% compared to representative static and heuristic baselines, while significantly enhancing fault tolerance resilience. These results validate the feasibility and effectiveness of intelligent, autonomous data replication in production-scale distributed systems.
📝 Abstract
This research paper investigates how machine learning-driven data replication strategies can enhance fault tolerance in large-scale distributed systems. Traditional replication methods, which rely on static configurations, often struggle to adapt to dynamic workloads and unexpected failures, leading to inefficient resource utilization and prolonged downtime. By integrating machine learning techniques-specifically predictive analytics and reinforcement learning. The study proposes adaptive replication mechanisms capable of forecasting system failures and optimizing data placement in real time. Through an extensive literature review, qualitative analysis, and comparative evaluations with traditional approaches, the paper identifies key limitations in existing replication strategies and highlights the transformative potential of machine learning in creating more resilient, self-optimizing systems. The findings underscore both the promise and the challenges of implementing ML-driven solutions in real-world environments, offering recommendations for future research and practical deployment in cloud-based and enterprise systems.