Power-Aware Modeling and Autonomic Management Framework for Distributed Computing Systems

Energy consumption is a critical concern in large-scale distributed computing systems, yet traditional approaches lack sophistication in managing power while maintaining quality of service. This work is innovative in applying control-theoretic approaches to autonomously manage power consumption, adapting system behavior to workload characteristics and environmental conditions.

This paper presents a power-aware modeling and autonomic management framework for distributed computing systems. The work develops a predictive power management approach that combines power consumption modeling with control techniques to minimize power consumption while maintaining desired system response times.

The framework demonstrates development of power consumption models for multi-tier systems using offline regression and online Kalman filtering techniques. Predictive control approaches successfully minimize power consumption while maintaining response time constraints, showing significant potential for reducing operational costs and environmental impact.