Integrated Monitoring and Control for Performance Management of Distributed Enterprise Systems

Large enterprise systems must simultaneously achieve multiple quality of service objectives including response time, throughput, and power consumption under varying workload conditions. This work innovates by integrating state estimation with model predictive control to adjust system parameters and maintain performance objectives. The approach accounts for complex system dynamics including bottleneck resources and context switching overhead that traditional queuing models overlook.

This paper presents an integrated monitoring and control framework for distributed enterprise systems that estimates system state from limited measurements and applies feedback control to achieve multiple quality of service objectives. The work develops system models that characterize performance behavior, applies exponential Kalman filtering to estimate service times and delays, and implements a feedback controller that optimizes multiple performance objectives. The approach demonstrates integration of monitoring, modeling, and control for managing distributed system performance.

Experiments demonstrate effective integration of monitoring and control for multi-tier systems achieving multiple quality of service objectives. Results show accurate system state estimation using Kalman filtering and effective parameter adjustment through feedback control. The framework achieves 18% power savings while maintaining response time constraints through integrated management of CPU frequency and resource allocation.