The paper presents intelligent identification methods for Smart Grid based on Wide Area Measuring systems (WAMS) technology. The methods are based on intelligent process knowledge analysis. The knowledgebase is create...
详细信息
A fault detection scheme has been developed for an electromechanical steering actuator under closed-loop control. The closed-loop system is modeled as a 2nd order system with bounded parameter uncertainties given by t...
详细信息
The performance and reliability of the pitch controlsystems significantly influences the functional safety of wind turbines. In this paper an observer-based fault detection approach for a class of nonlinear systems, ...
详细信息
This paper is concerned with stabilizing open loop unstable fluidized bed spray granulation with internal product classification by means of nonlinear feedback control. The processdynamics are described by a populati...
详细信息
Fault-tolerant controlsystems with discrete-event dynamics allow for differing sets of design requirements, that specify the system's behaviour during nominal operation and in the case of component degradation or...
详细信息
We consider cooperative distributed model predictive control of a linear, timeinvariant, discrete-time plant, which consists of coupled subsystems. The cooperating controllers minimize a quadratic cost criterion subje...
详细信息
The present article details a method suitable for fault detection of hydraulic flight control system actuators. A model based method is discussed, which use the linear parameter-varying (LPV) framework, which leads to...
详细信息
Concentration control (C-control) strategy for (semi-)batch antisolvent crystallization processes has been recently developed with the aid of new sensors that measure in situ process variables. This control strategy g...
详细信息
This paper describes an approach to optimal management of hydrogen networks in refineries, focusing on the problems of reconfiguration that appears when, due to plant failures, the production of the hydrogen generatin...
详细信息
Server parameter tuning in virtualized data centers is crucial to performance and availability of hosted Internet applications. It is challenging due to high dynamics and burstiness of workloads, multi-tier service ar...
详细信息
ISBN:
(纸本)9780769546759
Server parameter tuning in virtualized data centers is crucial to performance and availability of hosted Internet applications. It is challenging due to high dynamics and burstiness of workloads, multi-tier service architecture, and virtualized server infrastructure. In this paper, we investigate automated and agile server parameter tuning for maximizing effective throughput of multi-tier Internet applications. A recent study proposed a reinforcement learning based server parameter tuning approach for minimizing average response time of multi-tier applications. Reinforcement learning is a decision making process determining the parameter tuning direction based on trial-and-error, instead of quantitative values for agile parameter tuning. It relies on a predefined adjustment value for each tuning action. However it is nontrivial or even infeasible to find an optimal value under highly dynamic and bursty workloads. We design a neural fuzzy control based approach that combines the strengths of fast online learning and self-adaptiveness of neural networks and fuzzy control. Due to the model independence, it is robust to highly dynamic and bursty workloads. It is agile in server parameter tuning due to its quantitative control outputs. We implement the new approach on a testbed of virtualized HP ProLiant blade servers hosting RUBiS benchmark applications. Experimental results demonstrate that the new approach significantly outperforms the reinforcement learning based approach for both improving effective system throughput and minimizing average response time.
暂无评论