Dataset Information

Power and Performance Management in Nonlinear Virtualized Computing Systems via Predictive Control.

ABSTRACT: The problem of power and performance management captures growing research interest in both academic and industrial field. Virtulization, as an advanced technology to conserve energy, has become basic architecture for most data centers. Accordingly, more sophisticated and finer control are desired in virtualized computing systems, where multiple types of control actions exist as well as time delay effect, which make it complicated to formulate and solve the problem. Furthermore, because of improvement on chips and reduction of idle power, power consumption in modern machines shows significant nonlinearity, making linear power models(which is commonly adopted in previous work) no longer suitable. To deal with this, we build a discrete system state model, in which all control actions and time delay effect are included by state transition and performance and power can be defined on each state. Then, we design the predictive controller, via which the quadratic cost function integrating performance and power can be dynamically optimized. Experiment results show the effectiveness of the controller. By choosing a moderate weight, a good balance can be achieved between performance and power: 99.76% requirements can be dealt with and power consumption can be saved by 33% comparing to the case with open loop controller.

SUBMITTER: Wen C

PROVIDER: S-EPMC4520487 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Power and Performance Management in Nonlinear Virtualized Computing Systems via Predictive Control.

Wen Chengjian C Mu Yifen Y

PloS one 20150730 7

The problem of power and performance management captures growing research interest in both academic and industrial field. Virtulization, as an advanced technology to conserve energy, has become basic architecture for most data centers. Accordingly, more sophisticated and finer control are desired in virtualized computing systems, where multiple types of control actions exist as well as time delay effect, which make it complicated to formulate and solve the problem. Furthermore, because of improv ...[more]

PMID: 26225769

Similar Datasets

Project description:Manual wheelchair propulsion is known to be inefficient and causes upper extremity pain, fatigue, and injury. Power-assisted wheelchairs can mitigate these effects through motors that reduce users' effort and load during propulsion. Among the different control strategies proposed to govern the user-wheelchair interaction, impedance control-based ones appear to be the most natural and effective. It can change the apparent dynamical properties of the wheelchair, particularly mass and friction, and automatically compensate for external disturbances such as terrain conditions. This study investigates the advantages and disadvantages of this control strategy employing predictive simulations of locomotion with power-assisted wheelchairs in different scenarios. The simulations are generated using a biomechanically realistic model of the upper extremities and their interaction with the power-assisted wheelchair by solving an optimal control problem. Investigated scenarios include steady-state locomotion vs. a transient maneuver starting from rest, movement on a ramp vs. a level surface, and different choices of reference model parameters. The results reveal that the investigated impedance control-based strategy can effectively reproduce the reference model and reduce the user's effort, with a more significant effect of inertia in the transient maneuver and of friction in steady-state locomotion. However, the simulations also show that imposing a first-order, linear reference model with constant parameters can produce disadvantageous locomotion patterns, particularly in the recovery phase, leading to unnecessary energy dissipation and consequent increase in energy consumption from the batteries. These observations indicate there is room for improvement, for instance, by exploring energy regeneration in the recovery phase or by switching reference model nature or parameters along the cycle. To the best of our knowledge, this is the first investigation of impedance control-based strategies for power-assisted wheelchairs using predictive simulations and a realistic, nonlinear model of the user-wheelchair system.

Dataset Information

Power and Performance Management in Nonlinear Virtualized Computing Systems via Predictive Control.

Publications

Power and Performance Management in Nonlinear Virtualized Computing Systems via Predictive Control.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets