Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Internal Server State Estimation Using Event-based Particle Filtering

Ruuskanen, Johan LU orcid and Cervin, Anton LU orcid (2018) 4th International Conference on Event-Based Control, Communication and Signal Processing
Abstract
Closed-loop control of cloud resources requires there to be measurements readily available from the process in order to use the feedback mechanism to form a control law. If utilizing state-feedback control, sought states might be unfeasible or impossible to measure in real applications; instead they must be estimated. However, running the estimators in real time for all measurements will require a lot of computational overhead. Further, if the observer and process are disjoint, sending all measurements will put extra strain on the network.

In this work-in-progress paper, we propose an event-based particle filter approach to capture the internal dynamics of a server with CPU-intensive workload whilst minimizing the required... (More)
Closed-loop control of cloud resources requires there to be measurements readily available from the process in order to use the feedback mechanism to form a control law. If utilizing state-feedback control, sought states might be unfeasible or impossible to measure in real applications; instead they must be estimated. However, running the estimators in real time for all measurements will require a lot of computational overhead. Further, if the observer and process are disjoint, sending all measurements will put extra strain on the network.

In this work-in-progress paper, we propose an event-based particle filter approach to capture the internal dynamics of a server with CPU-intensive workload whilst minimizing the required computation or inter-system network strain. Preliminary results show some promise as it outperforms estimators derived from analytic expression for stationary systems in service rate estimation over number of samples used for a simulation experiment. Further we show that for the same simulation, an event-based sampling strategy outperforms periodic sampling. (Less)
Abstract (Swedish)
Closed-loop control of cloud resources requires there to be measurements readily available from the process in order to use the feedback mechanism to form a control law. If utilizing state-feedback control, sought states might be unfeasible or impossible to measure in real applications; instead they must be estimated. However, running the estimators in real time for all measurements will require a lot of computational overhead. Further, if the observer and process are disjoint, sending all measurements will put extra strain on the network.

In this work-in-progress paper, we propose an event-based particle filter approach to capture the internal dynamics of a server with CPU-intensive workload whilst minimizing the required... (More)
Closed-loop control of cloud resources requires there to be measurements readily available from the process in order to use the feedback mechanism to form a control law. If utilizing state-feedback control, sought states might be unfeasible or impossible to measure in real applications; instead they must be estimated. However, running the estimators in real time for all measurements will require a lot of computational overhead. Further, if the observer and process are disjoint, sending all measurements will put extra strain on the network.

In this work-in-progress paper, we propose an event-based particle filter approach to capture the internal dynamics of a server with CPU-intensive workload whilst minimizing the required computation or inter-system network strain. Preliminary results show some promise as it outperforms estimators derived from analytic expression for stationary systems in service rate estimation over number of samples used for a simulation experiment. Further we show that for the same simulation, an event-based sampling strategy outperforms periodic sampling. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceedings of the 4th International Conference on Event-Based Control, Communication, and Signal Processing
conference name
4th International Conference on Event-Based Control, Communication and Signal Processing
conference location
Perpignan, France
conference dates
2018-06-27 - 2018-06-29
project
Event-Based Control of Stochastic Systems with Application to Server Systems
Event-Based Information Fusion for the Self-Adaptive Cloud
language
English
LU publication?
yes
id
26b0a789-ea5e-4a16-89b4-129076a1de05
date added to LUP
2018-08-17 12:58:31
date last changed
2021-04-10 02:19:45
@inproceedings{26b0a789-ea5e-4a16-89b4-129076a1de05,
  abstract     = {{Closed-loop control of cloud resources requires there to be measurements readily available from the process in order to use the feedback mechanism to form a control law. If utilizing state-feedback control, sought states might be unfeasible or impossible to measure in real applications; instead they must be estimated. However, running the estimators in real time for all measurements will require a lot of computational overhead. Further, if the observer and process are disjoint, sending all measurements will put extra strain on the network.<br/><br/>In this work-in-progress paper, we propose an event-based particle filter approach to capture the internal dynamics of a server with CPU-intensive workload whilst minimizing the required computation or inter-system network strain. Preliminary results show some promise as it outperforms estimators derived from analytic expression for stationary systems in service rate estimation over number of samples used for a simulation experiment. Further we show that for the same simulation, an event-based sampling strategy outperforms periodic sampling.}},
  author       = {{Ruuskanen, Johan and Cervin, Anton}},
  booktitle    = {{Proceedings of the 4th International Conference on Event-Based Control, Communication, and Signal Processing}},
  language     = {{eng}},
  month        = {{06}},
  title        = {{Internal Server State Estimation Using Event-based Particle Filtering}},
  url          = {{https://lup.lub.lu.se/search/files/49609380/wip_ebccsp_18.pdf}},
  year         = {{2018}},
}