A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Prediction Model for Virtual Machine Power Consumption in Cloud Environments
2016
Procedia Computer Science
Preserved Fulltext
Experimental results with various standard benchmark workloads demonstrate that the prediction accuracy of proposed approach is better than the existing linear regression based power model. ...
However, linear models do not capture dependencies among multiple parameters and hence they do not ensure prediction accuracy across multiple workloads. ...
Figure 2 .Figure 3 . 23 Mean absolute error of power prediction for a VM running various Mean absolute percentage error of power prediction for a VM running various workloads for both linear and SVR prediction ...
doi:10.1016/j.procs.2016.05.137
fatcat:2huzwv2ruzaofmbcc5uncay3ra
PerTract: Model Extraction and Specification of Big Data Systems for Performance Prediction by the Example of Apache Spark and Hadoop
2019
Big Data and Cognitive Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Simulation results of adjusted DSL instances compared to measurement results show accurate predictions errors below 15% based upon averages for response times and resource utilization. ...
First, a system-and tool-agnostic domain-specific language (DSL) allows the modeling of performance-relevant factors of big data applications, computing resources, and data workload. ...
., four nodes and small workload) shows a response time prediction error of 0.78% for the RFC and 2.23% for the LR application. CPU prediction errors amount to 6.69% and 2.94%. ...
doi:10.3390/bdcc3030047
fatcat:dnbi74dnqbfd3ci6djrbhxmgje
Measuring Fault Tolerance with the FTAPE fault injection tool
[chapter]
1995
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The major parts of the tool include a system-wide fault injector, a workload generator, and a workload activity measurement tool. The workload creates high stress conditions on the machine. ...
Using stress-based injection, the fault injector is able to utilize knowledge of the workload activity to ensure a high level of fault propagation. ...
For each system area, the following methods are used to obtain the workload stress: Method 1: measure cpu The stress measure is based upon the CPU utilization. ...
doi:10.1007/bfb0024305
fatcat:rduk7thmvneqjfubsynsqj5gkm
A regression-based analytic model for capacity planning of multi-tier applications
2008
Cluster Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2013; you can also visit the original URL.
The file type is application/pdf.
In this work, we apply a regression-based approximation of the CPU demand of client transactions on a given hardware. ...
Then, we use this approximation in an analytic model of a simple network of queues, each queue representing a tier, and show the approximation's effectiveness for modeling diverse workloads with a changing ...
Fig. 16 16 CDF of relative errors for Server 2 under a different number of core transactions not help to evaluate the future CPU demands, and introduces a higher error compared to the regression based ...
doi:10.1007/s10586-008-0052-0
fatcat:7coi5ngfyraevc2wtjw4petupy
Adaptive energy minimization of embedded heterogeneous systems using regression-based learning
2015
2015 25th International Workshop on Power and Timing Modeling, Optimization and Simulation (PATMOS)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Fundamental to this approach is a runtime model, generated through regression-based learning of energy/performance trade-offs between different computing resources in the system. ...
The proposed approach is designed, engineered and validated on a Zynq-ZC702 platform, consisting of CPU, DSP and FPGA cores. ...
The authors would like to thank the EPSRC-UK for funding this work under PRiME project with grant number EP/K034448/1. ...
doi:10.1109/patmos.2015.7347594
dblp:conf/patmos/YangSMSLDA15
fatcat:2d6awkuoovgp3n67fezv4ndhj4
A Regression-Based Analytic Model for Dynamic Resource Provisioning of Multi-Tier Applications
2007
Fourth International Conference on Autonomic Computing (ICAC'07)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2008; you can also visit the original URL.
The file type is application/pdf.
In this work, we apply a regression-based approximation of the CPU demand of client transactions on a given hardware. ...
Then we use this approximation in an analytic model of a simple network of queues, each queue representing a tier, and show the approximation's effectiveness for modeling diverse workloads with a changing ...
whether a simplified workload model that is only based on the probabilistic transaction mixes can be used for performance modeling of such sites. ...
doi:10.1109/icac.2007.1
dblp:conf/icac/ZhangCS07
fatcat:si7sve4hfjffvlqzhn6tyvqebm
Dynamic Resource Allocation Through Workload Prediction for Energy Efficient Computing
[chapter]
2016
Advances in Intelligent Systems and Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We use CPU core as a dynamic resource that can be allocated and deallocated based on predicted workload. ...
We also analyse the effect of dynamic resource allocation on clients by measuring the request response time to clients for variable number of cores in operation. ...
Hence, for a single CPU with eight cores, dynamic allocation of cores based on the predicted workload leads to 75% reduction in CPU energy consumption. ...
doi:10.1007/978-3-319-46562-3_3
fatcat:t3y27hda2zdppj3n25dxnnjzpu
Performance modeling based on real data: a case study
1988
IEEE transactions on computers
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
Abstract-This paper describes a measurement-based performability model based on error and resource usage data collected on a multiprocessor system. ...
Index Terms-Error, measurements, performability, semi-Markov, workload. ...
Carter for valuable discussions during the initial phase of this work. We also thank L. T. Young and P. Duba for their careful proofreading of the draft of this manuscript. ...
doi:10.1109/12.2195
fatcat:mi4ya5oe2jg3pgkrhsfotucjky
Profiling and Modeling Resource Usage of Virtualized Applications
[chapter]
2008
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
error of less than 5% for both the RUBiS and TPC-W benchmarks. ...
Our approach has two key components: a set of microbenchmarks to profile the different types of virtualization overhead on a given platform, and a regression-based model that maps the native system usage ...
Model Accuracy To test the accuracy of a model, we use it to predict the CPU requirements of a test application based on a trace of the application running natively. ...
doi:10.1007/978-3-540-89856-6_19
fatcat:b2agbosqvbd6rjgguon66ysynu
Towards Virtual Machine Energy-Aware Cost Prediction in Clouds
[chapter]
2017
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The VMs' workload is firstly predicted based on an Autoregressive Integrated Moving Average (ARIMA) model. The power consumption is then predicted using regression models. ...
VMs with good prediction accuracy, e.g. with 0.06 absolute percentage error for the predicted total cost of the VM. ...
These metrics include, Absolute Percentage Error (APE) which measures the absolute value of the ratio of the error to the actual observed value; Mean Error (ME) which measures the average error of the ...
doi:10.1007/978-3-319-68066-8_10
fatcat:gwebcx35urcqnpvo7jfapedw4y
The cube-connected-cycles: A versatile network for parallel computation
1979
20th Annual Symposium on Foundations of Computer Science (sfcs 1979)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
Abstract-This paper describes a measurement-based performability model based on error and resource usage data collected on a multiprocessor system. ...
Index Terms-Error, measurements, performability, semi-Markov, workload. ...
Carter for valuable discussions during the initial phase of this work. We also thank L. T. Young and P. Duba for their careful proofreading of the draft of this manuscript. ...
doi:10.1109/sfcs.1979.43
dblp:conf/focs/PreparataV79
fatcat:vzzqqros4rajzlpdcjfv7h64zu
The cube-connected cycles: a versatile network for parallel computation
1981
Communications of the ACM
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
Abstract-This paper describes a measurement-based performability model based on error and resource usage data collected on a multiprocessor system. ...
Index Terms-Error, measurements, performability, semi-Markov, workload. ...
Carter for valuable discussions during the initial phase of this work. We also thank L. T. Young and P. Duba for their careful proofreading of the draft of this manuscript. ...
doi:10.1145/358645.358660
fatcat:iecwkpxyqrgs7cw7losf375oui
BFEPM: Best Fit Energy Prediction Modeling Based on CPU Utilization
2013
2013 IEEE Eighth International Conference on Networking, Architecture and Storage
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Energy cost becomes a major part of data center operational cost. Computer system consume more power when it runs under high workload. ...
It choose best model based on the power consumption benchmark result. We illustrate how to use benchmark result to find a best fit model. ...
We calculate the coefficients of a polynomial P(workloads) of (a) Mean error rate of different results (b) Mean error distribution degree 1,2,3 that fits the data measured power best in a leastsquares ...
doi:10.1109/nas.2013.12
dblp:conf/nas/ZhangLQ13
fatcat:nrjn4tdm7vgwdiiqrdoz65um2e
Accurate on-line prediction of processor and memoryenergy usage under voltage scaling
2007
Proceedings of the 7th ACM & IEEE international conference on Embedded software - EMSOFT '07
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We implemented the model on a real system and evaluated it under a comprehensive benchmark suite against measurements of the actual energy consumption. ...
This characterisation, done once for a particular platform, produces platform-specific but workload-independent performance and power models. ...
We consider the errors for the latter two to be indicative of the error for a pathological case (as opposed to the likely error for a real-world workload, which is much smaller). ...
doi:10.1145/1289927.1289945
dblp:conf/emsoft/SnowdonPH07
fatcat:kurjpgzitbhnxphm5igtjrg3za
Impact of DVFS on n-tier application performance
2013
Proceedings of the First ACM SIGOPS Conference on Timely Results in Operating Systems - TRIOS '13
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Simulation results (confirmed by extensive measurements) show the anti-synchrony happens routinely for a wide range of configurations. ...
Dynamic Voltage and Frequency Scaling (DVFS) has been widely deployed and proven to reduce energy consumption at low CPU utilization levels; however, our measurements of the n-tier application benchmark ...
For example, instead of a fixed input workload model for which a control system can be designed with predictable maximum error, the workload can vary arbitrarily. ...
doi:10.1145/2524211.2524220
dblp:conf/sosp/WangKLLMP13
fatcat:exfdw2rdpzgqzbtlki3e3hknky
« Previous
Showing results 1 — 15 out of 27,739 results