Empirical and analytical approaches for web server power modeling

Piga, Leonardo; Bergamaschi, Reinaldo A.; Rigo, Sandro

doi:10.1007/s10586-014-0373-0

Cited by 10 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although our cluster is not a production cluster, our study on designing power estimation approaches and evaluation methods in the paper can be useful for future work in production clusters. We can further improve the accuracy of approaches by considering operating frequency of CPU [32] and time series in the future. The CPU power for the different frequencies is totally distinct.…”

Section: Discussionmentioning

confidence: 99%

“…Wabmann et al [31] computed power consumption of each VM in the server using multiple-variable polynomial approach. Their features are the utilization of CPU, hard disk and NIC in the VM Piga et al [32] proposed a k-means model using a correlation-based feature selection. Zamani and Afsahi [23] considered a time-series factor in their model.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of non-linear power estimation models in a computing cluster

Zhu

Liao

Laat

et al. 2016

Sustainable Computing: Informatics and Systems

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Evaluation of non-linear power estimation models in a computing cluster

Zhu

Liao

Laat

et al. 2016

Sustainable Computing: Informatics and Systems

View full text Add to dashboard Cite

“…[9] added a logistic function to model non-linear disk and OS behavior in a linear model for web servers. [17] proposed a k-means model using a correlation-based feature selection. [18] considered a time-series factor in their model.…”

Section: Related Workmentioning

confidence: 99%

“…We can further improve the accuracy of approaches by considering operating frequency of CPU [17] and time series in the future. The CPU power for the different frequencies is totally distinct.…”

Section: Future Work and Conclusionmentioning

confidence: 99%

Evaluation of approaches for power estimation in a computing cluster

Zhu

Grosso

Liao

et al. 2014

International Green Computing Conference

View full text Add to dashboard Cite

Data centers as a cost-effective infrastructure for hosting Cloud and Grid applications incur tremendous energy cost and CO2 emissions in terms of power distribution and cooling. One of the effective approaches for saving energy in a cluster environment is workload consolidation. However, it is challenging to address this schedule problem as it requires the understanding of various cost factors. One of the important factors is the estimation of power consumption.Power models used in most of workload schedule solutions are a linear function of resource features, but we analysed the measurement data from our cluster and found the resource loads, in particular I/O load, had no convincing linearcorrelation with power consumption. Based on measurement data sets from our cluster, we propose multiple non-linear machine learning approaches to estimate power consumption of an entire node using OS-reported resource features. We evaluate the accuracy, portability and usability of the linear and non-linear approaches. Our work shows the multiple-variable linear regression approach is more precise than the CPU only linear approach. The neural network approaches have a slight advantage -its mean root mean square error is at most 15% less than that of the multiple-variable linear approach. But the neural network models have worse portability when the models generated on a node are applied on its homogeneous nodes. Gaussian Mixture Model has the highest accuracy on Hadoop nodes but requires the longest training time.

show abstract

How much power does your server consume? Estimating wall socket power using RAPL measurements

Khan

Hirki

et al. 2016

Comput Sci Res Dev

View full text Add to dashboard Cite

Empirical and analytical approaches for web server power modeling

Cited by 10 publications

References 17 publications

Evaluation of non-linear power estimation models in a computing cluster

Evaluation of non-linear power estimation models in a computing cluster

Evaluation of approaches for power estimation in a computing cluster

How much power does your server consume? Estimating wall socket power using RAPL measurements

Contact Info

Product

Resources

About