A machine learning approach for packet loss prediction in science flows

Giannakou, Anna; Dwivedi, Dipankar; Peisert, Sean

doi:10.1016/j.future.2019.07.053

Cited by 16 publications

(5 citation statements)

References 20 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, we use the RandomForestRegressor (RF Regressor) toolbox from Python's sklearn package (Pedregosa et al, 2011). Some examples using RF approach include Giannakou et al (2020), Mital et al (2020), Stockman et al (2019), andOppel andSchumann (2020).…”

Section: Random Forestmentioning

confidence: 99%

Imputation of Contiguous Gaps and Extremes of Subhourly Groundwater Time Series Using Random Forests

Dwivedi

Mital

Faybishenko

et al. 2022

J Mach Learn Model Comput

Self Cite

View full text Add to dashboard Cite

Machine learning can provide sustainable solutions to gap-fill groundwater (GW) data needed to adequately constrain watershed models. However, imputing missing extremes is more challenging than other parts of a hydrograph. To impute missing subhourly data, including extremes, within GW time-series data collected at multiple wells in the East River watershed, located in southwestern Colorado, we consider a single-well imputation (SWI) and a multiple-well imputation (MWI) approach. SWI gap-fills missing GW entries in a well using the same well's time-series data; MWI gap-fills a specific well's missing GW entry using the time series of neighboring wells. SWI takes advantage of linear interpolation and random forest (RF) approaches, whereas MWI exploits only the RF approach. We also use an information entropy framework to develop insights into how missing data patterns impact imputation. We discovered that if gaps were at random intervals, SWI could accurately impute up to 90% of missing data over an approximately two-year period. Contiguous gaps constituted more complex scenarios for imputation and required the use of MWI. Information entropy suggested that if gaps were contiguous, up to 50% of missing GW data could be estimated accurately over an approximately two-year period. The RF-feature importance suggested that a time feature (months) and a space feature (neighboring wells) were the most important predictors in the SWI and MWI. We also noted that neither SWI nor MWI methods could capture the missing extremes of a hydrograph. To counter this, we developed a new sequential approach and demonstrated the imputation of missing extremes in a GW time series with high accuracy.

show abstract

Section: Random Forestmentioning

confidence: 99%

Imputation of Contiguous Gaps and Extremes of Subhourly Groundwater Time Series Using Random Forests

Dwivedi

Mital

Faybishenko

et al. 2022

J Mach Learn Model Comput

Self Cite

View full text Add to dashboard Cite

show abstract

“…Já no contexto específico de previsão de falhas em redes, diferentes aplicac ¸ões e abordagens foram empregadas. Em [Giannakou et al 2020], explora-se o problema de previsão de retransmissão de pacotes em fluxos TCP relacionados a transferências de dados acadêmicos no NERSC (National Energy Research Scientific Computing Center). Com um modelo relativamente simples (Florestas Aleatórias) e vetores de características inerentes ao fluxos TCP, os autores obtiveram acurácia quase perfeita.…”

Section: Trabalhos Relacionadosunclassified

Caracterização e Previsão de Falhas em Serviços de Conectividade: uma Aplicação à Rede Ipê

Zanotelli

Comarela

Villaça

et al. 2021

Anais Do XXXIX Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2021)

View full text Add to dashboard Cite

A Rede Ipê é fundamental para a comunidade cientíﬁca brasileira por interconectar universidades e centros de pesquisa de todo o país. Este artigo analisa algumas características da Rede Ipê e explora o uso de técnicas de aprendizado de máquina para predição de falhas em serviços de conectividade usando dados públicos disponibilizados pela ferramenta ViaIpê. O problema é abordado como uma tarefa de classiﬁcação binária utilizando redes neurais recorrentes. Os resultados mostram que a dependabilidade do serviço de conectividade varia signiﬁcativamente nos diferentes PoPs da Rede Ipê. Além disso, apesar da heterogeneidade deste serviço, os modelos de predição mostram-se promissores, apresentando boa acurácia e boa precisão em alguns cenários.

show abstract

“…[1]. Giannakou et al used Random Forest Regression to process tstat logs and predict packet retransmission rate [2].…”

Section: Related Workmentioning

confidence: 99%

Towards Generalizable Network Anomaly Detection Models

Arifuzzaman

Islam

Arslan

2021

2021 IEEE 46th Conference on Local Computer Networks (LCN)

View full text Add to dashboard Cite

Finding the root causes of network performance anomalies is critical to satisfy the quality of service requirements. In this paper, we introduce machine learning (ML) models to process TCP socket statistics to pinpoint underlying reasons of performance issues such as packet loss and jitter. More importantly, we introduce a novel feature engineering method to transform network-dependent metrics (e.g., total packet count and round trip time) in training datasets into networkindependent forms to be able to transfer the models to new network settings without requiring to retrain them. Experimental results in various network settings show that the proposed feature engineering approach improves the performance of the models in previously unseen network settings from around 60% to nearly 90%. We believe ability to transfer ML models across networks will pave the way for wide adoption of ML solutions in production networks where collecting labeled data is not possible.

show abstract

A machine learning approach for packet loss prediction in science flows

Cited by 16 publications

References 20 publications

Imputation of Contiguous Gaps and Extremes of Subhourly Groundwater Time Series Using Random Forests

Imputation of Contiguous Gaps and Extremes of Subhourly Groundwater Time Series Using Random Forests

Caracterização e Previsão de Falhas em Serviços de Conectividade: uma Aplicação à Rede Ipê

Towards Generalizable Network Anomaly Detection Models

Contact Info

Product

Resources

About