A Novel Hybridization of Artificial Neural Networks and ARIMA Models for Forecasting Resource Consumption in an IIS Web Server

Yan, Yongquan; Guo, Ping; Liu, Lifeng

doi:10.1109/issrew.2014.27

Cited by 11 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ARMA model and ARIMA model separately are efficient methods to describe stationary data and no-stationary data [ 16 ]. Because the MEMS gyroscope’s output random signal has a weak linear trend item, the output random signal is a non-stationary time sequence, which needs to be modeled with the ARMIA model [ 26 ].…”

Section: Adaptive Filtering Methods Based On Online Measuring Noisementioning

confidence: 99%

“…Given

as a first difference operator, B as a backward shift operator [ 16 ], the first order difference to the non-stationary time sequence

can be expressed as

…”

Section: Adaptive Filtering Methods Based On Online Measuring Noisementioning

confidence: 99%

“…To describe random signals, the time sequence model is an effective approach [ 16 ]. According to differences in the random signal statistic characteristics, relevant researchers utilized the Auto Regressive and Moving Average (ARMA) model and the Auto Regressive Integrated Moving Average (ARIMA) model respectively to describe stationary data and non-stationary data [ 17 ], and combined them with the Kalman Filter to filter the random data [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Adaptive Filtering Approach Based on the Dynamic Variance Model for Reducing MEMS Gyroscope Random Error

Zhang

Peng

Mou

et al. 2018

Sensors

View full text Add to dashboard Cite

To improve the dynamic random error compensation accuracy of the Micro Electro Mechanical System (MEMS) gyroscope at different angular rates, an adaptive filtering approach based on the dynamic variance model was proposed. In this paper, experimental data were utilized to fit the dynamic variance model which describes the nonlinear mapping relations between the MEMS gyroscope output data variance and the input angular rate. After that, the dynamic variance model was applied to online adjustment of the Kalman Filter measurement noise coefficients. The proposed approach suppressed the interference from the angular rate in the filtering results. Dynamic random errors were better estimated and reduced. Turntable experiment results indicated that the adaptive filtering approach compensated for the MEMS gyroscope dynamic random error effectively both in the constant angular rate condition and the continuous changing angular rate condition, thus achieving adaptive dynamic random error compensation.

show abstract

Section: Adaptive Filtering Methods Based On Online Measuring Noisementioning

confidence: 99%

“…Given

as a first difference operator, B as a backward shift operator [ 16 ], the first order difference to the non-stationary time sequence

can be expressed as

…”

Section: Adaptive Filtering Methods Based On Online Measuring Noisementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Adaptive Filtering Approach Based on the Dynamic Variance Model for Reducing MEMS Gyroscope Random Error

Zhang

Peng

Mou

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Yongquan Yan et al [7] proposed a hybrid model that combines autoregressive integrated moving average (ARIMA) and artificial neural network (ANN) to improve the prediction accuracy of resource consumption of an IIS web server which suffered from software aging problems. Their assumption was that the error term was nonlinear in 3 nature and they used the ANN to model it.…”

Section: Related Workmentioning

confidence: 99%

“…Model adequacy was not discussed for the models presented at the end of the paper Yongquan Yan et al [7] Proposed hybrid model (ARIMA) and (ANN).…”

Section: The Authors Have Not Discussedmentioning

confidence: 99%

Resource Consumption Analysis Using ARIMA-ARCH and ARIMA-GARCH Models for Virtualized Server Consolidation System

Mohan¹,

Reddy²

2017

IJSEIA

View full text Add to dashboard Cite

show abstract

Time series-based workload prediction using the statistical hybrid model for the cloud environment

Devi

Valli²

2022

Computing

View full text Add to dashboard Cite

Resource management is addressed using infrastructure as a service. On demand, the resource management module effectively manages available resources. Resource management in cloud resource provisioning is aided by the prediction of central processing unit (CPU) and memory utilization. Using a hybrid ARIMA-ANN model, this study forecasts future CPU and memory utilization. The range of values discovered is utilized to make predictions, which is useful for resource management. In the cloud traces, the ARIMA model detects linear components in the CPU and memory utilization patterns. For recognizing and magnifying nonlinear components in the traces, the artificial neural network (ANN) leverages the residuals derived from the ARIMA model. The resource utilization patterns are predicted using a combination of linear and nonlinear components. From the predicted and previous history values, the Savitzky-Golay filter finds a range of forecast values. Point value forecasting may not be the best method for predicting multi-step resource utilization in a cloud setting. The forecasting error can be decreased by introducing a range of values, and we employ as reported by Engelbrecht HA and van Greunen M (in: Network and Service Management (CNSM), 2015 11th International Conference, 2015) OER (over estimation rate) and UER (under estimation rate) to cope with the error produced by over or under estimation of CPU and memory utilization. The prediction accuracy is tested using statistical-based analysis using Google's 29-day trail and BitBrain (BB).

show abstract

A Novel Hybridization of Artificial Neural Networks and ARIMA Models for Forecasting Resource Consumption in an IIS Web Server

Cited by 11 publications

References 13 publications

An Adaptive Filtering Approach Based on the Dynamic Variance Model for Reducing MEMS Gyroscope Random Error

An Adaptive Filtering Approach Based on the Dynamic Variance Model for Reducing MEMS Gyroscope Random Error

Resource Consumption Analysis Using ARIMA-ARCH and ARIMA-GARCH Models for Virtualized Server Consolidation System

Time series-based workload prediction using the statistical hybrid model for the cloud environment

Contact Info

Product

Resources

About