Infrastructure as a Service (IaaS) cloud provides resources as a service from a pool of compute, network, and storage resources. Cloud providers can manage their resource usage by knowing future usage demand from the current and past usage patterns of resources. Resource usage prediction is of great importance for dynamic scaling of cloud resources to achieve efficiency in terms of cost and energy consumption while keeping quality of service. The purpose of this paper is to present a real-time resource usage prediction system. The system takes real-time utilization of resources and feeds utilization values into several buffers based on the type of resources and time span size. Buffers are read by R language based statistical system. These buffers' data are checked to determine whether their data follows Gaussian distribution or not. In case of following Gaussian distribution, Autoregressive Integrated Moving Average (ARIMA) is applied; otherwise Autoregressive Neural Network (AR-NN) is applied. In ARIMA process, a model is selected based on minimum Akaike Information Criterion (AIC) values. Similarly, in AR-NN process, a network with the lowest Network Information Criterion (NIC) value is selected. We have evaluated our system with real traces of CPU utilization of an IaaS cloud of one hundred and twenty servers.
Adaptive Resource Utilization Prediction System for Infrastructure as a Service Cloud
Qazi Zia Ullah,Hassan Shahzad,G. M. Khan
Published 2017 in Computational Intelligence and Neuroscience
ABSTRACT
PUBLICATION RECORD
- Publication year
2017
- Venue
Computational Intelligence and Neuroscience
- Publication date
2017-07-25
- Fields of study
Medicine, Computer Science, Engineering
- Identifiers
- External record
- Source metadata
Semantic Scholar, PubMed
CITATION MAP
EXTRACTION MAP
CLAIMS
CONCEPTS
- aic
The Akaike Information Criterion used to select among ARIMA model candidates.
Aliases: Akaike Information Criterion
- arima
An autoregressive integrated moving average time-series model used here as one forecasting branch.
Aliases: Autoregressive Integrated Moving Average
- autoregressive neural network
A neural-network-based forecasting model used here as the alternative branch for non-Gaussian buffered data.
Aliases: AR-NN
- cpu utilization traces
Recorded CPU usage measurements from servers used as the evaluation data source.
Aliases: CPU traces
- gaussian distribution test
A statistical check used to decide whether buffered utilization data are treated as Gaussian.
Aliases: normality test, Gaussian check
- infrastructure as a service cloud
A cloud computing model in which compute, network, and storage resources are provided as services from a shared pool.
Aliases: IaaS cloud, IaaS
- nic
The Network Information Criterion used to select among Autoregressive neural network candidates.
Aliases: Network Information Criterion
- real-time resource usage prediction system
A prediction pipeline that consumes current utilization measurements and produces resource-usage forecasts.
Aliases: resource usage prediction system
- utilization buffers
Buffers that store resource utilization values grouped by resource type and time span before statistical processing.
Aliases: buffers
REFERENCES
Showing 1-49 of 49 references · Page 1 of 1
CITED BY
Showing 1-52 of 52 citing papers · Page 1 of 1