Abstract
In cloud environment, maximum utilization of resource is possible with good resource management strategies. Workload prediction plays a vital role in estimating the actual resource required for successful execution of an application on cloud. Most of the existing works concentrated on predicting workloads which either showed clear seasonality/trend or for irregular workload patterns. This paper presents a new perspective in forecasting both seasonal and non-seasonal workloads. To accomplish this, a hybrid prediction model which is a combination of statistical and machine learning technique is proposed. Suppose the seasonality exists in the workload pattern, Seasonal Auto Regressive Integrated Moving Average (SARIMA) model is applied for prediction. For non-seasonal workloads Long Short-Term Memory networks (LSTM) or AutoRegressive Integrated Moving Average (ARIMA) model is used based on the results of normality test. This paper presents a prediction model which forecasts the actual resource required for diverse time intervals of daily, hourly and minutes utilization. The experimental results confirm that accuracy of the prediction of LSTM model outperformed ARIMA for irregular workload patterns. The SARIMA model accurately forecasts the resource usage for forthcoming days. This work actually helps the cloud service provider (CSP) to analyze the workload and predict accordingly to avoid over or under provisioning of the cloud resources.
Highlights
The Cloud computing is a utility computing model which is convenient to access the pool of computing resources such as physical machines, servers, applications, computing, storage, networks and various other services
Calheiros et al [8] presented cloud workload prediction for SaaS providers which was based on the AutoRegressive Integrated Moving Average (ARIMA) model to achieve the accuracy in resource utilization
From the results it is found that Long Short-Term Memory networks (LSTM) has 20% less forecasting error when compared to ARIMA model and performed with better consistency
Summary
The Cloud computing is a utility computing model which is convenient to access the pool of computing resources such as physical machines, servers, applications, computing, storage, networks and various other services. Various research works have used only statistical methods to predict workload and they are unable to predict accurate results for large and heterogeneous data [8]. Several research works have been carried out to address prediction of high dimensional and greatly varying cloud workloads using machine learning models. The proposed Hybrid prediction model uses both statistical and machine learning approaches to achieve better quality prediction results with accuracy. This paper proposes a workload prediction model which is aimed to www.ijacsa.thesai.org (IJACSA) International Journal of Advanced Computer Science and Applications, Vol 12, No 4, 2021 predict the actual resource consumption of Central Processing Unit (CPU) and memory against provisioned resources. Remainder of the paper is structured as: Section 2 presents the overview of the existing works related to prediction using machine learning, statistical and hybrid methods in terms of resource utilization and accuracy.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
