A sequential pattern mining model for application workload prediction in cloud environment

Abstract

The resource provisioning is one of the challenging problems in the cloud environment. The resources should be allocated dynamically according to the demand changes of the applications. Over-provisioning increases energy wasting and costs. On the other hand, under-provisioning causes Service Level Agreements (SLA) violation and Quality of Service (QoS) dropping. Therefore the allocated resources should be close to the current demand of applications as much as possible. For this purpose, the future demand of applications should be determined. Thus, the prediction of the future workload of applications is an essential step before the resource provisioning. To the best of our knowledge, for the first time, this paper proposes a novel Prediction mOdel based on SequentIal paTtern mINinG (POSITING) that considers correlation between different resources and extracts behavioural patterns of applications independently of the fixed pattern length explicitly. Based on the extracted patterns and the recent behaviour of the application, the future demand of resources is predicted. The main goal of this paper is to show that models based on pattern mining could offer novel and useful points of view for tackling some of the issues involved in predicting the application workloads. The performance of the proposed model is evaluated based on both real and synthetic workloads. The experimental results show that the proposed model could improve the prediction accuracy in comparison to the other state-of-the-art methods such as moving average, linear regression, neural networks and hybrid prediction approaches.

A Novel Resource Productivity Based on Granular Neural Network in Cloud Computing

“…In 2017, Amiri et al proposed a POSITING extractionbased forecasting model to improve the provisioning of cloud resources, which examines the relationship between different sources and identifies behavioral patterns independent of fixed pattern length explicit extracts [11]. e proposed algorithm analyzes program behavior in the past, extracts behavior patterns, and then stores them based on the offline model.…”

Predicting Multi-Attribute Host Resource Utilization Using Support Vector Regression Technique

“…Resource management performance is improved by the effective prediction of future resource usage. Many researches [18]- [39] have been introduced for predicting cloud resource utilization under various workload traces. These prediction studies have examined the performance of different machine learning techniques.…”

“…There are also other studies that examined forecasting of host resources usage [29]- [31], prediction of VM usage [32]- [35] and prediction of web application workload [36]- [39]. Table 1 concludes the prediction approaches of resource utilization based on five characteristics: 1) prediction method, 2) workload datasets, 3) performance metrics, 4) preprocessing strategies, and 5) prediction windows.…”

An online learning model based on episode mining for workload prediction in cloud

“…In general, according to our previous work in [5], the prediction models proposed for cloud applications are classified into three main groups: control theory, queuing theory and machine learning techniques. Furthermore, in [17], we propose a new type of the predictor based on Sequential Pattern Mining (SPM). In the following subsections, each group is discussed briefly.…”

“…In our previous work [17], we proposed a prediction model based on episode mining, called POSITING, which investigates the correlation between different resources and extracts the behavioural patterns independently of the fixed pattern length explicitly. As the red dashed box in Fig.…”