Machine Learning Methods for Refining Sla Based Admission Control and Resource Allocation in Cloud Computing

Abstract

Cloud computing is the most advanced technology in the real world environment and provides flexible and convenient possibilities for users to utilize available services. Resource provisioning to the satisfaction of user requirements becomes the most challenging task in the heterogeneous cloud environment. Proper admission control algorithms need to be proposed for better resource provisioning with improved user satisfaction level. In this research, Knowledge-based Service Level Agreement (SLA) aware admission controlled scheduling and resource allocation are proposed which makes use of machine learning algorithms namely Support Vector Machine (SVM) and Artificial Neural Network (ANN) for better admission control. It seeks to study the knowledge of resource status information by using machine learning algorithms in the training phase. Based on these strategies, admission control would be done in the testing phase which would lead to efficient and better resource provisioning. As our proposed work we mentioned Position Balanced Parallel Particle Swarm Optimization (PBPPSO) is utilized for optimal scheduling and resource allocation which can handle large volumes of tasks in an optimal manner.

A Reinforcement Learning Based Model for Adaptive Service Quality Management in E-Commerce Websites

“…Computer and Information Technology Engineering Department, Amirkabir University (Tehran Polytechnic), Tehran, Iran e-mail: sa.hashemi@aut.ac.ir H. Ghavamipoor e-mail: h.ghavamipoor@aut.ac.ir valuable customers by satisfying them through better service quality in order to gain the highest possible profit from their business. For this purpose, some research in the area of information systems and especially e-commerce systems has been undertaken to realize differentiation in offering e-services to different Web sessions (Bhatti and Friedrich 1999;Li and Jamin 2000;Urgaonkar and Shenoy 2005;Urgaonkar 2005;Yue and Wang 2007;Ewing and Menascé 2009; Totok and Karamcheti 2010; Suchacka and Borzemski 2013;Lakshmi et al 2017;Poggi 2014). One of the common methods of service differentiation and admission control in the literature is prioritization (Totok and Karamcheti 2010;Poggi 2014;Lakshmi et al 2017).…”

“…Simultaneous with the extensive commercial use of cloud computing systems, some admission control systems in this context were proposed (Lakshmi et al 2017;Poggi 2014). Despite the previous studies, these models configured the required cloud infrastructure (including different external resources) to present different QoS levels for predefined classes of sessions.…”

“…Consequently, choosing an optimal combination of cloud resources to present the final e-service was an issue in these works. Lakshmi et al (2017) proposed an admission control and resource allocation mechanism in a cloud computing context. However, although this cloud-based mechanism expanded the previous models which were applicable in the limited context of an e-commerce Website, it cannot be utilized in the e-services supply chain layer.…”

“…Furthermore, Lakshmi et al (2017) utilized Support Vector Machine (SVM) and Artificial Neural Network (ANN) to detect the classes of customers statically and allocate the appropriate resources to each request. Both of these methods belong to the category of supervised machine learning which relies on the fact that there is prior knowledge of what the output values for an input sample should be.…”

“…In addition to the baseline model, the proposed model was compared with some related admission control models (Totok and Karamcheti 2010; Lakshmi et al 2017;Poggi 2014) regarding the profit aspect, as this is the main objective of the proposed model. For this purpose, the following experiment setup was considered (Table 6).…”