Machine Learning and Optimization Models for Optimization in Cloud

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
Chapter 1 Introduction to Virtualization in Cloud Computing
	1.1 Introduction
	1.2 Cloud Models
		1.2.1 Public Cloud
		1.2.2 Private Cloud
		1.2.3 Community Cloud
		1.2.4 Hybrid Cloud
	1.3 What Is Virtualization?
		1.3.1 Benefits and Disadvantages of Virtualization
		1.3.2 Virtualization Architecture for Cloud [3–6]
		1.3.3 Virtualization’s Significance in Cloud Computing [7]
		1.3.4 Classes of Virtualization and Its Effects
	1.4 Conclusions
	References
Chapter 2 Machine Learning, Deep Learning-Based Optimization in Multilayered Cloud
	2.1 Introduction
	2.2 Related Work
	2.3 Proposed Methodology
		2.3.1 Initialization
		2.3.2 Dataset Preparation
		2.3.3 Model Preparation
		2.3.4 Training
		2.3.5 Backpropagation and Error Correction
		2.3.6 Task Scheduling
		2.3.7 Steps of Big Bang–Big Crunch
			2.3.7.1 Phase 1: Initialization/Population Generation
			2.3.7.2 Phase 2: Fitness Evaluation
			2.3.7.3 Phase 3: Crossover/Center of Mass and Mutation
			2.3.7.4 Phase 4: Big Crunch
	2.4 Experimental Result
		2.4.1 Results Using Fabricated Data
		2.4.2 Experimental Results Using Real Datasets
	2.5 Conclusion
	References
Chapter 3 Neural Network-Based Resource Allocation Model in Multilayered Cloud
	3.1 Introduction
	3.2 Related Work
	3.3 Proposed Model
		3.3.1 Model Setup
		3.3.2 Dataset Generation
		3.3.3 Model Preparation
		3.3.4 Training
		3.3.5 Backpropagation and Error Correction
		3.3.6 Task Scheduling
		3.3.7 Steps of Big Bang–Big Crunch
			3.3.7.1 Initialization
			3.3.7.2 Evaluation
			3.3.7.3 Selection
			3.3.7.4 Crossover
			3.3.7.5 Mutation
			3.3.7.6 Big Crunch
			3.3.7.7 Stopping Condition
		3.3.8 Results and Discussions
	3.4 Conclusion and Future Works
	References
Chapter 4 Consideration of Availability and Reliability in Cloud Computing
	4.1 Introduction
	4.2 Related Work
	4.3 Availability and Reliability in Cloud SLA
		4.3.1 Availability
		4.3.2 Reliability
	4.4 Conclusion
	References
Chapter 5 Neural Network and Deep Learning-Based Resource Allocation Model for Multilayered Cloud
	5.1 Introduction
		5.1.1 Cloud Delivery/Deployment Model
		5.1.2 Cloud Service/Model Type
		5.1.3 Current Issues in Cloud
			5.1.3.1 Cost Management
			5.1.3.2 Security Issues
			5.1.3.3 Migration
			5.1.3.4 Performance
			5.1.3.5 Multi-Cloud (Hybrid Cloud) Management
			5.1.3.6 Resource Allocation and Management
		5.1.4 Factors Affecting Resource Allocation
			5.1.4.1 Resource Scaling
			5.1.4.2 Energy Utilization
			5.1.4.3 Virtual Machine (VM) Migration
	5.2 Introduction to Neural Networks
		5.2.1 Artificial Neural Networks (ANN)
		5.2.2 Convolution Neural Network (CNN)
		5.2.3 Recurrent Neural Networks (RNN)
	5.3 Introduction to the Genetic Algorithm
	5.4 Proposed Model 1 (a Hybrid GA and Naïve Bayes Model for Optimization)
	5.5 Whale Optimization Algorithm (WOA)
		5.5.1 Mathematical Model
			5.5.1.1 Stage 1: Encircling Prey
			5.5.1.2 Stage 2: Bubble-Net Attacking (Exploitation Phase)
			5.5.1.3 Stage 3: Capture Loop (Search for Prey (Exploration Phase))
	5.6 Related Work
	5.7 Conclusion
	References
Chapter 6 Machine Learning-Based Predictive Model to Improve Cloud Application Performance in Cloud SaaS
	6.1 Introduction
		6.1.1 Essential Characteristics
		6.1.2 Cloud Delivery/Deployment Model
		6.1.3 Cloud Service/Model Type
	6.2 Cloud Challenges
	6.3 Literature Review
	6.4 Comparative Analysis
	6.5 Conclusion
	References
Chapter 7 Fault-Aware Machine Learning and Deep Learning-Based Algorithm for Cloud Architecture
	7.1 Introduction
	7.2 Related Work
	7.3 Outcomes of the Related Works
	7.4 Proposed Model
		7.4.1 Initialization
		7.4.2 Training Datasets Preparations
		7.4.3 Multilayer Perceptron Model Design
		7.4.4 Model Training
		7.4.5 Error Backpropagation and Correction
		7.4.6 Task Scheduling
		7.4.7 Algorithm of the Proposed Resource Provisioning Technique Bat-ANN
			7.4.7.1 Bat Optimization Approach
		7.4.8 Proposed Bat-ANN Task Scheduling Algorithm
	7.5 Results and Discussions
	7.6 Conclusion and Future Works
	References
Chapter 8 Energy-Efficient VM Placement Using Backpropagation Neural Network and Genetic Algorithm
	8.1 Introduction
	8.2 Traditional VM Placement Work
	8.3 System Model
		8.3.1 Data Center Framework
		8.3.2 Energy Consumption Modeling
	8.4 Problem Formulation and Solution
		8.4.1 Multi-Objective VM Placement Problem
		8.4.2 VM Placement Optimization
	8.5 Proposed Energy-Efficient BPGA optimization model
		8.5.1 Pass 1: Non-Dominated Sorting Genetic Algorithm (NSGA)
	8.6 Performance Evaluations
		8.6.1 Experimental Setup
		8.6.2 Simulation Results and Comparison
	8.7 Conclusions and Future Scope
	References
Chapter 9 Meta-Heuristic Algorithms for Power Efficiency in Cloud Computing
	9.1 Introduction
		9.1.1 Essential Features of Cloud Computing
		9.1.2 Cloud Service Models
	9.2 Cloud Technology: Virtualization
		9.2.1 Power Consumption in Cloud
		9.2.2 Virtual Machine Consolidation
	9.3 Meta-Heuristic Algorithms for VM Placement
		9.3.1 Simulated Annealing
		9.3.2 Ant Colony Optimization
		9.3.3 Particle Swarm Optimization
		9.3.4 Genetic Algorithm
		9.3.5 Biogeographic-Based Optimization (BBO)
		9.3.6 Honey Bee Optimization
		9.3.7 Bat Optimization
	9.4 Conclusion
	References
Chapter 10 Intelligent Scalable Algorithm for Resource Efficiency in Cloud
	10.1 Introduction
	10.2 Energy-Constrained Cloud Infrastructure
	10.3 Literature Review
	10.4 Problem Identification and Proposed Solutions
		10.4.1 Estimation of Residual Battery Power
		10.4.2 Estimation of Residual Battery Power
	10.5 Hierarchical Task Scheduling
		10.5.1 Algorithm
		10.5.2 Algorithm Description
	10.6 Advantages of the Proposed Approach
	10.7 Simulation
		10.7.1 Based on the Number of Requests
	10.8 Conclusion
	References
Index