Resource Management in Distributed Systems

✍ Scribed by Anwesha Mukherjee, Debashis De, Rajkumar Buyya

• Publisher: Springer
• Year: 2024
• Tongue: English
• Leaves: 319
• Series: Studies in Big Data, Volume 151
• Category: Library

✦ Table of Contents

Preface
Contents
About the Editors
Resource Management in Distributed Computing
1 Introduction
2 Resource Management in Cloud Computing
3 Resource Allocation in Edge Computing
4 Resource Allocation in Fog Computing
5 Load Balancing in Resource Utilization
6 Resource Allocation and Scheduling Algorithms
7 Summary
References
Cloud Computing Resource Management
1 Introduction
2 Categories of Cloud Resources
2.1 Fast Computation Utility
2.2 Storage Utility
2.3 Communication Utility
2.4 Energy/Power Utility
2.5 Security Utility
3 Classification of Cloud Resource Management Methods
3.1 Energy-Aware Resource Management
3.2 SLA-Aware Resource Management
3.3 Market-Based Resource Management
3.4 Load-Balanced Resource Management
3.5 Network Load-Aware Resource Management
3.6 Hybrid Cloud Resource Management
3.7 MCC Resource Management
4 Mathematical Model of Performance Evaluation Parameters
4.1 Throughput
4.2 Network Overhead
4.3 VM Migration Time
4.4 Number of VM Migrations
4.5 Resource Utilization
4.6 Energy Consumption
4.7 Revenue and Profit
4.8 SLA Violation
5 Resource Management for Edge and Fog Computing
5.1 Resource Management in Edge Computing
5.2 Resource Management Issues of Fog Computing
6 Resource Management Systems and Simulation Tools
6.1 Resource Management Systems in Practice
6.2 Simulators for Resource Management
7 Research Challenges
7.1 Consumer-Based Service Management
7.2 Autonomic Resource Management
7.3 Resource Information Management
7.4 Heterogeneous Resources
7.5 Sharing of Network Resources
7.6 Security
7.7 Large-Scale Cloud Management
7.8 Computational Risk Analysis and Management
7.9 Multi-parametric Performance Evaluation
7.10 Service Benchmarking
7.11 Robustness
8 Summary
References
Resource Allocation and Placement in Multi-access Edge Computing
1 Introduction
2 MEC Scenarios and Optimization Objectives
3 Resource Allocation
3.1 Computing
3.2 Communication
3.3 Storage
3.4 Multi-resource Allocation
3.5 Network Slicing
4 Placement Issues
4.1 Server Placement
4.2 Service Placement
4.3 NFV Placement
5 Challenges and Future Research Directions
6 Conclusions
References
Resource Scheduling in Integrated IoT and Fog Computing Environments: A Taxonomy, Survey and Future Directions
1 Introduction
2 Challenges in Cloud Computing
3 Fog Computing Architecture
3.1 IoT Layer
3.2 Fog Layer
3.3 Cloud Layer
4 Taxonomy of Recent Resource Scheduling Techniques
4.1 Static Scheduling
4.2 Dynamic Scheduling
4.3 Artificial Intelligence
5 Federated Learning for QoS Optimisation
6 Open Issues and Future Research Directions
7 Conclusions
References
Trusted Task Offloading and Resource Allocation Strategy in MEC Environment
1 Introduction
2 Mobile Edge Computing
2.1 Cloud Computing
2.2 Mobile Edge Cloud Computing
3 Trust Evaluation Mechanism
3.1 Trusted Identity
3.2 Trusted Behavior
3.3 Trusted Capability
4 Resource Allocation Strategy
4.1 Markov Decision Process
4.2 Deep Reinforcement Learning
4.3 Federated Learning
5 Balanced Multi-objective Approach
5.1 Entropy
5.2 Principal Component Analysis
5.3 Kernel Principal Component Analysis
6 Experiment
6.1 Experiment Setup
6.2 Target Weight Coefficient
6.3 Task Scaling
6.4 Compute Node Expansion
7 Conclusion
References
Resource Management in Edge Clouds: Latency-Aware Approaches for Big Data Analysis
1 Introduction
2 Fog, Edge, and Dew Computing
3 Why Latency is Important in Emerging Cloud-Based Services?
4 Resource Management in Fog/Edge-Cloud Architecture
5 Resource Management Approaches
5.1 Application Placement
5.2 Load Balancing
5.3 Resource Scheduling
5.4 Offloading and Caching
5.5 Virtual Machine (VM) Migration and Service Function Chaining (SFC)
6 Role of SDN in Latency-Aware Resource Management
7 AI-Powered Latency-Aware Resource Management
8 Conclusion and Future Works
References
FSRmSTS—An Optimize Task Scheduling with a Hybrid Approach: Integrating FCFS, SJF, and RR with Median Standard Time Slice
1 Introduction
2 Literature Survey
3 Proposed Work
3.1 Analyzing Median
4 Experimental Results and Analysis
4.1 Illustrative Example 1
4.2 Ready Queue Using FCFS
4.3 Ready Queue Using SJF
4.4 Ready Queue Using RR
4.5 Illustrative Example 2
5 Performance Analysis
5.1 Comparison—Performance Metric: Turn Around Time
6 Conclusion
References
Container Orchestration in Heterogeneous Edge Computing Environments
1 Introduction
2 Background and Related Works
2.1 Kubernetes
2.2 Autoscaling
2.3 Related Works
3 System Design
3.1 Replica Placement
3.2 Autoscaling Replicas
4 Evaluation Environment and Experimental Setup
4.1 Testbed Configuration
4.2 Benchmark Applications and Workloads
4.3 Metrics
5 Results and Analysis
5.1 Web Service Results
5.2 Object Detection Service Results
6 Discussions and Limitations
7 Conclusions and Future Work
References
Resource Targeted Cybersecurity Attacks in Cloud Computing Environments
1 Introduction
2 Cloud Targeted Attacks
2.1 Economic Denial of Sustainability (EDoS) Attack
2.2 Side Channel Attacks
2.3 Session Hijacking Using Cookie Poisoning
2.4 Malware Injection Attacks
2.5 Gray Cloud Attacks
2.6 Memory Inspection Attacks
2.7 Botcloud and Out-Cloud Attacks
2.8 Miscellaneous Attacks
3 Summary and Guidelines
4 Conclusions
References
Load Balancing Using Swarm Intelligence in Cloud Environment
1 Introduction
1.1 Cloud Computing
1.2 Cloud Computing Services
1.3 Virtualization
2 Load Balancing
2.1 Static and Dynamic Load Balancing
3 Swarm Intelligence Based Techniques for Load Balancing
3.1 Ant Colony Optimization
3.2 Particle Swarm Optimization
3.3 Genetic Algorithm
3.4 BAT Algorithm
3.5 Grey Wolf Optimization (GWO)
3.6 Artificial Bee Colony (ABC)
3.7 Whale Optimization Algorithm (WOA)
3.8 Social Spider Optimization
3.9 Dragonfly Algorithm
3.10 Raven Roosting Optimization (RRO)
4 Hybrid Algorithm
4.1 Performance Matrices for Load Balancing
5 Conclusion
References
Interoperability and Portability in Big Data Analysis Based Cloud-Fog-Edge-Dew Computing
1 Introduction
2 Dew, Edge, Fog and Cloud Computing
3 Interoperability in Cloud Computing for Big Data Analysis
3.1 Interoperability in Fog/Edge/Dew Computing
3.2 Strategies, Architecture, and Technologies
4 Portability in Cloud Computing
4.1 Cloud Portability at IaaS Level
4.2 Cloud Portability at PaaS and SaaS Level
4.3 Data Portability
5 Management and Orchestration for Interoperability and Portability
6 Working Groups and Standardization Bodies in Interoperability and Portability
6.1 Cloud Standards Coordination (CSC)
6.2 National Institute of Standards and Technology (NIST)
6.3 The Open Grid Forum (OGF)
6.4 Open Cloud Computing Interface (OCCI)
6.5 IEEE SA
6.6 Cloud Application Management for Platforms (CAMP)
6.7 Topology and Orchestration Specification for Cloud Applications (TOSCA)
6.8 Cloud Data Management Interface (CDMI)
6.9 The Distributed Management Task Force (DMTF)
6.10 IEEE Std 2301™
7 Challenges and Future Direction
References
Cyber Attack Victim Separation: New Dimensions to Minimize Attack Effects by Resource Management
1 Introduction
2 Victim Separation Methods: Classification
2.1 Moving Target Defense (MTD)
2.2 Resource Isolation
2.3 Solutions to Co-residency Attack
2.4 Victim Service Migration
2.5 Demilitarized Zone (DMZ)
3 Discussion and Future Directions
4 Conclusions
References
eBPF and XDP Technologies as Enablers for Ultra-Fast and Programmable Next-Gen Network Infrastructures
1 Introduction
2 Background: eeBPF and XDP Technical Description
2.1 Main Characteristics
2.2 eBPF Programs in the XDP: Advantages and Limitations
3 Related Work: eeBPF-Based Networking Applications
4 Use Case
4.1 Functionality Overview
4.2 Technical Details
4.3 Testbench
4.4 Results
5 Conclusion
References
Deep Reinforcement Learning (DRL)-Based Methods for Serverless Stream Processing Engines: A Vision, Architectural Elements, and Future Directions
1 Introduction
2 Significance and Innovation of Our Vision
3 Architectural Framework
4 Research Issues and Envisioned Approaches/Future Directions
4.1 DRL-Based Resource Management Agents
4.2 Exploration Aids
4.3 Policies for Management of Rewards, States, and Enactment
4.4 Automated Techniques for Metrics and Configuration Management
5 A Case Study—Use Case Scenario: Multi-source Stream Video Analytics System
5.1 Use Case Overview
5.2 Use Case Implementation
5.3 DRL-SSPE Implementation for Video Grayscale
5.4 Results Discussion
6 Conclusions and Final Remarks
References