This informative text/reference presents a detailed review of the state of the art in fog computing paradigm. In particular, the book examines a broad range of important cooperative and distributed computation algorithms, along with their design objectives and technical challenges.
The coverage includes the conceptual fundamental of fog computing, its practical applications, cooperative and distributed computation algorithms using optimization, swarm intelligence, matching theory, and reinforcement learning methods. Discussions are also provided on remaining challenges and open research issues for designing and developing the efficient distributed computation solutions in the next-generation of fog-enabled IoT systems.
Fog Computing: Concepts & Recent Advances.- 1.1 Introduction.- 1.2 Fog
Computing Architectures.- 1.2.1 Hierarchical Architecture Model.- 1.2.2
Layered Architecture Model.- 1.3 Computation Offloading in Fog Computing
Architectures.- 1.4 Key Technologies for Future Fog Computing Architectures
.- 1.4.1 Communication and Networking Technologies.- 1.4.2 Virtualization
Technologies .- 1.4.3 Storage Technologies.- 1.4.4 Privacy and Data Security
Technologies .- 1.5 Conclusions.- 2 Applications of Fog Computing.- 2.1
Introduction.- 2.2 Typical Applications of Fog Computing.- 2.2.1 Healthcare.-
2.2.2 Smart Cities.- 2.2.3 Smart Grid.- 2.2.4 Industrial Robotics and
Automation in Smart Factories.- 2.2.5 Agriculture.- 2.2.6 Logistics and
Supply Chains.- 2.3 Summary and Conclusions.- .- 3 Cooperation for
Distributed Task Offloading in Fog Computing Networks.- 3.1 Introduction.-
3.2 System Model.- 3.2.1 Fog Computing Networks.- 3.2.2 Computation Tasks.-
3.2.3 Computation Offloading Model.- 3.3 Cooperation-based Task Offloading
Models.- 3.4 Open Research Issues.- 3.4.1 Data Fragmentation.- 3.4.2
Distribution of Fog Networks.- 3.4.3 Advances of Distributed Algorithms.-
3.4.4 Comprehensive Performance Analysis.- 3.5 Conclusions.- .- 4 Fog
Resource Aware Framework for Adaptive Task Offloading in Fog-based IoT
Systems.- 4.1 Introduction.- 4.2 Related Works.- 4.3 System Model and Problem
Formulation.- 4.3.1 System Model.- 4.3.2 Problem Formulation 4.4 FRATO: Fog
Resource Aware Task Offloading Framework.- 4.4.1 Offloading Strategies for
Minimizing Service Provisioning Delay.- 4.4.2 Mathematical Formulation of
FRATO .- 4.4.3 Solution Deployment Analysis.- 4.5 Distributed Resource
Allocation in Fog.- 4.5.1 Task Priority-based Resource Allocation .- 4.5.2
Maximal Resource Utilization based Allocation .- 4.6 Simulation and
Performance Evaluation.- 4.6.1 Simulation Environment Setup .- 4.6.2
Comparative Approaches.- 4.6.3 Evaluation and Analysis.- 4.6.4 Further
Analysis of Computation Time and Complexity .- 4.7 Conclusions.- 4.8 Future
Works.- 4.8.1 Data Fragmentation .- 4.8.2 Distribution of Fog Networks.-
4.8.3 Advance of Optimization Algorithms.- 4.8.4 Comprehensive Performance
Analysis.- .- 5 Dynamic Collaborative Task Offloading in Fog computing
Systems.- 5.1 Introduction.- 5.2 Related Works.- 5.3 System Model and Problem
Formulation.- 5.3.1 System Model.- 5.3.2 Computation Task Model.- 5.3.3
Problem Formulation.- 5.4 Optimization Problem for Minimization of Task
Execution Delay .- 5.5 Simulation and Performance Evaluation .- 5.5.1
Simulation Environment Setup.- 5.5.2 Evaluation and Analysis.- 5.6
Conclusions and Future Works.- 6 Fundamentals of Matching Theory.- 6.1
Introduction.- 6.2 Basic Concepts and Terminologies .- 6.3 Classification.-
6.3.1 One-to-One (OTO) Matching.- 6.3.2 Many-to-One (MTO) Matching.- 6.3.3
Many-to-Many (MTM) Matching.- 6.3.4 Variants of Matching Models.- 6.4
Matching Algorithms.- 6.5 Conclusions.- 7 Matching Theory for Distributed
Computation Offloading in Fog Computing Systems.- 7.1 Introduction.- 7.2
System and Offloading Problem Description .- 7.2.1 System Model.- 7.2.2
Computation Tasks .- 7.2.3 Computation Offloading Models.- 7.2.4 Optimization
Problems of Computational Offloading .- 7.3 Proposed Matching-based Models
for Distributed Computation .- 7.3.1 One-to-One (OTO) Matching.- 7.3.2
Many-to-One (MTO) Matching7.- 7.3.3 Many-to-Many (MTM) Matching.- 7.4
Challenges and Open Research Issues.- 7.4.1 Matching With Dynamics.- 7.4.2
Matching with Groups.- 7.4.3 Matching with Externality.- 7.4.4 Security and
Privacy of Data and End Users.- 7.4.5 New Offloading Application Scenarios.-
7.4.6 Application of AI and ML-Based Techniques.- 7.5 Conclusions.-
8 Distributed Computation Offloading Frameworks for Fog Networks.- 8.1
Introduction.- 8.2 Preliminary and Related Works.- 8.2.1 Preliminary of
Many-to-One (M2O) Matching Model.- 8.2.2 Related Works.- 8.3 System Model.-
8.3.1 Fog Computing Networks .- 8.3.2 Computation Offloading Model.- 8.4
Problem Formulation.- 8.5 Description of DISCO Framework.- 8.5.1 Overview.-
8.5.2 PL Construction.- 8.5.3 Matching Algorithms.- 8.5.4 Optimal Task
Offloading and Communication Scheduling Algorithm.- 8.5.5 Stability
Analysis.- 8.6 Simulations and Performance Evaluation .- 8.6.1 Simulation
Environment Setup .- 8.6.2 Evaluation and Analysis .- 8.7 Conclusions .- 9
Reinforcement Learning-based Resource Allocations in Fog Networks.- 9.1
Introduction.- 9.2 Fog Computing Environment.- 9.2.1 System Model.- 9.2.2
Resource Allocation Problems in Fog Computing Systems.- 9.3 Reinforcement
Learning.- 9.3.1 Basic Concepts.- 9.3.2 Taxonomy of RL Algorithms.- 9.4 RL
based Algorithms for Resource Allocation in FC Systems.- 9.4.1 Resource
Sharing and Management.- 9.4.2 Task Scheduling.- 9.4.3 Task Offloading and
Redistribution.- 9.5 Challenges and Open Issues of RL-based Resource
Allocations.- 9.5.1 RL-related Challenges.- 9.5.2 Fog Computing Environment
related Challenges.- 9.5.3 Computation Task related Challenges.- 9.6
Conclusions and Discussions.- .- .- 10 Bandit Learning and Matching based
Distributed Task Offloading in Fog Networks.- 10.1 Introduction.- 10.2
Bacground and Related Works.- 10.2.1 One-to-One Matching-based Task
Offloading.- 10.2.2 Bandit Learning-based Computation Offloading.- 10.3
System Model.- 10.3.1 Fog Computing networks.- 10.3.2 Computation Offloading
Model.- 10.4 Design of BLM-DTO Algorithm.- 10.4.1 OTO Matching Model for
Computation Offloading.- 10.4.2 Multi-Player Multi-Armed Bandit with TS.-
10.5 Simulation Results and Evaluation Analysis.- 10.5.1 Simulation
Environment Configuration.- 10.5.2 Comparative Evaluation and Analysis.- 10.6
Conclusions and Discussions.
Dr. Hoa Tran-Dang is research professor, working in the ICT-Convergence research center, in the department of IT convergence engineering at Kumoh National Institute of Technology (KIT). His research interests include Fog/Edge computing, Wireless Communication Networks, Resource Optimization, Machine Learning, and AI.
Prof. Dong-Seong Kim is Director of Networked System Laboratory/ICT-Convergence Research Center (ITRC program), supported by the Korean government, at Kumoh National Institute of Technology, Gumi, South Korea. He is a senior member of the IEEE, and ACM. His research interests include real-time IoT, industrial wireless control network, networked embedded system and Fieldbus.
More information about ebooks