Оглавление
Группа авторов. Fog Computing
Table of Contents
List of Tables
List of Illustrations
Guide
Pages
WILEY SERIES ON PARALLEL AND DISTRIBUTED COMPUTING
Fog Computing: Theory and Practice
List of Contributors
Acronyms
1 Mobile Fog Computing
1.1 Introduction
1.2 Mobile Fog Computing and Related Models
1.3 The Needs of Mobile Fog Computing
1.3.1 Infrastructural Mobile Fog Computing. 1.3.1.1 Road Crash Avoidance
1.3.1.2 Marine Data Acquisition
1.3.1.3 Forest Fire Detection
1.3.1.4 Mobile Ambient Assisted Living
1.3.2 Land Vehicular Fog
1.3.3 Marine Fog
1.3.4 Unmanned Aerial Vehicular Fog
1.3.5 User Equipment-Based Fog
1.3.5.1 Healthcare
1.3.5.2 Content Delivery
1.3.5.3 Crowd Sensing
1.4 Communication Technologies
1.4.1 IEEE 802.11
1.4.2 4G, 5G Standards
1.4.3 WPAN, Short-Range Technologies
1.4.4 LPWAN, Other Medium- and Long-Range Technologies
1.5 Nonfunctional Requirements
1.5.1 Heterogeneity
1.5.1.1 Server Heterogeneity
1.5.1.2 End-Device Heterogeneity
1.5.1.3 End-to-End Network Heterogeneity
1.5.2 Context-Awareness
1.5.2.1 Server Context
1.5.2.2 Mobility Context
1.5.2.3 End-to-end Context
1.5.2.4 Application Context
1.5.3 Tenant
1.5.3.1 Application Management
1.5.3.2 Cost of Energy and Tenancy
1.5.4 Provider
1.5.4.1 Physical Placement
1.5.4.2 Server Discoverability and Connectivity
1.5.4.3 Operation Management
1.5.4.4 Operation Cost
1.5.5 Security
1.5.5.1 Physical Security
1.5.5.2 End-to-End Security
1.5.5.3 Security Monitoring and Management
1.5.5.4 Trust Management and Multitenancy Security
1.6 Open Challenges
1.6.1 Challenges in Land Vehicular Fog Computing
1.6.2 Challenges in Marine Fog Computing
1.6.3 Challenges in Unmanned Aerial Vehicular Fog Computing
1.6.4 Challenges in User Equipment-based Fog Computing
1.6.5 General Challenges. 1.6.5.1 Testbed Tool
1.6.5.2 Autonomous Runtime Adjustment and Rapid Redeployment
1.6.5.3 Scheduling of Fog Applications
1.6.5.4 Scalable Resource Management of Fog Providers
1.7 Conclusion
Acknowledgment
References
Note
2 Edge and Fog: A Survey, Use Cases, and Future Challenges
2.1 Introduction
2.2 Edge Computing
2.2.1 Edge Computing Architecture
2.3 Fog Computing
2.3.1 Fog Computing Architecture
2.4 Fog and Edge Illustrative Use Cases
2.4.1 Edge Computing Use Cases
2.4.1.1 A Wearable ECG Sensor
2.4.1.2 Smart Home
2.4.2 Fog Computing Use Cases
2.4.2.1 Smart Traffic Light System
2.4.2.2 Smart Pipeline Monitoring System
2.5 Future Challenges
2.5.1 Resource Management
2.5.2 Security and Privacy
2.5.3 Network Management
2.6 Conclusion
Acknowledgment
References
3 Deep Learning in the Era of Edge Computing: Challenges and Opportunities
3.1 Introduction
3.2 Challenges and Opportunities. 3.2.1 Memory and Computational Expensiveness of DNN Models
3.2.2 Data Discrepancy in Real-world Settings
3.2.3 Constrained Battery Life of Edge Devices
3.2.4 Heterogeneity in Sensor Data
3.2.5 Heterogeneity in Computing Units
3.2.6 Multitenancy of Deep Learning Tasks
3.2.7 Offloading to Nearby Edges
3.2.8 On-device Training
3.3 Concluding Remarks
References
4 Caching, Security, and Mobility in Content-centric Networking
4.1 Introduction
4.2 Caching and Fog Computing
4.3 Mobility Management in CCN
4.3.1 Classification of CCN Contents and their Mobility
4.3.2 User Mobility
4.3.3 Server-side Mobility
4.3.4 Direct Exchange for Location Update
4.3.5 Query to the Rendezvous for Location Update
4.3.6 Mobility with Indirection Point
4.3.7 Interest Forwarding
4.3.8 Proxy-based Mobility Management
4.3.9 Tunnel-based Redirection (TBR)
4.4 Security in Content-centric Networks
4.4.1 Risks Due to Caching
4.4.2 DOS Attack Risk
4.4.3 Security Model
4.5 Caching
4.5.1 Cache Allocation Approaches
4.5.2 Data Allocation Approaches
4.6 Conclusions
References
5 Security and Privacy Issues in Fog Computing
5.1 Introduction
5.2 Trust in IoT
5.3 Authentication
5.3.1 Related Work
5.4 Authorization
5.4.1 Related Work
5.5 Privacy
5.5.1 Requirements of Privacy in IoT
5.5.1.1 Device Privacy
5.5.1.2 Communication Privacy
5.5.1.3 Storage Privacy
5.5.1.4 Processing Privacy
5.6 Web Semantics and Trust Management for Fog Computing
5.6.1 Trust Through Web Semantics
5.7 Discussion
5.7.1 Authentication
5.7.2 Authorization
5.8 Conclusion
References
6 How Fog Computing Can Support Latency/Reliability-sensitive IoT Applications: An Overview and a Taxonomy of State-of-the-art Solutions
6.1 Introduction
6.2 Fog Computing for IoT: Definition and Requirements
6.2.1 Definitions
6.2.2 Motivations
6.2.3 Fog Computing Requirements When Applied to Challenging IoTs Application Domains
6.2.3.1 Scalability
6.2.3.2 Interoperability
6.2.3.3 Real-Time Responsiveness
6.2.3.4 Data Quality
6.2.3.5 Security and Privacy
6.2.3.6 Location-Awareness
6.2.3.7 Mobility
6.2.4 IoT Case Studies
6.3 Fog Computing: Architectural Model
6.3.1 Communication
6.3.2 Security and Privacy
6.3.3 Internet of Things
6.3.4 Data Quality
6.3.5 Cloudification
6.3.6 Analytics and Decision-Making
6.4 Fog Computing for IoT: A Taxonomy
6.4.1 Communication
6.4.1.1 Standardization
6.4.1.2 Reliability
6.4.1.3 Low-Latency
6.4.1.4 Mobility
6.4.2 Security and Privacy Layer
6.4.2.1 Safety
6.4.2.2 Security
6.4.2.3 Privacy
6.4.3 Internet of Things
6.4.3.1 Sensors
6.4.3.2 Actuators
6.4.4 Data Quality
6.4.4.1 Data Normalization
6.4.4.2 Data Filtering
6.4.4.3 Data Aggregation
6.4.5 Cloudification
6.4.5.1 Virtualization
6.4.5.2 Storage
6.4.6 Analytics and Decision-Making Layer
6.4.6.1 Data Analytics
6.4.6.2 Decision-Making
6.5 Comparisons of Surveyed Solutions
6.5.1 Communication
6.5.1.1 Standardization
6.5.1.2 Reliability
6.5.1.3 Low-latency Communication
6.5.1.4 Mobility
6.5.2 Security and Privacy
6.5.2.1 Security
6.5.2.2 Privacy
6.5.2.3 Safety
6.5.3 Internet of Things
6.5.3.1 Sensors
6.5.3.2 Actuators
6.5.4 Data Quality
6.5.4.1 Data Normalization
6.5.4.2 Data Filtering
6.5.4.3 Data Aggregation
6.5.5 Cloudification
6.5.5.1 Virtualization
6.5.5.2 Storage
6.5.6 Analytics and Decision-Making Layer
6.5.6.1 Data Analytics
6.5.6.2 Decision-Making
6.6 Challenges and Recommended Research Directions
6.7 Concluding Remarks
References
7 Harnessing the Computing Continuum for Programming Our World
7.1 Introduction and Overview
7.2 Research Philosophy
7.3 A Goal-oriented Approach to Programming the Computing Continuum
7.3.1 A Motivating Continuum Example
7.3.2 Goal-oriented Annotations for Intensional Specification
7.3.3 A Mapping and Run-time System for the Computing Continuum
7.3.4 Building Blocks and Enabling Technologies
7.3.4.1 The Array of Things (AoT)
7.3.4.2 Iowa Quantified (IQ)
7.3.4.3 Intelligent, Multiversion Libraries
7.3.4.4 Data Flow Execution for Big Data
7.4 Summary
References
Note
8 Fog Computing for Energy Harvesting-enabled Internet of Things
8.1 Introduction
8.2 System Model
8.2.1 Computation Model
8.2.1.1 Local Execution Model
8.2.1.2 Fog Execution Model
8.2.2 Energy Harvesting Model
8.2.2.1 Stochastic Process
8.2.2.2 Wireless Power Transfer
8.3 Tradeoffs in EH Fog Systems
8.3.1 Energy Consumption vs. Latency
8.3.2 Execution Delay vs. Task Dropping Cost
8.4 Future Research Challenges
Acknowledgment
References
9 Optimizing Energy Efficiency of Wearable Sensors Using Fog-assisted Control
9.1 Introduction
9.2 Background
9.3 Related Topics
9.4 Design Challenges
9.5 IoT System Architecture
9.5.1 Fog Computing and its Benefits
9.6 Fog-assisted Runtime Energy Management in Wearable Sensors
9.6.1 Computational Self-Awareness
9.6.2 Energy Optimization Algorithms
9.6.3 Myopic Strategy
9.6.4 MDP Strategy
9.7 Conclusions
Acknowledgment
References
10 Latency Minimization Through Optimal Data Placement in Fog Networks
10.1 Introduction
10.2 Related Work
10.2.1 Long-Term and Short-Term Placement
10.2.2 Data Replication
10.3 Problem Statement
10.3.1 Network Model
10.3.2 Multiple Data Placement with Budget Problem
10.3.3 Challenges
10.4 Delay Minimization Without Replication
10.4.1 Problem Formulation
10.4.2 Min-Cost Flow Formulation
10.4.3 Complexity Reduction
10.5 Delay Minimization with Replication
10.5.1 Hardness Proof
10.5.2 Single Request in Line Topology
Algorithm 10.1 Dynamic Programming for Single Request
10.5.3 Greedy Solution in Multiple Requests
10.5.4 Rounding Approach in Multiple Requests
10.5.4.1 Generating Linear Programming Solution
Algorithm 10.2 Min-Volume Algorithm
Algorithm 10.3 Rounding Algorithm
10.5.4.2 Creating Centers
10.5.4.3 Converting to Integral Solution
10.6 Performance Evaluation
10.6.1 Trace Information
10.6.2 Experimental Setting
10.6.3 Algorithm Comparison
10.6.4 Experimental Results. 10.6.4.1 Trace Analysis
10.6.4.2 Results Without Data Replication
10.6.4.3 Results with Data Replication
10.6.4.4 Summary
10.7 Conclusion
Acknowledgement
References
11 Modeling and Simulation of Distributed Fog Environment Using FogNetSim++
11.1 Introduction
11.2 Modeling and Simulation
11.3 FogNetSim++: Architecture
11.4 FogNetSim++: Installation and Environment Setup
11.4.1 OMNeT++ Installation
11.4.2 FogNetSim++ Installation
11.4.3 Sample Fog Simulation
11.5 Conclusion
References
Notes
12 Distributed Machine Learning for IoT Applications in the Fog
12.1 Introduction
12.2 Challenges in Data Processing for IoT
12.2.1 Big Data in IoT
12.2.2 Big Data Stream
12.2.3 Data Stream Processing
12.3 Computational Intelligence and Fog Computing
12.3.1 Machine Learning
12.3.2 Deep Learning
12.4 Challenges for Running Machine Learning on Fog Devices
12.4.1 Solutions Available on the Market to Deploy ML on Fog Devices
12.5 Approaches to Distribute Intelligence on Fog Devices
12.6 Final Remarks
Acknowledgments
References
Notes
13 Fog Computing-Based Communication Systems for Modern Smart Grids
13.1 Introduction
13.2 An Overview of Communication Technologies in Smart Grid
13.3 Distribution Management System (DMS) Based on Fog/Cloud Computing
13.4 Real-time Simulation of the Proposed Feeder-based Communication Scheme Using MATLAB and ThingSpeak
13.5 Conclusion
References
14 An Estimation of Distribution Algorithm to Optimize the Utility of Task Scheduling Under Fog Computing Systems
14.1 Introduction
14.2 Estimation of Distribution Algorithm
14.3 Related Work
14.4 Problem Statement
14.5 Details of Proposed Algorithm
14.5.1 Encoding and Decoding Method
14.5.2 uEDA Scheme
14.5.2.1 Probability Model and Initialization
14.5.2.2 Updating and Sampling Method
14.5.3 Local Search Method
Algorithm 14.1 Local Search Method
14.6 Simulation
14.6.1 Comparison Algorithm
Algorithm 14.2 Modified Heuristic Algorithm
14.6.2 Simulation Environment and Experiment Settings
14.6.3 Compared with the Heuristic Method
14.7 Conclusion
References
15 Reliable and Power-Efficient Machine Learning in Wearable Sensors
15.1 Introduction
15.2 Preliminaries and Related Work
15.2.1 Gold Standard MET Computation
15.2.2 Sensor-based MET Estimation
15.2.3 Unreliability Mitigation
15.2.4 Transfer Learning
15.3 System Architecture and Methods
15.3.1 Reliable MET Calculation
15.3.1.1 Sensor Localization
15.3.1.2 MET Value Estimation
15.3.2 The Reconfigurable MET Estimation System
Algorithm 15.1 Transfer Label Algorithm
15.4 Data Collection and Experimental Procedures
15.4.1 Exergaming Experiment
15.4.2 Treadmill Experiment
15.5 Results
15.5.1 Reliable MET Calculation
15.5.1.1 Sensor Localization
15.5.1.2 MET Value Estimation
15.5.1.3 The Impact of Sensor Localization
15.5.2 Reconfigurable Design
15.5.2.1 Treadmill Experiment
15.5.2.2 Exergaming Experiment
15.6 Discussion and Future Work
15.7 Summary
References
16 Insights into Software-Defined Networking and Applications in Fog Computing
16.1 Introduction
16.2 OpenFlow Protocol
16.2.1 OpenFlow Switch
16.3 SDN-Based Research Works
16.4 SDN in Fog Computing
16.5 SDN in Wireless Mesh Networks. 16.5.1 Challenges in Wireless Mesh Networks
16.5.2 SDN Technique in WMNs
16.5.3 Benefits of SDN in WMNs
16.5.4 Fault Tolerance in SDN-based WMNs
16.6 SDN in Wireless Sensor Networks. 16.6.1 Challenges in Wireless Sensor Networks
16.6.2 SDN in Wireless Sensor Networks
16.6.3 Sensor Open Flow
16.6.4 Home Networks Using SDWN
16.6.5 Securing Software Defined Wireless Networks (SDWN)
16.7 Conclusion
References
17 Time-Critical Fog Computing for Vehicular Networks
17.1 Introduction
17.2 Applications and Timeliness Guarantees and Perturbations
17.2.1 Application Scenarios
17.2.2 Application Model
17.2.3 Timeliness Guarantees
17.2.4 Benchmarking Vehicular Applications Concerning Timeliness Guarantees
17.2.5 Building Blocks to Reach Timeliness Guarantees
17.2.6 Timeliness Perturbations
17.2.6.1 Constraints
17.2.6.2 Failures
17.2.6.3 Threats
17.3 Coping with Perturbation to Meet Timeliness Guarantees
17.3.1 Coping with Constraints
17.3.1.1 Network Resource Management
17.3.1.2 Computational Resource and Data Management
17.3.2 Coping with Failures
17.3.3 Coping with Threats
17.4 Research Gaps and Future Research Directions
17.4.1 Mobile Fog Computing
17.4.2 Fog Service Level Agreement (SLA)
17.5 Conclusion
References
18 A Reliable and Efficient Fog-Based Architecture for Autonomous Vehicular Networks
18.1 Introduction
18.2 Proposed Methodology
18.3 Hypothesis Formulation
18.4 Simulation Design
18.4.1 Results and Discussions
18.4.2 Hypothesis Testing
18.4.2.1 First Hypothesis
18.4.2.2 Second Hypothesis
18.4.2.3 Third Hypothesis
18.5 Conclusions
References
19 Fog Computing to Enable Geospatial Video Analytics for Disaster-incident Situational Awareness
19.1 Introduction
19.1.1 How Can Geospatial Video Analytics Help with Disaster-Incident Situational Awareness?
19.1.2 Fog Computing for Geospatial Video Analytics
19.1.3 Function-Centric Cloud/Fog Computing Paradigm
19.1.4 Function-Centric Fog/Cloud Computing Challenges
19.1.5 Chapter Organization
19.2 Computer Vision Application Case Studies and FCC Motivation
19.2.1 Patient Tracking with Face Recognition Case Study. 19.2.1.1 Application's 3C Pipeline Needs
19.2.1.2 Face Recognition Pipeline Details
19.2.2 3-D Scene Reconstruction from LIDAR Scans. 19.2.2.1 Application's 3C Pipeline Needs
19.2.2.2 3-D Scene Reconstruction Pipeline Details
19.2.3 Tracking Objects of Interest in WAMI. 19.2.3.1 Application's 3C Pipeline Needs
19.2.3.2 Object Tracking Pipeline Details
19.3 Geospatial Video Analytics Data Collection Using Edge Routing
19.3.1 Network Edge Geographic Routing Challenges
19.3.2 Artificial Intelligence Relevance in Geographic Routing
19.3.3 AI-Augmented Geographic Routing Implementation
19.4 Fog/Cloud Data Processing for Geospatial Video Analytics Consumption
19.4.1 Geo-Distributed Latency-Sensitive SFC Challenges
19.4.1.1 SFC Optimality
19.4.1.2 SFC Reliability
19.4.1.3 Our Approach
19.4.2 Metapath-Based Composite Variable Approach
19.4.2.1 Metalinks and Metapaths
19.4.2.2 Constrained Shortest Metapaths
19.4.2.3 Multiple-link Chain Composition via Metapath
19.4.2.4 Allowable Fitness Functions for Metapath-Based Variables
19.4.2.5 Metapath Composite Variable Approach Results
19.4.3 Metapath-Based SFC Orchestration Implementation
19.4.3.1 Control Applications
19.4.3.2 SCL
19.4.3.3 SDN and Hypervisor
19.5 Concluding Remarks. 19.5.1 What Have We Learned?
19.5.2 The Road Ahead and Open Problems
References
Note
20 An Insight into 5G Networks with Fog Computing
20.1 Introduction
20.2 Vision of 5G
20.3 Fog Computing with 5G Networks. 20.3.1 Fog Computing
20.3.2 The Need of Fog Computing in 5G Networks
20.4 Architecture of 5G. 20.4.1 Cellular Architecture
20.4.2 Energy Efficiency
20.4.3 Two-Tier Architecture
20.4.4 Cognitive Radio
20.4.5 Cloud-Based Architecture
20.5 Technology and Methodology for 5G
20.5.1 HetNet
HTC Use Case
MTC Use Case
CTC Use Case
20.5.2 Beam Division Multiple Access (BDMA)
20.5.3 Mixed Bandwidth Data Path
20.5.4 Wireless Virtualization
20.5.5 Flexible Duplex
20.5.6 Multiple-Input Multiple-Output (MIMO)
20.5.7 M2M
20.5.8 Multibeam-Based Communication System
20.5.9 Software-Defined Networking (SDN)
20.6 Applications
20.6.1 Health Care
20.6.2 Smart Grid
20.6.3 Logistic and Tracking
20.6.4 Personal Usage
20.6.5 Virtualized Home
20.7 Challenges
20.8 Conclusion
References
21 Fog Computing for Bioinformatics Applications
21.1 Introduction
21.2 Cloud Computing
21.2.1 Service Models
21.2.2 Delivery Models
21.3 Cloud Computing Applications in Bioinformatics
21.3.1 Bioinformatics Tools Deployed as SaaS
21.3.2 Bioinformatics Platforms Deployed as PaaS
21.3.3 Bioinformatics Tools Deployed as IaaS
21.4 Fog Computing
21.5 Fog Computing for Bioinformatics Applications
21.5.1 Real-Time Microorganism Detection System
21.6 Conclusion
References
Index
WILEY END USER LICENSE AGREEMENT
