Fog Computing

Assad Abbas, PhD, is an Assistant Professor in the Department of Computer Science, COMSATS University Islamabad, Pakistan. He is a member of IEEE and IEEE-Eta Kappa Nu (IEEE-HKN). Samee U. Khan, PhD, is the Walter B. Booth Endowed Professor at the North Dakota State University, Fargo, ND, USA, and is on the editorial boards of several leading journals. Albert Y. Zomaya, PhD, is the Chair Professor of High Performance Computing & Networking in the School of Computer Science, The University of Sydney. He is also the Director of the Centre for Distributed and High Performance Computing.

• List of Contributors xxiiiAcronyms xxixPart I Fog Computing Systems and Architectures 11 Mobile Fog Computing 3Chii Chang, Amnir Hadachi, Jakob Mass, and Satish Narayana Srirama1.1 Introduction 31.2 Mobile Fog Computing and Related Models 51.3 The Needs of Mobile Fog Computing 61.3.1 Infrastructural Mobile Fog Computing 71.3.2 Land Vehicular Fog 91.3.3 Marine Fog 111.3.4 Unmanned Aerial Vehicular Fog 121.3.5 User Equipment-Based Fog 131.4 Communication Technologies 151.4.1 IEEE 802.11 151.4.2 4G, 5G Standards 161.4.3 WPAN, Short-Range Technologies 171.4.4 LPWAN, Other Medium- and Long-Range Technologies 181.5 Nonfunctional Requirements 181.5.1 Heterogeneity 201.5.2 Context-Awareness 231.5.3 Tenant 251.5.4 Provider 271.5.5 Security 291.6 Open Challenges 311.6.1 Challenges in Land Vehicular Fog Computing 311.6.2 Challenges in Marine Fog Computing 321.6.3 Challenges in Unmanned Aerial Vehicular Fog Computing 321.6.4 Challenges in User Equipment-based Fog Computing 331.6.5 General Challenges 331.7 Conclusion 35Acknowledgment 36References 362 Edge and Fog: A Survey, Use Cases, and Future Challenges 43Cosmin Avasalcai, Ilir Murturi, and Schahram Dustdar2.1 Introduction 432.2 Edge Computing 442.2.1 Edge Computing Architecture 462.3 Fog Computing 472.3.1 Fog Computing Architecture 492.4 Fog and Edge Illustrative Use Cases 502.4.1 Edge Computing Use Cases 502.4.2 Fog Computing Use Cases 542.5 Future Challenges 572.5.1 Resource Management 572.5.2 Security and Privacy 582.5.3 Network Management 612.6 Conclusion 61Acknowledgment 62References 623 Deep Learning in the Era of Edge Computing: Challenges and Opportunities 67Mi Zhang, Faen Zhang, Nicholas D. Lane, Yuanchao Shu, Xiao Zeng, Biyi Fang, Shen Yan, and Hui Xu3.1 Introduction 673.2 Challenges and Opportunities 683.2.1 Memory and Computational Expensiveness of DNN Models 683.2.2 Data Discrepancy in Real-world Settings 703.2.3 Constrained Battery Life of Edge Devices 713.2.4 Heterogeneity in Sensor Data 723.2.5 Heterogeneity in Computing Units 733.2.6 Multitenancy of Deep Learning Tasks 733.2.7 Offloading to Nearby Edges 753.2.8 On-device Training 763.3 Concluding Remarks 76References 774 Caching, Security, and Mobility in Content-centric Networking 79Osman Khalid, Imran Ali Khan, Rao Naveed Bin Rais, and Assad Abbas4.1 Introduction 794.2 Caching and Fog Computing 814.3 Mobility Management in CCN 824.3.1 Classification of CCN Contents and their Mobility 834.3.2 User Mobility 834.3.3 Server-side Mobility 844.3.4 Direct Exchange for Location Update 844.3.5 Query to the Rendezvous for Location Update 844.3.6 Mobility with Indirection Point 844.3.7 Interest Forwarding 854.3.8 Proxy-based Mobility Management 854.3.9 Tunnel-based Redirection (TBR) 864.4 Security in Content-centric Networks 884.4.1 Risks Due to Caching 904.4.2 DOS Attack Risk 904.4.3 Security Model 914.5 Caching 914.5.1 Cache Allocation Approaches 914.5.2 Data Allocation Approaches 934.6 Conclusions 101References 1015 Security and Privacy Issues in Fog Computing 105Ahmad Ali, Mansoor Ahmed, Muhammad Imran, and Hasan Ali Khattak5.1 Introduction 1055.2 Trust in IoT 1075.3 Authentication 1095.3.1 Related Work 1095.4 Authorization 1135.4.1 Related Work 1145.5 Privacy 1175.5.1 Requirements of Privacy in IoT 1185.6 Web Semantics and Trust Management for Fog Computing 1205.6.1 Trust Through Web Semantics 1205.7 Discussion 1235.7.1 Authentication 1245.7.2 Authorization 1255.8 Conclusion 130References 1306 How Fog Computing Can Suppor Latency/Reliability-sensitive IoT Applications: An Overview and a Taxonomy of State-of-the-art Solutions 139Paolo Bellavista, Javier Berrocal, Antonio Corradi, Sajal K. Das, Luca Foschini, Isam Mashhour Al Jawarneh, and Alessandro Zanni6.1 Introduction 1396.2 Fog Computing for IoT: Definition and Requirements 1426.2.1 Definitions 1426.2.2 Motivations 1446.2.3 Fog Computing Requirements When Applied to Challenging IoTs Application Domains 1486.2.4 IoT Case Studies 1526.3 Fog Computing: Architectural Model 1546.3.1 Communication 1546.3.2 Security and Privacy 1566.3.3 Internet of Things 1566.3.4 Data Quality 1566.3.5 Cloudification 1576.3.6 Analytics and Decision-Making 1576.4 Fog Computing for IoT: A Taxonomy 1586.4.1 Communication 1596.4.2 Security and Privacy Layer 1656.4.3 Internet of Things 1706.4.4 Data Quality 1736.4.5 Cloudification 1796.4.6 Analytics and Decision-Making Layer 1836.5 Comparisons of Surveyed Solutions 1896.5.1 Communication 1896.5.2 Security and Privacy 1916.5.3 Internet of Things 1936.5.4 Data Quality 1946.5.5 Cloudification 1956.5.6 Analytics and Decision-Making Layer 1976.6 Challenges and Recommended Research Directions 1986.7 Concluding Remarks 201References 2027 Harnessing the Computing Continuum for Programming Our World 215Pete Beckman, Jack Dongarra, Nicola Ferrier, Geoffrey Fox, Terry Moore, Dan Reed, and Micah Beck7.1 Introduction and Overview 2157.2 Research Philosophy 2177.3 A Goal-oriented Approach to Programming the Computing Continuum 2197.3.1 A Motivating Continuum Example 2197.3.2 Goal-oriented Annotations for Intensional Specification 2217.3.3 A Mapping and Run-time System for the Computing Continuum 2227.3.4 Building Blocks and Enabling Technologies 2247.4 Summary 228References 2288 Fog Computing for Energy Harvesting-enabled Internet of Things 231S. A. Tegos, P. D. Diamantoulakis, D. S. Michalopoulos, and G. K. Karagiannidis8.1 Introduction 2318.2 System Model 2328.2.1 Computation Model 2338.2.2 Energy Harvesting Model 2358.3 Tradeoffs in EH Fog Systems 2388.3.1 Energy Consumption vs. Latency 2388.3.2 Execution Delay vs. Task Dropping Cost 2398.4 Future Research Challenges 240Acknowledgment 241References 2419 Optimizing Energy Efficiency of Wearable Sensors Using Fog-assisted Control 245Delaram Amiri, Arman Anzanpour, Iman Azimi, Amir M. Rahmani, Pasi Liljeberg, Nikil Dutt, and Marco Levorato9.1 Introduction 2459.2 Background 2479.3 Related Topics 2499.4 Design Challenges 2509.5 IoT System Architecture 2519.5.1 Fog Computing and its Benefits 2529.6 Fog-assisted Runtime Energy Management in Wearable Sensors 2539.6.1 Computational Self-Awareness 2559.6.2 Energy Optimization Algorithms 2559.6.3 Myopic Strategy 2589.6.4 MDP Strategy 2599.7 Conclusions 263Acknowledgment 264References 26410 Latency Minimization Through Optimal Data Placement in Fog Networks 269Ning Wang and Jie Wu10.1 Introduction 26910.2 RelatedWork 27210.2.1 Long-Term and Short-Term Placement 27210.2.2 Data Replication 27210.3 Problem Statement 27310.3.1 Network Model 27310.3.2 Multiple Data Placement with Budget Problem 27410.3.3 Challenges 27410.4 Delay Minimization Without Replication 27510.4.1 Problem Formulation 27510.4.2 Min-Cost Flow Formulation 27610.4.3 Complexity Reduction 27710.5 Delay Minimization with Replication 27910.5.1 Hardness Proof 27910.5.2 Single Request in Line Topology 27910.5.3 Greedy Solution in Multiple Requests 28010.5.4 Rounding Approach in Multiple Requests 28210.6 Performance Evaluation 28510.6.1 Trace Information 28510.6.2 Experimental Setting 28510.6.3 Algorithm Comparison 28610.6.4 Experimental Results 28710.7 Conclusion 289Acknowledgement 289References 29011 Modeling and Simulation of Distributed Fog Environment Using FogNetSim++ 293Tariq Qayyum, Asad Waqar Malik, Muazzam A. Khan, and Samee U. Khan11.1 Introduction 29311.2 Modeling and Simulation 29411.3 FogNetSim++: Architecture 29611.4 FogNetSim++: Installation and Environment Setup 29811.4.1 OMNeT++ Installation 29811.4.2 FogNetSim++ Installation 30011.4.3 Sample Fog Simulation 30011.5 Conclusion 305References 305Part II Fog Computing Techniques and Applications 30912 Distributed Machine Learning for IoT Applications in the Fog 311Aluizio F. Rocha Neto, Flavia C. Delicato, Thais V. Batista, and Paulo F. Pires12.1 Introduction 31112.2 Challenges in Data Processing for IoT 31412.2.1 Big Data in IoT 31512.2.2 Big Data Stream 31812.2.3 Data Stream Processing 31912.3 Computational Intelligence and Fog Computing 32212.3.1 Machine Learning 32212.3.2 Deep Learning 32612.4 Challenges for Running Machine Learning on Fog Devices 32812.4.1 Solutions Available on the Market to Deploy ML on Fog Devices 33112.5 Approaches to Distribute Intelligence on Fog Devices 33412.6 Final Remarks 340Acknowledgments 341References 34113 Fog Computing-Based Communication Systems for Modern Smart Grids 347Miodrag Forcan and Mirjana Maksimović13.1 Introduction 34713.2 An Overview of Communication Technologies in Smart Grid 34913.3 Distribution Management System (DMS) Based on Fog/Cloud Computing 35613.4 Real-time Simulation of the Proposed Feeder-based Communication Scheme Using MATLAB and ThingSpeak 35913.5 Conclusion 366References 36714 An Estimation of Distribution Algorithm to Optimize the Utility of Task Scheduling Under Fog Computing Systems 371Chu-ge Wu and Ling Wang14.1 Introduction 37114.2 Estimation of Distribution Algorithm 37214.3 Related Work 37314.4 Problem Statement 37414.5 Details of Proposed Algorithm 37614.5.1 Encoding and Decoding Method 37614.5.2 uEDA Scheme 37714.5.3 Local Search Method 37814.6 Simulation 37814.6.1 Comparison Algorithm 37814.6.2 Simulation Environment and Experiment Settings 37914.6.3 Compared with the Heuristic Method 38114.7 Conclusion 383References 38315 Reliable and Power-Efficient Machine Learning in Wearable Sensors 385Parastoo Alinia and Hassan Ghasemzadeh15.1 Introduction 38515.2 Preliminaries and Related Work 38615.2.1 Gold Standard MET Computation 38615.2.2 Sensor-based MET Estimation 38715.2.3 Unreliability Mitigation 38815.2.4 Transfer Learning 38815.3 System Architecture and Methods 38915.3.1 Reliable MET Calculation 39015.3.2 The Reconfigurable MET Estimation System 39215.4 Data Collection and Experimental Procedures 39415.4.1 Exergaming Experiment 39415.4.2 Treadmill Experiment 39515.5 Results 39615.5.1 Reliable MET Calculation 39615.5.2 Reconfigurable Design 40215.6 Discussion and Future Work 40415.7 Summary 405References 40616 Insights into Software-Defined Networking and Applications in Fog Computing 411Osman Khalid, Imran Ali Khan, and Assad Abbas16.1 Introduction 41116.2 OpenFlow Protocol 41416.2.1 OpenFlow Switch 41416.3 SDN-Based Research Works 41616.4 SDN in Fog Computing 41916.5 SDN in Wireless Mesh Networks 42116.5.1 Challenges in Wireless Mesh Networks 42116.5.2 SDN Technique in WMNs 42116.5.3 Benefits of SDN in WMNs 42316.5.4 Fault Tolerance in SDN-based WMNs 42416.6 SDN in Wireless Sensor Networks 42416.6.1 Challenges in Wireless Sensor Networks 42416.6.2 SDN in Wireless Sensor Networks 42516.6.3 Sensor Open Flow 42616.6.4 Home Networks Using SDWN 42616.6.5 Securing Software Defined Wireless Networks (SDWN) 42616.7 Conclusion 427References 42717 Time-Critical Fog Computing for Vehicular Networks 431Ahmed Chebaane, Abdelmajid Khelil, and Neeraj Suri17.1 Introduction 43117.2 Applications and Timeliness Guarantees and Perturbations 43417.2.1 Application Scenarios 43417.2.2 Application Model 43617.2.3 Timeliness Guarantees 43617.2.4 Benchmarking Vehicular Applications Concerning Timeliness Guarantees 43717.2.5 Building Blocks to Reach Timeliness Guarantees 44017.2.6 Timeliness Perturbations 44117.3 Coping with Perturbation to Meet Timeliness Guarantees 44317.3.1 Coping with Constraints 44317.3.2 Coping with Failures 44817.3.3 Coping with Threats 44817.4 Research Gaps and Future Research Directions 44917.4.1 Mobile Fog Computing 44917.4.2 Fog Service Level Agreement (SLA) 45017.5 Conclusion 451References 45118 A Reliable and Efficient Fog-Based Architecture for Autonomous Vehicular Networks 459Shuja Mughal, Kamran Sattar Awaisi, Assad Abbas, Inayat ur Rehman, Muhammad Usman Shahid Khan, and Mazhar Ali18.1 Introduction 45918.2 Proposed Methodology 46118.3 Hypothesis Formulation 46318.4 Simulation Design 46418.4.1 Results and Discussions 46418.4.2 Hypothesis Testing 46718.5 Conclusions 469References 47019 Fog Computing to Enable Geospatial Video Analytics for Disaster-incident Situational Awareness 473Dmitrii Chemodanov, Prasad Calyam, and Kannappan Palaniappan19.1 Introduction 47319.1.1 How Can Geospatial Video Analytics Help with Disaster-Incident Situational Awareness? 47319.1.2 Fog Computing for Geospatial Video Analytics 47419.1.3 Function-Centric Cloud/Fog Computing Paradigm 47519.1.4 Function-Centric Fog/Cloud Computing Challenges 47619.1.5 Chapter Organization 47719.2 Computer Vision Application Case Studies and FCC Motivation 47819.2.1 Patient Tracking with Face Recognition Case Study 47819.2.2 3-D Scene Reconstruction from LIDAR Scans 48019.2.3 Tracking Objects of Interest in WAMI 48219.3 Geospatial Video Analytics Data Collection Using Edge Routing 48419.3.1 Network Edge Geographic Routing Challenges 48419.3.2 Artificial Intelligence Relevance in Geographic Routing 48619.3.3 AI-Augmented Geographic Routing Implementation 48719.4 Fog/Cloud Data Processing for Geospatial Video Analytics Consumption 49019.4.1 Geo-Distributed Latency-Sensitive SFC Challenges 49119.4.2 Metapath-Based Composite Variable Approach 49219.4.3 Metapath-Based SFC Orchestration Implementation 49519.5 Concluding Remarks 49619.5.1 What Have We Learned? 49619.5.2 The Road Ahead and Open Problems 497References 49820 An Insight into 5G Networks with Fog Computing 505Osman Khalid, Imran Ali Khan, Rao Naveed Bin Rais, and Asad Waqar Malik20.1 Introduction 50520.2 Vision of 5G 50720.3 Fog Computing with 5G Networks 50820.3.1 Fog Computing 50820.3.2 The Need of Fog Computing in 5G Networks 50820.4 Architecture of 5G 50820.4.1 Cellular Architecture 50820.4.2 Energy Efficiency 51020.4.3 Two-Tier Architecture 51220.4.4 Cognitive Radio 51220.4.5 Cloud-Based Architecture 51320.5 Technology and Methodology for 5G 51420.5.1 HetNet 51520.5.2 Beam Division Multiple Access (BDMA) 51620.5.3 Mixed Bandwidth Data Path 51620.5.4 Wireless Virtualization 51620.5.5 Flexible Duplex 51820.5.6 Multiple-Input Multiple-Output (MIMO) 51820.5.7 M2M 51920.5.8 Multibeam-Based Communication System 52020.5.9 Software-Defined Networking (SDN) 52020.6 Applications 52120.6.1 Health Care 52120.6.2 Smart Grid 52120.6.3 Logistic and Tracking 52120.6.4 Personal Usage 52120.6.5 Virtualized Home 52220.7 Challenges 52220.8 Conclusion 524References 52421 Fog Computing for Bioinformatics Applications 529Hafeez Ur Rehman, Asad Khan, and Usman Habib21.1 Introduction 52921.2 Cloud Computing 53121.2.1 Service Models 53221.2.2 Delivery Models 53221.3 Cloud Computing Applications in Bioinformatics 53321.3.1 Bioinformatics Tools Deployed as SaaS 53321.3.2 Bioinformatics Platforms Deployed as PaaS 53521.3.3 Bioinformatics Tools Deployed as IaaS 53521.4 Fog Computing 53721.5 Fog Computing for Bioinformatics Applications 53921.5.1 Real-Time Microorganism Detection System 54121.6 Conclusion 543References 543Index 547