Mung Chiang is the Arthur LeGrand Doty Professor of Electrical Engineering at Princeton University, the Director of the Keller Center for Innovation in Engineering Education, and the Chair of Princeton Entrepreneurship Council, USA. Dr. Chiang founded the Princeton EDGE Lab in 2009 and a co-founder of OpenFog Consortium in 2015. He is the recipient of the 2013 Alan T. Waterman Award by US National Science Foundation. Bharath Balasubramanian is a distributed systems researcher in the Cloud Software Research Department at ATT Labs Research, USA. Prior to this, he was a postdoc in the Electrical Engineering Department at Princeton University, working with Mung Chiang in the EDGE Lab. Flavio Bonomi is the CEO of Nebbiolo Technologies, USA. Before that he was a Vice President and Fellow at Cisco, USA.

• Contributors xiIntroduction 1Bharath Balasubramanian, Mung Chiang, and Flavio BonomiI.1 Summary of Chapters 5I.2 Acknowledgments 7References 8I Communication and Management of Fog 111 ParaDrop: An Edge Computing Platform in Home Gateways 13Suman Banerjee, Peng Liu, Ashish Patro, and Dale Willis1.1 Introduction 131.1.1 Enabling Multitenant Wireless Gateways and Applications through ParaDrop 141.1.2 ParaDrop Capabilities 151.2 Implementing Services for the ParaDrop Platform 171.3 Develop Services for ParaDrop 191.3.1 A Security Camera Service Using ParaDrop 191.3.2 An Environmental Sensor Service Using ParaDrop 22References 232 Mind Your Own Bandwidth 24Carlee Joe-Wong, Sangtae Ha, Zhenming Liu, Felix Ming Fai Wong, and Mung Chiang2.1 Introduction 242.1.1 Leveraging the Fog 252.1.2 A Home Solution to a Home Problem 252.2 Related Work 282.3 Credit Distribution and Optimal Spending 282.3.1 Credit Distribution 292.3.2 Optimal Credit Spending 312.4 An Online Bandwidth Allocation Algorithm 322.4.1 Estimating Other Gateways’ Spending 322.4.2 Online Spending Decisions and App Prioritization 342.5 Design and Implementation 352.5.1 Traffic and Device Classification 372.5.2 Rate Limiting Engine 372.5.3 Traffic Prioritization Engine 382.6 Experimental Results 392.6.1 Rate Limiting 392.6.2 Traffic Prioritization 412.7 Gateway Sharing Results 412.8 Concluding Remarks 45Acknowledgments 46Appendix 2.A 462.A.1 Proof of Lemma 2.1 462.A.2 Proof of Lemma 2.2 462.A.3 Proof of Proposition 2.1 472.A.4 Proof of Proposition 2.2 482.A.5 Proof of Proposition 2.3 492.A.6 Proof of Proposition 2.4 49References 503 Socially-Aware Cooperative D2D and D4D Communications toward Fog Networking 52Xu Chen, Junshan Zhang, and Satyajayant Misra3.1 Introduction 523.1.1 From Social Trust and Social Reciprocity to D2D Cooperation 543.1.2 Smart Grid: An IoT Case for Socially-Aware Cooperative D2D and D4D Communications 553.1.3 Summary of Main Results 573.2 Related Work 583.3 System Model 593.3.1 Physical (Communication) Graph Model 603.3.2 Social Graph Model 613.4 Socially-Aware Cooperative D2D and D4D Communications toward Fog Networking 623.4.1 Social Trust-Based Relay Selection 633.4.2 Social Reciprocity-Based Relay Selection 633.4.3 Social Trust and Social Reciprocity-Based Relay Selection 683.5 Network Assisted Relay Selection Mechanism 693.5.1 Reciprocal Relay Selection Cycle Finding 693.5.2 NARS Mechanism 703.5.3 Properties of NARS Mechanism 733.6 Simulations 753.6.1 Erdos–Renyi Social Graph 763.6.2 Real Trace Based Social Graph 783.7 Conclusion 82Acknowledgments 82References 834 You Deserve Better Properties (From Your Smart Devices) 86Steven Y. Ko4.1 Why We Need to Provide Better Properties 864.2 Where We Need to Provide Better Properties 874.3 What Properties We Need to Provide and How 884.3.1 Transparency 884.3.2 Predictable Performance 934.3.3 Openness 994.4 Conclusions 102Acknowledgment 102References 103II Storage and Computation in Fog 1075 Distributed Caching for Enhancing Communications Efficiency 109A. Salman Avestimehr and Andreas F. Molisch5.1 Introduction 1095.2 Femtocaching 1115.2.1 System Model 1115.2.2 Adaptive Streaming from Helper Stations 1145.3 User-Caching 1155.3.1 Cluster-Based Caching and D2D Communications 1155.3.2 IT LinQ-Based Caching and Communications 1185.3.3 Coded Multicast 1265.4 Conclusions and Outlook 130References 1316 Wireless Video Fog: Collaborative Live Streaming with Error Recovery 133Bo Zhang, Zhi Liu, and S.-H. Gary Chan6.1 Introduction 1336.2 Related Work 1366.3 System Operation and Network Model 1386.4 Problem Formulation and Complexity 1406.4.1 NC Packet Selection Optimization 1406.4.2 Broadcaster Selection Optimization 1436.4.3 Complexity Analysis 1446.5 VBCR: A Distributed Heuristic for Live Video with Cooperative Recovery 1446.5.1 Initial Information Exchange 1456.5.2 Cooperative Recovery 1456.5.3 Updated Information Exchange 1476.5.4 Video Packet Forwarding 1476.6 Illustrative Simulation Results 1506.7 Concluding Remarks 156References 1567 Elastic Mobile Device Clouds: Leveraging Mobile Devices to Provide Cloud Computing Services at the Edge 159Karim Habak, Cong Shi, Ellen W. Zegura, Khaled A. Harras, and Mostafa Ammar7.1 Introduction 1597.2 Design Space with Examples 1617.2.1 Mont-Blanc 1627.2.2 Computing while Charging 1637.2.3 FemtoCloud 1647.2.4 Serendipity 1667.3 FemtoCloud Performance Evaluation 1687.3.1 Experimental Setup 1687.3.2 FemtoCloud Simulation Results 1697.3.3 FemtoCloud Prototype Evaluation 1737.4 Serendipity Performance Evaluation 1757.4.1 Experimental Setup 1757.4.2 Serendipity’s Performance Benefits 1767.4.3 Impact of Network Environment 1797.4.4 The Impact of the Job Properties 1827.5 Challenges 186References 186III Applications of Fog 1898 The Role of Fog Computing in the Future of the Automobile 191Flavio Bonomi, Stefan Poledna, and Wilfried Steiner8.1 Introduction 1918.2 Current Automobile Electronic Architectures 1938.3 Future Challenges of Automotive E/E Architectures and Solution Strategies 1958.4 Future Automobiles as Fog Nodes on Wheels 2008.5 Deterministic FOG Nodes on Wheels Through Real-Time Computing and Time-Triggered Technologies 2038.5.1 Deterministic Fog Node Addressing the Scalability Challenge through Virtualization 2038.5.2 Deterministic Fog Node Addressing the Connectivity and Security Challenges 2048.5.3 Emerging Use Case of Deterministic Fog Nodes in Automotive Applications—Vehicle-Wide Virtualization 2068.6 Conclusion 209References 2099 Geographic Addressing for Field Networks 211Robert J. Hall9.1 Introduction 2119.1.1 Field Networking 2119.1.2 Challenges of Field Networking 2129.2 Geographic Addressing 2149.3 SAGP: Wireless GA in the Field 2159.3.1 SAGP Processing 2169.3.2 SAGP Retransmission Heuristics 2179.3.3 Example of SAGP Packet Propagation 2189.3.4 Followcast: Efficient SAGP Streaming 2199.3.5 Meeting the Challenges 2209.4 Georouting: Extending GA to the Cloud 2219.5 SGAF: A Multi-Tiered Architecture for Large-Scale GA 2229.5.1 Bridging Between Tiers 2239.5.2 Hybrid Security Architecture 2259.6 The AT&T Labs Geocast System 2259.7 Two GA Applications 2269.7.1 PSCommander 2269.7.2 Geocast Games 2309.8 Conclusions 232References 23210 Distributed Online Learning and Stream Processing for a Smarter Planet 234Deepak S. Turaga and Mihaela van der Schaar10.1 Introduction: Smarter Planet 23410.2 Illustrative Problem: Transportation 23710.3 Stream Processing Characteristics 23810.4 Distributed Stream Processing Systems 23910.4.1 State of the Art 23910.4.2 Stream Processing Systems 24010.5 Distributed Online Learning Frameworks 24410.5.1 State of the Art 24410.5.2 Systematic Framework for Online Distributed Ensemble Learning 24710.5.3 Online Learning of the Aggregation Weights 25010.5.4 Collision Detection Application 25410.6 What Lies Ahead 257Acknowledgment 258References 25811 Securing the Internet of Things: Need for a New Paradigm and Fog Computing 261Tao Zhang, Yi Zheng, Raymond Zheng, and Helder Antunes11.1 Introduction 26111.2 New IoT Security Challenges That Necessitate Fundamental Changes to the Existing Security Paradigm 26311.2.1 Many Things Will Have Long Life Spans but Constrained and Difficult-to-Upgrade Resources 26411.2.2 Putting All IoT Devices Inside Firewalled Castles Will Become Infeasible or Impractical 26411.2.3 Mission-Critical Systems Will Demand Minimal-Impact Incident Responses 26511.2.4 The Need to Know the Security Status of a Vast Number of Devices 26611.3 A New Security Paradigm for the Internet of Things 26811.3.1 Help the Less Capable with Fog Computing 26911.3.2 Scale Security Monitoring to Large Number of Devices with Crowd Attestation 27211.3.3 Dynamic Risk–Benefit-Proportional Protection with Adaptive Immune Security 27711.4 Summary 281Acknowledgment 281References 281Index 285

Mung Chiang is the Arthur LeGrand Doty Professor of Electrical Engineering at Princeton University, the Director of the Keller Center for Innovation in Engineering Education, and the Chair of Princeton Entrepreneurship Council, USA. Dr. Chiang founded the Princeton EDGE Lab in 2009 and a co-founder of OpenFog Consortium in 2015. He is the recipient of the 2013 Alan T. Waterman Award by US National Science Foundation. Bharath Balasubramanian is a distributed systems researcher in the Cloud Software Research Department at ATT Labs Research, USA. Prior to this, he was a postdoc in the Electrical Engineering Department at Princeton University, working with Mung Chiang in the EDGE Lab. Flavio Bonomi is the CEO of Nebbiolo Technologies, USA. Before that he was a Vice President and Fellow at Cisco, USA.

• Contributors xiIntroduction 1Bharath Balasubramanian, Mung Chiang, and Flavio BonomiI.1 Summary of Chapters 5I.2 Acknowledgments 7References 8I Communication and Management of Fog 111 ParaDrop: An Edge Computing Platform in Home Gateways 13Suman Banerjee, Peng Liu, Ashish Patro, and Dale Willis1.1 Introduction 131.1.1 Enabling Multitenant Wireless Gateways and Applications through ParaDrop 141.1.2 ParaDrop Capabilities 151.2 Implementing Services for the ParaDrop Platform 171.3 Develop Services for ParaDrop 191.3.1 A Security Camera Service Using ParaDrop 191.3.2 An Environmental Sensor Service Using ParaDrop 22References 232 Mind Your Own Bandwidth 24Carlee Joe-Wong, Sangtae Ha, Zhenming Liu, Felix Ming Fai Wong, and Mung Chiang2.1 Introduction 242.1.1 Leveraging the Fog 252.1.2 A Home Solution to a Home Problem 252.2 Related Work 282.3 Credit Distribution and Optimal Spending 282.3.1 Credit Distribution 292.3.2 Optimal Credit Spending 312.4 An Online Bandwidth Allocation Algorithm 322.4.1 Estimating Other Gateways’ Spending 322.4.2 Online Spending Decisions and App Prioritization 342.5 Design and Implementation 352.5.1 Traffic and Device Classification 372.5.2 Rate Limiting Engine 372.5.3 Traffic Prioritization Engine 382.6 Experimental Results 392.6.1 Rate Limiting 392.6.2 Traffic Prioritization 412.7 Gateway Sharing Results 412.8 Concluding Remarks 45Acknowledgments 46Appendix 2.A 462.A.1 Proof of Lemma 2.1 462.A.2 Proof of Lemma 2.2 462.A.3 Proof of Proposition 2.1 472.A.4 Proof of Proposition 2.2 482.A.5 Proof of Proposition 2.3 492.A.6 Proof of Proposition 2.4 49References 503 Socially-Aware Cooperative D2D and D4D Communications toward Fog Networking 52Xu Chen, Junshan Zhang, and Satyajayant Misra3.1 Introduction 523.1.1 From Social Trust and Social Reciprocity to D2D Cooperation 543.1.2 Smart Grid: An IoT Case for Socially-Aware Cooperative D2D and D4D Communications 553.1.3 Summary of Main Results 573.2 Related Work 583.3 System Model 593.3.1 Physical (Communication) Graph Model 603.3.2 Social Graph Model 613.4 Socially-Aware Cooperative D2D and D4D Communications toward Fog Networking 623.4.1 Social Trust-Based Relay Selection 633.4.2 Social Reciprocity-Based Relay Selection 633.4.3 Social Trust and Social Reciprocity-Based Relay Selection 683.5 Network Assisted Relay Selection Mechanism 693.5.1 Reciprocal Relay Selection Cycle Finding 693.5.2 NARS Mechanism 703.5.3 Properties of NARS Mechanism 733.6 Simulations 753.6.1 Erdos–Renyi Social Graph 763.6.2 Real Trace Based Social Graph 783.7 Conclusion 82Acknowledgments 82References 834 You Deserve Better Properties (From Your Smart Devices) 86Steven Y. Ko4.1 Why We Need to Provide Better Properties 864.2 Where We Need to Provide Better Properties 874.3 What Properties We Need to Provide and How 884.3.1 Transparency 884.3.2 Predictable Performance 934.3.3 Openness 994.4 Conclusions 102Acknowledgment 102References 103II Storage and Computation in Fog 1075 Distributed Caching for Enhancing Communications Efficiency 109A. Salman Avestimehr and Andreas F. Molisch5.1 Introduction 1095.2 Femtocaching 1115.2.1 System Model 1115.2.2 Adaptive Streaming from Helper Stations 1145.3 User-Caching 1155.3.1 Cluster-Based Caching and D2D Communications 1155.3.2 IT LinQ-Based Caching and Communications 1185.3.3 Coded Multicast 1265.4 Conclusions and Outlook 130References 1316 Wireless Video Fog: Collaborative Live Streaming with Error Recovery 133Bo Zhang, Zhi Liu, and S.-H. Gary Chan6.1 Introduction 1336.2 Related Work 1366.3 System Operation and Network Model 1386.4 Problem Formulation and Complexity 1406.4.1 NC Packet Selection Optimization 1406.4.2 Broadcaster Selection Optimization 1436.4.3 Complexity Analysis 1446.5 VBCR: A Distributed Heuristic for Live Video with Cooperative Recovery 1446.5.1 Initial Information Exchange 1456.5.2 Cooperative Recovery 1456.5.3 Updated Information Exchange 1476.5.4 Video Packet Forwarding 1476.6 Illustrative Simulation Results 1506.7 Concluding Remarks 156References 1567 Elastic Mobile Device Clouds: Leveraging Mobile Devices to Provide Cloud Computing Services at the Edge 159Karim Habak, Cong Shi, Ellen W. Zegura, Khaled A. Harras, and Mostafa Ammar7.1 Introduction 1597.2 Design Space with Examples 1617.2.1 Mont-Blanc 1627.2.2 Computing while Charging 1637.2.3 FemtoCloud 1647.2.4 Serendipity 1667.3 FemtoCloud Performance Evaluation 1687.3.1 Experimental Setup 1687.3.2 FemtoCloud Simulation Results 1697.3.3 FemtoCloud Prototype Evaluation 1737.4 Serendipity Performance Evaluation 1757.4.1 Experimental Setup 1757.4.2 Serendipity’s Performance Benefits 1767.4.3 Impact of Network Environment 1797.4.4 The Impact of the Job Properties 1827.5 Challenges 186References 186III Applications of Fog 1898 The Role of Fog Computing in the Future of the Automobile 191Flavio Bonomi, Stefan Poledna, and Wilfried Steiner8.1 Introduction 1918.2 Current Automobile Electronic Architectures 1938.3 Future Challenges of Automotive E/E Architectures and Solution Strategies 1958.4 Future Automobiles as Fog Nodes on Wheels 2008.5 Deterministic FOG Nodes on Wheels Through Real-Time Computing and Time-Triggered Technologies 2038.5.1 Deterministic Fog Node Addressing the Scalability Challenge through Virtualization 2038.5.2 Deterministic Fog Node Addressing the Connectivity and Security Challenges 2048.5.3 Emerging Use Case of Deterministic Fog Nodes in Automotive Applications—Vehicle-Wide Virtualization 2068.6 Conclusion 209References 2099 Geographic Addressing for Field Networks 211Robert J. Hall9.1 Introduction 2119.1.1 Field Networking 2119.1.2 Challenges of Field Networking 2129.2 Geographic Addressing 2149.3 SAGP: Wireless GA in the Field 2159.3.1 SAGP Processing 2169.3.2 SAGP Retransmission Heuristics 2179.3.3 Example of SAGP Packet Propagation 2189.3.4 Followcast: Efficient SAGP Streaming 2199.3.5 Meeting the Challenges 2209.4 Georouting: Extending GA to the Cloud 2219.5 SGAF: A Multi-Tiered Architecture for Large-Scale GA 2229.5.1 Bridging Between Tiers 2239.5.2 Hybrid Security Architecture 2259.6 The AT&T Labs Geocast System 2259.7 Two GA Applications 2269.7.1 PSCommander 2269.7.2 Geocast Games 2309.8 Conclusions 232References 23210 Distributed Online Learning and Stream Processing for a Smarter Planet 234Deepak S. Turaga and Mihaela van der Schaar10.1 Introduction: Smarter Planet 23410.2 Illustrative Problem: Transportation 23710.3 Stream Processing Characteristics 23810.4 Distributed Stream Processing Systems 23910.4.1 State of the Art 23910.4.2 Stream Processing Systems 24010.5 Distributed Online Learning Frameworks 24410.5.1 State of the Art 24410.5.2 Systematic Framework for Online Distributed Ensemble Learning 24710.5.3 Online Learning of the Aggregation Weights 25010.5.4 Collision Detection Application 25410.6 What Lies Ahead 257Acknowledgment 258References 25811 Securing the Internet of Things: Need for a New Paradigm and Fog Computing 261Tao Zhang, Yi Zheng, Raymond Zheng, and Helder Antunes11.1 Introduction 26111.2 New IoT Security Challenges That Necessitate Fundamental Changes to the Existing Security Paradigm 26311.2.1 Many Things Will Have Long Life Spans but Constrained and Difficult-to-Upgrade Resources 26411.2.2 Putting All IoT Devices Inside Firewalled Castles Will Become Infeasible or Impractical 26411.2.3 Mission-Critical Systems Will Demand Minimal-Impact Incident Responses 26511.2.4 The Need to Know the Security Status of a Vast Number of Devices 26611.3 A New Security Paradigm for the Internet of Things 26811.3.1 Help the Less Capable with Fog Computing 26911.3.2 Scale Security Monitoring to Large Number of Devices with Crowd Attestation 27211.3.3 Dynamic Risk–Benefit-Proportional Protection with Adaptive Immune Security 27711.4 Summary 281Acknowledgment 281References 281Index 285

Mung Chiang is the Arthur LeGrand Doty Professor of Electrical Engineering at Princeton University, the Director of the Keller Center for Innovation in Engineering Education, and the Chair of Princeton Entrepreneurship Council, USA. Dr. Chiang founded the Princeton EDGE Lab in 2009 and a co-founder of OpenFog Consortium in 2015. He is the recipient of the 2013 Alan T. Waterman Award by US National Science Foundation. Bharath Balasubramanian is a distributed systems researcher in the Cloud Software Research Department at ATT Labs Research, USA. Prior to this, he was a postdoc in the Electrical Engineering Department at Princeton University, working with Mung Chiang in the EDGE Lab. Flavio Bonomi is the CEO of Nebbiolo Technologies, USA. Before that he was a Vice President and Fellow at Cisco, USA.

• Contributors xiIntroduction 1Bharath Balasubramanian, Mung Chiang, and Flavio BonomiI.1 Summary of Chapters 5I.2 Acknowledgments 7References 8I Communication and Management of Fog 111 ParaDrop: An Edge Computing Platform in Home Gateways 13Suman Banerjee, Peng Liu, Ashish Patro, and Dale Willis1.1 Introduction 131.1.1 Enabling Multitenant Wireless Gateways and Applications through ParaDrop 141.1.2 ParaDrop Capabilities 151.2 Implementing Services for the ParaDrop Platform 171.3 Develop Services for ParaDrop 191.3.1 A Security Camera Service Using ParaDrop 191.3.2 An Environmental Sensor Service Using ParaDrop 22References 232 Mind Your Own Bandwidth 24Carlee Joe-Wong, Sangtae Ha, Zhenming Liu, Felix Ming Fai Wong, and Mung Chiang2.1 Introduction 242.1.1 Leveraging the Fog 252.1.2 A Home Solution to a Home Problem 252.2 Related Work 282.3 Credit Distribution and Optimal Spending 282.3.1 Credit Distribution 292.3.2 Optimal Credit Spending 312.4 An Online Bandwidth Allocation Algorithm 322.4.1 Estimating Other Gateways’ Spending 322.4.2 Online Spending Decisions and App Prioritization 342.5 Design and Implementation 352.5.1 Traffic and Device Classification 372.5.2 Rate Limiting Engine 372.5.3 Traffic Prioritization Engine 382.6 Experimental Results 392.6.1 Rate Limiting 392.6.2 Traffic Prioritization 412.7 Gateway Sharing Results 412.8 Concluding Remarks 45Acknowledgments 46Appendix 2.A 462.A.1 Proof of Lemma 2.1 462.A.2 Proof of Lemma 2.2 462.A.3 Proof of Proposition 2.1 472.A.4 Proof of Proposition 2.2 482.A.5 Proof of Proposition 2.3 492.A.6 Proof of Proposition 2.4 49References 503 Socially-Aware Cooperative D2D and D4D Communications toward Fog Networking 52Xu Chen, Junshan Zhang, and Satyajayant Misra3.1 Introduction 523.1.1 From Social Trust and Social Reciprocity to D2D Cooperation 543.1.2 Smart Grid: An IoT Case for Socially-Aware Cooperative D2D and D4D Communications 553.1.3 Summary of Main Results 573.2 Related Work 583.3 System Model 593.3.1 Physical (Communication) Graph Model 603.3.2 Social Graph Model 613.4 Socially-Aware Cooperative D2D and D4D Communications toward Fog Networking 623.4.1 Social Trust-Based Relay Selection 633.4.2 Social Reciprocity-Based Relay Selection 633.4.3 Social Trust and Social Reciprocity-Based Relay Selection 683.5 Network Assisted Relay Selection Mechanism 693.5.1 Reciprocal Relay Selection Cycle Finding 693.5.2 NARS Mechanism 703.5.3 Properties of NARS Mechanism 733.6 Simulations 753.6.1 Erdos–Renyi Social Graph 763.6.2 Real Trace Based Social Graph 783.7 Conclusion 82Acknowledgments 82References 834 You Deserve Better Properties (From Your Smart Devices) 86Steven Y. Ko4.1 Why We Need to Provide Better Properties 864.2 Where We Need to Provide Better Properties 874.3 What Properties We Need to Provide and How 884.3.1 Transparency 884.3.2 Predictable Performance 934.3.3 Openness 994.4 Conclusions 102Acknowledgment 102References 103II Storage and Computation in Fog 1075 Distributed Caching for Enhancing Communications Efficiency 109A. Salman Avestimehr and Andreas F. Molisch5.1 Introduction 1095.2 Femtocaching 1115.2.1 System Model 1115.2.2 Adaptive Streaming from Helper Stations 1145.3 User-Caching 1155.3.1 Cluster-Based Caching and D2D Communications 1155.3.2 IT LinQ-Based Caching and Communications 1185.3.3 Coded Multicast 1265.4 Conclusions and Outlook 130References 1316 Wireless Video Fog: Collaborative Live Streaming with Error Recovery 133Bo Zhang, Zhi Liu, and S.-H. Gary Chan6.1 Introduction 1336.2 Related Work 1366.3 System Operation and Network Model 1386.4 Problem Formulation and Complexity 1406.4.1 NC Packet Selection Optimization 1406.4.2 Broadcaster Selection Optimization 1436.4.3 Complexity Analysis 1446.5 VBCR: A Distributed Heuristic for Live Video with Cooperative Recovery 1446.5.1 Initial Information Exchange 1456.5.2 Cooperative Recovery 1456.5.3 Updated Information Exchange 1476.5.4 Video Packet Forwarding 1476.6 Illustrative Simulation Results 1506.7 Concluding Remarks 156References 1567 Elastic Mobile Device Clouds: Leveraging Mobile Devices to Provide Cloud Computing Services at the Edge 159Karim Habak, Cong Shi, Ellen W. Zegura, Khaled A. Harras, and Mostafa Ammar7.1 Introduction 1597.2 Design Space with Examples 1617.2.1 Mont-Blanc 1627.2.2 Computing while Charging 1637.2.3 FemtoCloud 1647.2.4 Serendipity 1667.3 FemtoCloud Performance Evaluation 1687.3.1 Experimental Setup 1687.3.2 FemtoCloud Simulation Results 1697.3.3 FemtoCloud Prototype Evaluation 1737.4 Serendipity Performance Evaluation 1757.4.1 Experimental Setup 1757.4.2 Serendipity’s Performance Benefits 1767.4.3 Impact of Network Environment 1797.4.4 The Impact of the Job Properties 1827.5 Challenges 186References 186III Applications of Fog 1898 The Role of Fog Computing in the Future of the Automobile 191Flavio Bonomi, Stefan Poledna, and Wilfried Steiner8.1 Introduction 1918.2 Current Automobile Electronic Architectures 1938.3 Future Challenges of Automotive E/E Architectures and Solution Strategies 1958.4 Future Automobiles as Fog Nodes on Wheels 2008.5 Deterministic FOG Nodes on Wheels Through Real-Time Computing and Time-Triggered Technologies 2038.5.1 Deterministic Fog Node Addressing the Scalability Challenge through Virtualization 2038.5.2 Deterministic Fog Node Addressing the Connectivity and Security Challenges 2048.5.3 Emerging Use Case of Deterministic Fog Nodes in Automotive Applications—Vehicle-Wide Virtualization 2068.6 Conclusion 209References 2099 Geographic Addressing for Field Networks 211Robert J. Hall9.1 Introduction 2119.1.1 Field Networking 2119.1.2 Challenges of Field Networking 2129.2 Geographic Addressing 2149.3 SAGP: Wireless GA in the Field 2159.3.1 SAGP Processing 2169.3.2 SAGP Retransmission Heuristics 2179.3.3 Example of SAGP Packet Propagation 2189.3.4 Followcast: Efficient SAGP Streaming 2199.3.5 Meeting the Challenges 2209.4 Georouting: Extending GA to the Cloud 2219.5 SGAF: A Multi-Tiered Architecture for Large-Scale GA 2229.5.1 Bridging Between Tiers 2239.5.2 Hybrid Security Architecture 2259.6 The AT&T Labs Geocast System 2259.7 Two GA Applications 2269.7.1 PSCommander 2269.7.2 Geocast Games 2309.8 Conclusions 232References 23210 Distributed Online Learning and Stream Processing for a Smarter Planet 234Deepak S. Turaga and Mihaela van der Schaar10.1 Introduction: Smarter Planet 23410.2 Illustrative Problem: Transportation 23710.3 Stream Processing Characteristics 23810.4 Distributed Stream Processing Systems 23910.4.1 State of the Art 23910.4.2 Stream Processing Systems 24010.5 Distributed Online Learning Frameworks 24410.5.1 State of the Art 24410.5.2 Systematic Framework for Online Distributed Ensemble Learning 24710.5.3 Online Learning of the Aggregation Weights 25010.5.4 Collision Detection Application 25410.6 What Lies Ahead 257Acknowledgment 258References 25811 Securing the Internet of Things: Need for a New Paradigm and Fog Computing 261Tao Zhang, Yi Zheng, Raymond Zheng, and Helder Antunes11.1 Introduction 26111.2 New IoT Security Challenges That Necessitate Fundamental Changes to the Existing Security Paradigm 26311.2.1 Many Things Will Have Long Life Spans but Constrained and Difficult-to-Upgrade Resources 26411.2.2 Putting All IoT Devices Inside Firewalled Castles Will Become Infeasible or Impractical 26411.2.3 Mission-Critical Systems Will Demand Minimal-Impact Incident Responses 26511.2.4 The Need to Know the Security Status of a Vast Number of Devices 26611.3 A New Security Paradigm for the Internet of Things 26811.3.1 Help the Less Capable with Fog Computing 26911.3.2 Scale Security Monitoring to Large Number of Devices with Crowd Attestation 27211.3.3 Dynamic Risk–Benefit-Proportional Protection with Adaptive Immune Security 27711.4 Summary 281Acknowledgment 281References 281Index 285