6G Enabled Fog Computing in IoT: Applications and Opportunities

✍ Scribed by Mohit Kumar (editor), Sukhpal Singh Gill (editor), Jitendra Kumar Samriya (editor), Steve Uhlig (editor)

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 416
• Edition: 1st ed. 2023
• Category: Library

✦ Synopsis

Over the past few years, the demand for data traffic has experienced explosive growth thanks to the increasing need to stay online. New applications of communications, such as wearable devices, autonomous systems, drones, and the Internet of Things (IoT), continue to emerge and generate even more data traffic with vastly different performance requirements. With the COVID-19 pandemic, the need to stay online has become even more crucial, as most of the fields, would they be industrial, educational, economic, or service-oriented, had to go online as best as they can. As the data traffic is expected to continuously strain the capacity of future communication networks, these networks need to evolve consistently in order to keep up with the growth of data traffic. Thus, more intelligent processing, operation, and optimization will be needed for tomorrow’s communication networks. The Sixth Generation (6G) technology is latest approach for mobile systems or edge devices in terms of reduce traffic congestions, energy consumption blending with IoT devices applications. The 6G network works beyond the 5G (B5G), where we can use various platforms as an application e.g. fog computing enabled IoT networks, Intelligent techniques for SDN network, 6G enabled healthcare industry, energy aware location management. Still this technology must resolve few challenges like security, IoT enabled trust network.
This book will focus on the use of AI/ML-based techniques to solve issues related to 6G enabled networks, their layers, as well as their applications. It will be a collection of original contributions regarding state-of-the-art AI/ML-based solutions for signal detection, channel modeling, resource optimization, routing protocol design, transport layer optimization, user/application behavior prediction 6G enabled software-defined networking, congestion control, communication network optimization, security, and anomaly detection. The proposed edited book emphasis on the 6G network blended with Fog-IoT networks to introduce its applications and future perspectives that helps the researcher to apply this technique in their domain and it may also helpful to resolve the challenges and future opportunities with 6G networks.

✦ Table of Contents

Abstract
Preface
Contents
Editors and Contributors
About the Editors
Contributors
Part I Applications
AI Enabled Resources Scheduling in Cloud Paradigm
1 Introduction to Cloud Computing
1.1 Characteristics of Cloud Computing
1.2 Deployment Models of Cloud Computing
1.3 Service Models of Cloud Computing
2 Resource Scheduling in Cloud Computing
2.1 Resource Scheduling Algorithms Modeled by Metaheuristic Approaches in Cloud Computing
2.2 Resource Scheduling Algorithms Modeled by Metaheuristic Approaches in Cloud Computing
3 Double Deep Q-Networks
4 Simulation and Results
5 Evaluation of Makespan
5.1 Evaluation of Energy Consumption
6 Conclusions and Future Research Directions
7 Future Research Directions
References
Role of AI for Data Security and Privacy in 5G Healthcare Informatics
1 Introduction
1.1 Innovation in e-Health Technology
1.2 Real-Time Data Analytics in IoT Using ML
2 Measures Undertaken for Practicing Privacy and Security in Healthcare Organizations
2.1 Data Protection Laws
3 Privacy and Security Methodologies Currently Practiced for IoT-Cloud-Based e-Health Systems
3.1 Data Encryption
3.2 Data Anonymization
3.3 Data Authentication
3.4 Access Control
3.5 Trusted Third Party Auditing
3.6 Data Search
4 Security and Privacy Threats Faced in the Domain of Healthcare
4.1 Leniency in the HIPAA Regulations
4.2 Resource Constraints for IoT Devices
4.3 Active Attacks in Information Security
4.4 Passive Attacks in Information Security
4.5 IoT Devices with Malware
5 Secure, Private and Robust ML/DL Techniques as a Countermeasure Against IoT Threats
5.1 Privacy Isolation Algorithm
5.2 Software Defined Networks (SDNs)
5.3 Network Intrusion Detection Systems (NIDS)
5.4 Application Programming Interfaces (APIs)
5.5 Deep Learning Models
5.6 Amalgamation of OpCode and Deep Learning
5.7 Federated AI Learning
5.8 Security Flaw Detection Using Twitter
6 Secure, Private, and Robust Blockchain Techniques as a Countermeasure Against IoT Threats
6.1 Cyber-Physical Systems (CPS)
6.2 Prevention of MiTM and DoS Attacks
6.3 Intrusion Detection Systems
6.4 Privacy Efforts
6.5 Countermeasures Against Other Attacks
7 Future Limitations Concerning Network Security and IoT Devices
8 Future Limitations Concerning ML/BC Approaches
9 Future Scope
10 Conclusion
References
GPU Based AI for Modern E-Commerce Applications: Performance Evaluation, Analysis and Future Directions
1 Introduction
1.1 Motivation and Our Contributions
1.2 Article Organisation
2 Related Work
2.1 Critical Analysis
3 Methodology
3.1 Dataset
3.2 Data Exploration
4 Data-Preprocessing
4.1 Null Values
4.2 Removing Outliers
4.3 Feature Generation
4.4 Data Encoding
4.5 Handling Erroneous Predictions
4.6 Model Building
4.6.1 Linear Regression
4.6.2 XGBoost
4.6.3 Neural Networks
4.6.4 AutoML
4.6.5 Catboost
4.6.6 Ensembles
5 Performance Evaluation
5.1 Configuration Settings
5.2 Results and Discussion
6 Conclusion and Future Works
6.1 Future Works
6.1.1 Leveraging Advanced Computing
6.1.2 Scaling with Distributed Machine Learning
6.1.3 Privacy-Preserving Machine Learning
References
Air Quality Index Prediction Using Various Machine Learning Algorithms
1 Introduction
2 Literature Review
3 Methodology
3.1 Dataset
3.2 Data Collection and Pre-processing
3.2.1 Independent Variable Analysis
3.3 Data Analysis
3.4 Machine Learning Algorithms
3.4.1 Support Vector Machine
3.4.2 Random Forest Model
3.4.3 Linear Regression
3.4.4 LSTM
3.4.5 Decision Tree
3.4.6 XGBoost
4 Evaluation Parameters and Implementation
5 Results and Discussion
5.1 Model Evaluation Metrics
5.1.1 Mean Absolute Error (MAE)
5.1.2 Mean Square Error (MSE)
5.1.3 Root Mean Squared Error (RMSE)
5.1.4 R-Squared Score (R2)
5.2 Model Analysis
5.2.1 Bar Plot of R2
5.2.2 Bar Plot of MSE
5.2.3 Bar Plot of MAE
5.2.4 Bar Plot of RMSE
6 Conclusion and Future Scope
References
Leveraging Cloud-Native Microservices Architecture for High Performance Real-Time Intra-Day Trading: A Tutorial
1 Introduction
1.1 Main Contributions
1.2 Article Organisation
2 Related Work
3 Technologies Used
3.1 Kafka
3.2 Kafka Message
3.3 Broker
3.4 Partition
3.5 Producer
3.6 Leading Indicators
3.7 Lagging Indicators
3.8 Microservices
3.9 Producer-Consumer
3.10 Earlier Considerations
4 Application Architecture
5 Implementation Highlights
5.1 Brief Introduction to the API
5.2 Technology Stacks
5.3 The Key Microservices Used in the Application
5.4 The Prediction Services Used in the Application
5.5 The Client Side of the Application
5.6 Firebase Cloud Database
5.7 Challenges
6 Conclusions and Future Work
6.1 Future Directions
References
Part II Architecture, Systems and Services
Efficient Resource Allocation in Virtualized Cloud Platforms Using Encapsulated Virtualization Based Ant Colony Optimization (EVACO)
1 Introduction
2 Motivation
3 Related Study
4 Traditional ACO
4.1 Apprising Pheromone Value
4.2 Evaporation
5 Proposed Solution
5.1 Formulating Primary Population for Virtualized Computing Resources
5.2 Apprising Pheromone to the Control Domain
5.3 Generation of Updated Solution
5.4 Mutating EVACO to Optimize Further
5.5 Flowchart and Service Model
6 Result Analysis
6.1 Simulation Set-Up
6.2 Simulation Result
7 Conclusion
References
Authenticated, Secured, Intelligent and Assisted Medicine Dispensing Machine for Elderly Visual Impaired People
1 Introduction
2 Related Work
3 Proposed Architecture
3.1 Dispensing Machine
3.1.1 Construction of Dispensing Machine
3.2 Authentication Process
3.2.1 Recovery of the System
3.3 Normal Operation
3.3.1 Sequence of Operation for a Chamber
4 Implementation
4.1 Database
4.2 Algorithm
4.2.1 Timely Assistance Messaging Algorithm (TMS)
4.2.2 Biometric Algorithm
4.2.3 Individual Chamber Operation Algorithm (ICO)
5 Result and Discussion
5.1 Experimental Setup
5.1.1 Medical Dispenser Monitoring and Controlling System (MDMC)
5.2 Result
5.2.1 Scenario – Filling of Tablet
5.2.2 Scenario – Overdosage Situation
5.3 Discussion
6 Conclusion
7 Future Enhancements
References
Prediction of Liver Disease Using Soft Computing and Data Science Approaches
1 Introduction
2 Motivation
3 Literature Review
4 Materials and Methods
4.1 Dataset
4.2 Algorithms Description
4.2.1 Logistic Regression
4.2.2 Gaussian Naïve Bayes
4.2.3 Stochastic Gradient Descent
4.2.4 K-Nearest Neighbours
4.2.5 Decision Tree Classifier
4.2.6 Random Forest
4.2.7 Support Vector Machine
5 Experimental Results and Discussion
6 Conclusion and Future Scope
References
Artificial Intelligence Based Transfer Learning Approach in Identifying and Detecting Covid-19 Virus from CT-Scan Images
1 Introduction
2 Related Work
2.1 Existing Limitations
3 Materials and Methods
3.1 Methodology
3.2 Preparing Dataset
3.3 Data Augmentation
3.4 Proposed Architecture
3.4.1 VGG16
3.4.2 Support Vector Machine
3.5 Machine Learning Methods
3.5.1 XGBoost
3.5.2 Random Forest
3.6 Multivariate Analysis
4 Results and Discussion
4.1 Experimental Setup
4.2 Dataset and Metrics
4.3 Hyper Parameter Selection
4.4 Experimental Results
4.4.1 Experiment 1: Cross Validation
4.4.2 Experiment 2: (Learning Curve Method)
4.5 Comparative Analysis
4.6 Limitations
5 Conclusion
References
Blockchain-Based Medical Report Management and DistributionSystem
1 Introduction
2 Literature Survey
2.1 How to Maintain Patient Control While Maintaining Public Standards for Electronic Medical Records
2.2 Blocking of Health Information Report
3 Existing System
4 Integration of Blockchain and Cloud
4.1 SaaS
4.2 PaaS
4.3 IaaS
5 Encryption/Decryption
5.1 Data Encryption
5.2 Data Decryption
6 Software Development Life Cycle (SDLC)
7 System Requirements Specification or Analysis
7.1 Functional Requirements
7.2 Non-useful Necessities
8 System Design
8.1 System Specifications
8.2 Input Design
8.3 Output Design
8.4 Implementation
9 Modules
10 UML Diagrams
10.1 Use Case Diagram
10.2 Class Diagram
10.3 ER Diagram
10.4 Deployment Diagram
10.5 Collaboration Diagram
10.6 DFD Diagram
11 Conclusions and Future Scope
References
Design of 3-D Pipe Routing for Internet of Things Networks Using Genetic Algorithm
1 Introduction
2 Literature Review
3 Genetic Algorithm
4 Methodology
4.1 Representation of 3-Dimensional Space
4.2 Mathematically Modelling of 3-d Space
4.3 Representation of Obstacles
4.4 Representation of Pipe
4.5 Problem Formulation
4.6 Implementation
4.6.1 Single Inlet Multiple Outlet
4.6.2 Single Inlet Multiple Outlet
5 Results and Discussion
5.1 Base Environment
5.2 Performance Study
5.3 Number of Generations
5.4 Number of Populations
6 Conclusion and Future Scope
References
Part III Further Reading
Intelligent Fog-IoT Networks with 6G Endorsement: Foundations, Applications, Trends and Challenges
1 Introduction
1.1 Article Organization
2 Related Studies: Current Status
3 Overview of 6G Network, IoT, and Fog Computing
3.1 6G Vision
3.2 Fog Computing
3.3 Massive IoT
4 Fog Enabled Intelligent IoT Applications: Trends and Challenges
5 Fog as a Solution to IoT Challenges
6 Conclusions and Summary
References
The Role of Machine Learning in the Advancement of 6G Technology: Opportunities and Challenges
1 Introduction
2 Literature Review
3 The Architecture of 6G
4 IoT and 6G
5 6G Challenges and AI Implications
6 Challenges in Data Collection
7 Importance of Machine Learning in 6G
8 Applications of 6G in Different Domains
9 Case Study of 6G Network
10 Conclusion and Future Scope
References
A Comprehensive Survey on Network Resource Management in SDN Enabled Data Centre Network
1 Introduction
2 Background
2.1 A Subsection Sample
2.2 Datacentre Architecture
2.3 Data Centre Design Models
3 Related Work
4 Challenges Associated with the Resource Management in SDN-DCN
5 Promising Trend and Opportunities in SDN-DCN
6 Conclusion and Future Work
References
Artificial Intelligence Advancement for 6G Communication: A Visionary Approach
1 Introduction
2 Core Technologies of 6G Communication
2.1 Eminence of Services
2.2 The Standard of Experiences
2.3 Quality of Lives
3 Internet of Everything
4 Evolution from Smart to Intelligent
5 AI Empowered 6G
5.1 Extreme Detail
5.2 Highly Capable
5.3 Overly Sensitive
6 Machine Learning with 6G
6.1 Supervised Learning
6.2 Unsupervised and Semi-supervised Learning
6.3 Reinforcement Learning
7 A Deep Learning 6G System
7.1 Artificial Neural Network (ANN)
7.2 Deep Neural Network (DNN)
7.3 Federated Instruction in the 6G
7.4 Black-Box
8 UAV with 6G
9 Automated Vehicle with 6G
9.1 Autonomous Automobiles
9.2 Automated Allied Vehicles
10 Data Science and 6G
10.1 Descriptive Examination of Data
10.2 Data Analysis for Diagnostics
10.3 Analysing Prospective Data
10.4 Predictive Data Analysis
11 Artificial Robots with 6G
11.1 Robots with Expressive Intelligence
11.2 Industrial Robots
11.3 Robots in Healthcare
11.4 Smart Cities with Robotics
12 Security, Secrecy and Discretion
13 Advanced AI/ML Techniques for 6G
13.1 Reinforcement Erudition
13.2 Transfer Learning
13.3 Federated Learning
13.4 Quantum Machine Learning
13.5 Timeline for Integrating AI/ML into 6G Standards
14 Intelligent 6G Edge Technology
14.1 Intelligent Hyper-connected Edge Networking
14.2 Split Computing with the Hyper-connected Edge Networks
14.3 Edge-Offloading Technology
15 Conceptualization of the Intelligent PHY Layer for 6G
15.1 Management of Independent Radio Resources Based on Cognitive Intelligence
15.2 Intelligent Modulation and Coding of the Channels
15.3 Channel Estimate with AI
15.4 Intelligent Spectrum Sharing and Multiple Access
16 Conclusion
References
AI Meets SDN: A Survey of Artificial Intelligent Techniques Applied to Software-Defined Networks
1 Introduction
2 Architecture of SDN
3 Artificial Intelligence in Software-Defined Networking
3.1 Supervised Learning Techniques
3.1.1 Support Vector Machines (SVM)
3.1.2 K-Nearest Neighbor (K-NN)
3.1.3 Decision Trees
3.1.4 Artificial Neural Network (ANN)
3.1.5 Ensemble Methods
3.2 Unsupervised Learning
3.2.1 K-Means Clustering
3.2.2 Self-Organizing Feature Maps (SOFM)
3.2.3 Hidden Markov Model (HMM)
3.2.4 Semi-Supervised Learning
3.2.5 Restricted Boltzmann Machine (RBM) and Deep Belief Networks (DBN)
3.3 Reinforcement Learning (RL) Techniques
3.3.1 Q-Learning
3.3.2 Deep Reinforcement Learning
4 AI Enabled SDN Controllers
4.1 AI-Enabled Traffic Classification in SDN
4.2 AI-Enabled Routing in SDN
4.3 AI-Enabled Traffic Predictions in SDN
4.4 AI-Enabled Prediction of Quality of Service/Experience
4.5 AI-Enabled Resource Management in SDN
4.6 Meta-heuristic Algorithms in SDN
5 Challenges of Applying AI Techniques in SDN
5.1 Lack of Training Datasets
5.2 Handling Large Networks with Multi-controllers
5.3 Addressing Security Aspects of SDN
5.4 Partial SDN Deployment
6 Knowledge-Defined Networking
7 Conclusion
References