ARTIFICIAL INTELLIGENCE AND QUANTUM COMPUTING FOR ADVANCED WIRELESS NETWORKS

A comprehensive presentation of the implementation of artificial intelligence and quantum computing technology in large-scale communication networks

Increasingly dense and flexible wireless networks require the use of artificial intelligence (AI) for planning network deployment, optimization, and dynamic control. Machine learning algorithms are now often used to predict traffic and network state in order to reserve resources for smooth communication with high reliability and low latency.

In Artificial Intelligence and Quantum Computing for Advanced Wireless Networks, the authors deliver a practical and timely review of AI-based learning algorithms, with several case studies in both Python and R. The book discusses the game-theory-based learning algorithms used in decision making, along with various specific applications in wireless networks, like channel, network state, and traffic prediction. Additional chapters include Fundamentals of ML, Artificial Neural Networks (NN), Explainable and Graph NN, Learning Equilibria and Games, AI Algorithms in Networks, Fundamentals of Quantum Communications, Quantum Channel, Information Theory and Error Correction, Quantum Optimization Theory, and Quantum Internet, to name a few.

The authors offer readers an intuitive and accessible path from basic topics on machine learning through advanced concepts and techniques in quantum networks. Readers will benefit from:

A thorough introduction to the fundamentals of machine learning algorithms, including linear and logistic regression, decision trees, random forests, bagging, boosting, and support vector machines
An exploration of artificial neural networks, including multilayer neural networks, training and backpropagation, FIR architecture spatial-temporal representations, quantum ML, quantum information theory, fundamentals of quantum internet, and more
Discussions of explainable neural networks and XAI
Examinations of graph neural networks, including learning algorithms and linear and nonlinear GNNs in both classical and quantum computing technology

Perfect for network engineers, researchers, and graduate and masters students in computer science and electrical engineering, Artificial Intelligence and Quantum Computing for Advanced Wireless Networks is also an indispensable resource for IT support staff, along with policymakers and regulators who work in technology.

Savo Glisic, Professor of Telecommunications at University of Oulu, Finland, and Director of Institute for Networking Sciences. His research interest is in the area of network optimization theory, network topology control and graph theory, cognitive networks and game theory, radio resource management, QoS and queuing theory, networks information theory, protocol design, advanced routing and network coding, relaying, cellular, WLAN, ad hoc, sensor, active and bio inspired networks with emphasis on genetic algorithms and stochastic geometry. The latest interest is in the area of spectra sharing, robust heterogeneous network design, Artificial Intelligence (AI), Inter System Networking (ISN), block chains and complex networks theory. Dr. Glisic has served as the Technical Program Chairman of the third IEEE ISSSTA'94, the eighth IEEE PIMRC'97, and IEEE ICC'01. He was also Director of IEEE ComSoc MD programs.

Beatriz Lorenzo, Assistant Professor, Electrical and Computer Engineering Department, University of Massachusetts at Amherst, USA. Dr Lorenzo obtained her Ph.D degree from the University of Oulu, Finland, in 2012. She co-published Advanced Wireless Networks: 4G Cognitive Opportunistic and Cooperative Technology with Savo Glisic in 2009, and her current research interests include communication networks, wireless networks, mobile computing, dynamic networking paradigms, network economics, optimization theory. She is a member of the IEEE.

Preface

PART 1:ARTIFICIAL INTELLIGENCE

Ch 1. INTRODUCTION

1.1 Motivation

1.2 Book Structure

Ch 2 ML ALGORITHMS

2.1. Fundamentals

2.1.1. Linear Regression

2.1.2 Logistic Regression

2.1.3 Decision Tree: Regression Trees vs Classification Trees

2.1.4 Trees in R and Python

2.1.5 Bagging and Random Forest

2.1.6 Boosting GBM and XGboost

2.1.7. SVM Support Vector Machine

2.1.8 Naive Bayes , kNN, K Means

2.1.9 Dimensionality Reduction

2.2. ML Algorithms Analysis

2.2.1 Logistic Regression

2.2.2. Decision Trees Classiﬁers

2.2.3 Dimensionality reduction techniques

2 REFERENCES

Ch 3 ARTIFICIAL NEURAL NETWORKS

3.1 Multi-layer Feedforward Neural Networks

3.1.1 Single Neurons

3.1.2 Weights Optimization

3.2 FIR Architecture

3.2.1 Spatial Temporal Representations

3.2.2. Neural Network Unfolding

3.2.3 Adaptation

3.3 Time Series Prediction

3.3.1 Adaptation and Iterated Predictions

3.4. Recurrent Neural Networks

3.4.1 Filters as Predictors

3.4.2 Feedback Options in Recurrent Neural Networks

3.4.3 Advanced RNN Architectures

3.5 Cellular Neural Networks (CeNN)

3.6 Convolutional CoNN

3.6.1 CoNN Architecture

3.6.2 Layers in CoNN

3 REFERENCES

Ch 4 EXPLAINABLE NN

4.1 Explainability Methods

4.1.1 The complexity and Interoperability

4.1.2 Global Versus Local Interpretabity

4.1.3 Model Extraction

4.2 Relevance Propagation in ANN

4.2.1 Pixel-Wise Decomposition

4.2.2 Pixel-Wise Decomposition for Multilayer NN

4.3 Rule Extraction from LSTM Networks

4.4 Accuracy and Interpretability

4.4.1 Fuzzy Models

4.4.2 Support Vector Regression

4.4.3 Combination of Fuzzy Models and SVR

4 REFERENCES

Ch 5 GRAPH NEURAL NETWORKS

5.1 Concept of graph neural network (GNN)

5.1.1 Classification of Graphs

5.1.2 Propagation Types

5.1.3 Graph Networks

5.2 Categorization and Modeling of GNN

5.2.1 Recurrent Graph Neural Networks (RecGNNs)

5.2.2 Convolutional Graph Neural Networks (ConvGNNs)

5.2.3 Graph Autoencoders (GAEs)

5.2.4 Spatial‐Temporal Graph Neural Networks (STGNNs)

5.3 Complexity of NN

5.3.1 Labeled Graph NN (LGNN)

5.3.2 Computational Complexity

Appendix 5.1

Appendix 5.2 Graph Fourier Transform

Ch 6 LEARNING EQUILIBRIA AND GAMES

6.1 Learning in Games

6.1.1 Learning Equilibria of Games

6.2 Online Learning of Nash Equilibria

in Congestion Games

6.3 Minority Games

6.4 Nash Q-Learning

6.4.1 Multiagent Q‐learning

6.4.2 Convergence

6.5 Routing Games

6.5.1 Nonatomic Selfish Routing

6.5.2 Atomic Selfish Routing

6.5.3 Existence of Equilibrium

6.5.4 Reducing the Price of Anarchy

6.6. Routing with Edge Priorities

6.6.1 Computing Equilibria

6 REFERENCES

Ch 7 AI ALGORITHMS IN NETWORKS

7.1. AI Based Algorithms in Networks

7.1.2 Traffic classification

7.1.3 Traffic Routing

7.1.4 Congestion Control

7.1.5 Resource Management

7.1.6 Fault management

7.1.7 QoS and QoE management

7.1.8 Network security

7.2 ML for Caching in Small Cell Networks

7.2.1 System Model

7.3 Q-learning Based Joint Channel and Power Level Selection in Heterogeneous Cellular Networks

7.3.1 Stochastic Non‐Cooperative Game

7.3.2 Multi-Agent Q-Learning

7.3.3 Q-learning for Channel and Power Level Selection

7.4 ML for Self-Organizing Cellular Networks

7.4.1 Learning In Self-Configuration

7.4.2 RL for SON Coordination

7.4.2a SON Function Model

7.4.2b Reinforcement Learning

7.5 RL Based Caching

7.5.1 System Model

7.5.2 Optimality Conditions

7.6 Big Data Analytics in Wireless Networks

7.6.1. Evolution of Analytics

7.6.2 Data-Driven Networks Optimization

7.7. Graph Neural Networks for

7.7.1 Network Virtualization

7.7.2 GNN‐Based Dynamic Resource Management

7.8 DRL for Multioperator Network Slicing

7.8.1 System Model

7.8.2 System Optimization

7.8.3 Game Equilibria by DRL

7.9 Deep Q-Learning for Latency Limited Network Virtualization

7.9.1. System Model

7.9.2 Learning and Prediction

7.9.3 DRL for Dynamic VNF Migration

7.10 Multiarmed Bandit Estimator MBE

7.10.1 System Model

7.10.2 System Performance

7.11 Network Representation Learning

7.11.1Network properties

7.11.2 Unsupervised NRL

7.11.3 Semi‐Supervised NRL

7 REFERENCES

PART 2:QUANTUM COMPUTING

Ch8 FUNDAMENTALS OF QUANTUM COMMUNICATIONS

8.1 Introduction

8.2. Quantum Gates and Quantum Computing

8.2.1 Quantum circuits

8.2.2 Quantum algorithms

8.3 Quantum Fourier Transform

8.3.1 QFT vs FFT Revisited

8 REFERENCE

Ch 9 QUANTUM CHANNEL

INFORMATION THEORY

9.1 Communication Over a Q Channel

9.1 Quantum Information Theory

9.1.1 Density Matrix and Trace Operator

9.1.2 Quantum Measurement

9.2 Q Channel Description

9.2.1 Q Channel Entropy

9.2.2 A Bit on History

9.3 Q Channel Classical Capacities

9.3.1 Capacity of Classical Channels

9.3.2 The Private Classical Capacity

9.3.3 The Entanglement‐Assisted Classical Capacity

9.3.4 The Classical Zero‐Error Capacity

9.3.5 Entanglement‐Assisted Classical Zero‐Error Capacity

9.4 Q Channel Quantum Capacity

9.4.1 Preserving Quantum Information

9.4.2 Quantum Coherent Information

9.4.3 Connection Between Classical and Quantum Information

9.5 Quantum Channel Examples

9.5.1. Channel Maps

9.5.2. Capacities

9.5.3 Q Channel Parameters

9 REFERENCES

Ch 10 QUANTUM ERROR CORRECTION

10.1 Stabilizer codes

10.2 Surface Code

10.2.1 The rotated lattice

10.3 Fault-tolerant gates

10.3.1 Fault Tolerance

10.4 Theoretical Framework

10.4.1 Classical error correction

10.4.2. Theory of Quantum Error Correction

Appendix: Binary fields and discrete vector spaces

Appendix 1: A Bit on Noise Physics

10 REFERENCES

Ch 11 QSA ALGORITHMS

11.1 Quantum Search Algorithms

11.1.1 The Deutsch Algorithm

11.1.2 The Deutsch-Jozsa Algorithm

11.1.3 Simon’s Algorithm

11.1.4 Shor’s Algorithm

11.1.5 Quantum Phase Estimation Algorithm

11.1.6 Grover’s Quantum Search Algorithm

11.1.7 Boyer-Brassard-Høyer-Tapp Quantum Search Algorithm

11.1.8 Dürr-Høyer Quantum Search Algorithm

11.1.9 Quantum Counting Algorithm

11.1.10 Quantum Heuristic Algorithm

11.1.11 Quantum Genetic Algorithm

11.1.12 Harrow-Hassidim-Lloyd Algorithm

11.1.13 Quantum Mean Algorithm

11.1.14 Quantum Weighted Sum Algorithm

11.2 Physics of Quantum Algorithms

11.2.1 Implementation of Deutsch’s Algorithm

11.2.2 Implementation of Deutsch and Jozsa’s Algorithm

11.2.3 Ethan Bernstein and Umesh Vazirani Implementation

11.2.4 Implementation of Quantum Fourier Transform

11.2.5 Estimating Arbitrary Phases

11.2.6 Improving success probability when estimating phases

11.2.7 The Order‐Finding Problem

11.2.8 Concatenated Interference

11.2.9 DESIGN EXAMPLE2): Grover’s algorithm

11.2.10 DESIGN EXAMPLE3) :Simon’s algorithm

11.2.11 DESIGN EXAMPLE4) : Shor’s Algorithm

11 REFERENCES

Ch12. QUANTUM MACHINE LEARNING

12.1 Quantum machine learning algorithms

12.2 Quantum Neural Network Preliminaries

12.3 Quantum Classifiers with ML: Near Term Solutions

12.3.1 The Circuit‐Centric Quantum Classifier

12.3.2 Training

12.4 Gradients of Parameterized Quantum Gates

12.5 Classification with Quantum Neural Networks

12.5.1 Representation

12.5.2 Learning

12.6 Quantum Decision Tree Classifier

12.6.1 Model of the Classifier

APPENDIX: Matrix Exponential.

12 REFERENCES

Ch 13 QC OPTIMIZATION

13.1 Optimization for hybrid quantum ‐classical algorithms

13.1.1 Quantum Approximate Optimization Algorithm (QAOA)

13.2. Convex Optimization in Quantum Information Theory

13.2.1 Relative Entropy of Entanglement

13.3 Quantum Algorithms for Combinatorial Optimization Problems

13.4. QC for Linear Systems of Equations

13.4.1 Algorithm in Brief

13.4.2 Detailed Description of the Algorithm

13.4.3 Error Analysis

13.5 DESIGN EXAMPLE: QC for Multiple Regression

13.5.1 Quantum Circuit

13.6 Quantum Algorithm for Systems of Nonlinear Differential Equations

13 REFERENCES

Ch 14 QUANTUM DECISION THEORY

14.1 Potential Enablers for Qc

14.2 Quantum Game Theory

14.2.1 Definitions

14.2.2 Quantum Games

14.2.3. DESIGN EXAMPLE: Quantum routing games

14.2.4 Quantum Game for Spectrum Sharing

14.3 Quantum Decision Theory (QDT)

14.3.1 Model: quantum decision theory

14.4 Predictions in Quantum Decision Theory

14.4.1 Utility Factors

14.4.2 Classification of Lotteries by Attraction Indices

14 REFERENCES

Ch 15 QC IN WIRELESS NETWORKS

15.1 Quantum Satellite Networks

15.1.1 Satellite-Based QKD System

15.1.2 Quantum Satellite Networks Architecture

15.1.3 Routing and Resource Allocation Algorithm

15.2 QC Routing for Social Overlay Networks

15.2.1 Social Overlay Network

15.2.2 Multiple-Objective Optimization Model

15.3 Quantum Key Distribution Networks

15.3.1 QOS in QKD Overlay Networks

15.3.2 Adaptive QoS-QKD Networks

15.3.3 Routing Protocol for QKD Network

15 REFERENCE:

Ch 16 QUANTUM NETWORK ON GRAPH

16.1 Optimal Routing in Quantum Networks

16.1.1 Network Model

16.1.2 Entanglement

16.1.3 Optimal Quantum Routing

16.2 Quantum Network on Symmetric Graph

16.3 Quantum walks

16.3.1 Discrete quantum walks on a line (DQWL)

16.3.2 Performance study of DQWL

16.4 Multidimensional Quantum Walks

16.4.1 The quantum random walk

16.4.2 Quantum Random Walks on General Graphs

16.4.3 Continuous time quantum random walk

16.4.4. Searching Large Scale Graphs

16 REFERENCES

Ch 17 QUANTUM INTERNET

17.1 System Model

17.1.1 Routing Algorithms

17.1.2 Quantum Network on General Virtual Graph

17.1.3 Quantum Network on Ring and Grid Graph

17.1.4 QN on Recursively Generated Graphs (RGG)

17.1.5 Recursively Generated Virtual Graph

17.2 QN Protocol Stack

17.2.1 Preliminaries

17.2.2 QN Protocol Stack

17.2.3 Layer 3— Reliable State Linking

17.2.4 Layer 4— Region Routing

17 REFERENCES

Index

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.