Amini Optimization, Learning, and Control for Interdependent Complex Networks

1. Auflage 2020
ISBN: 978-3-030-34094-0
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 1123, 306 Seiten

Reihe: Advances in Intelligent Systems and Computing

This book focuses on a wide range of optimization, learning, and control algorithms for interdependent complex networks and their role in smart cities operation, smart energy systems, and intelligent transportation networks. It paves the way for researchers working on optimization, learning, and control spread over the ?elds of computer science, operation research, electrical engineering, civil engineering, and system engineering. This book also covers optimization algorithms for large-scale problems from theoretical foundations to real-world applications, learning-based methods to enable intelligence in smart cities, and control techniques to deal with the optimal and robust operation of complex systems. It further introduces novel algorithms for data analytics in large-scale interdependent complex networks.  •  Speci?es the importance of efficient theoretical optimization and learning methods in    dealing with emerging problems in the context of interdependent networks  •  Provides a comprehensive investigation of advance data analytics and machine learning algorithms for large-scale complex networks  •  Presents basics and mathematical foundations needed to enable efficient decision making and intelligence in interdependent complex networks  M. Hadi Amini is an Assistant Professor at the School of Computing and Information Sciences at Florida International University (FIU). He is also the founding director of Sustainability, Optimization, and Learning for InterDependent networks laboratory (solid lab). He received his Ph.D. and M.Sc. from Carnegie Mellon University in 2019 and 2015 respectively. He also holds a doctoral degree in Computer Science and Technology. Prior to that, he received M.Sc. from Tarbiat Modares University in 2013, and the B.Sc. from Sharif University of Technology in 2011.

M. Hadi Amini is an Assistant Professor at the School of Computing and Information Sciences at Florida International University (FIU). He is also the founding director of Sustainability, Optimization, and Learning for InterDependent networks laboratory (solid lab). He received his Ph.D. and M.Sc. from Carnegie Mellon University in 2019 and 2015 respectively. He also holds a doctoral degree in Computer Science and Technology. Prior to that, he received M.Sc. from Tarbiat Modares University in 2013, and the B.Sc. from Sharif University of Technology in 2011. His research interests include distributed machine learning and optimization algorithms, distributed intelligence, sensor networks, interdependent networks, and cyberphysical resilience. Application domains include energy systems, healthcare, device-free human sensing, and transportation networks. Prof. Amini is a life member of IEEE-Eta Kappa Nu (IEEE-HKN), the honor society of IEEE. He organized a panel on distributed learning and novel artificial intelligence algorithms, and their application to healthcare, robotics, energy cybersecurity, distributed sensing, and policy issues in 2019 workshop on artificial intelligence at FIU. He also served as President of Carnegie Mellon University Energy Science and Innovation Club; as technical program committee of several IEEE and ACM conferences; and as the lead editor for a book series on ''Sustainable Interdependent Networks'' since 2017. He has published more than 80 refereed journal and conference papers, and book chapters. He has co-authored two books, and edited three books on various aspects of optimization and machine learning for interdependent networks. He is the recipient of the best paper award of 'IEEE Conference on Computational Science & Computational Intelligence' in 2019, best reviewer award from four IEEE Transactions, the best journal paper award in 'Journal of Modern Power Systems and Clean Energy', and the dean's honorary award from the President of Sharif University of Technology.

Autoren/Hrsg.

Amini, M. Hadi

Inhaltsverzeichnis

1;Preface;6
2;Contents;7
3;About the Editor;9
4;1 Panorama of Optimization, Control, and Learning Algorithms for Interdependent SWEET (Societal, Water, Energy, Economic, and Transportation) Networks;11
4.1;1.1 Introduction;11
4.2;1.2 Part I: Theoretical Algorithms for Optimization, Learning, and Data Analytics in Interdependent Complex Networks;14
4.2.1;1.2.1 Chapter 2: Promises of Fully Distributed Optimization for IoT-Based Smart City Infrastructures: Theory and Applications;14
4.2.2;1.2.2 Chapter 3: Evolutionary Computation, Optimization, and Learning Algorithms for Data Science;14
4.2.3;1.2.3 Chapter 4: Applications of Nature-Inspired Algorithms for Dimension Reduction: Enabling Efficient Data Analytics;15
4.2.4;1.2.4 Chapter 5: Feature Selection in High-Dimensional Data;16
4.2.5;1.2.5 Chapter 6: An Introduction to Advanced Machine Learning: Meta-Learning Algorithms, Applications, and Promises;17
4.3;1.3 Part II: Application of Optimization, Learning, and Control in Interdependent Complex Networks;17
4.3.1;1.3.1 Chapter 7: Predictive Analytics in Future Power Systems: A Panorama and State-of-the-Art of Deep Learning Applications;17
4.3.2;1.3.2 Chapter 8: Bilevel Adversary-Operator Cyberattack Framework and Algorithms for Transmission Networks in Smart Grids;18
4.3.3;1.3.3 Chapter 9: Toward Operational Resilience of Smart Energy Networks in Complex Infrastructures;18
4.3.4;1.3.4 Chapter 10: Control of Cooperative Unmanned Aerial Vehicles: Review of Applications, Challenges, and Algorithms;19
4.3.5;1.3.5 Chapter 11: An Optimal Approach for Load-Frequency Control of Islanded Microgrids Based on Non-linear Model;19
4.3.6;1.3.6 Chapter 12: PV Design for Smart Cities and Demand Forecasting Using Truncated Conjugate Gradient Algorithm;20
4.4;References;21
5;Part I Theoretical Algorithms for Optimization, Learning, and Data Analytics in Interdependent Complex Networks;22
5.1;2 Promises of Fully Distributed Optimization for IoT-Based Smart City Infrastructures;23
5.1.1;2.1 Introduction;24
5.1.1.1;2.1.1 Motivation;24
5.1.1.2;2.1.2 Related Works;25
5.1.1.3;2.1.3 Contribution;27
5.1.1.4;2.1.4 Organization;28
5.1.2;2.2 A Novel Holistic Framework for Interdependent Operation of Power Systems and Electrified Transportation networks;28
5.1.3;2.3 Definition of Agents and Their Corresponding Features;30
5.1.3.1;2.3.1 Power System-Specific Agents;31
5.1.3.2;2.3.2 Transportation Network-Specific Agents;32
5.1.3.3;2.3.3 Coupling Agents;32
5.1.4;2.4 General Optimization Problem;35
5.1.4.1;2.4.1 Problem Formulation;35
5.1.4.2;2.4.2 Optimality Conditions;35
5.1.5;2.5 Consensus+Innovations Based Distributed Algorithm;36
5.1.5.1;2.5.1 Distributed Decision Making: General Distributed Update Rule;36
5.1.5.2;2.5.2 Agent-Based Distributed Algorithm;36
5.1.6;2.6 Conclusions;37
5.1.7;Appendix 1: Convergence Analysis;38
5.1.8;References;39
5.2;3 Evolutionary Computation, Optimization, and Learning Algorithms for Data Science;44
5.2.1;3.1 Introduction;45
5.2.1.1;3.1.1 Overview;45
5.2.1.2;3.1.2 Motivation;46
5.2.1.3;3.1.3 Curse of Dimensionality;48
5.2.1.4;3.1.4 Nature-Inspired Computation;48
5.2.1.5;3.1.5 Nature-Inspired Meta-Heuristic Computation;49
5.2.1.6;3.1.6 Nature-Inspired Evolutionary Computation;49
5.2.1.6.1;3.1.6.1 Evolutionary-Based Memetic Algorithms;49
5.2.1.7;3.1.7 Organization;50
5.2.2;3.2 Feature Extraction Techniques;51
5.2.3;3.3 Bio-Inspired Evolutionary Computation;53
5.2.3.1;3.3.1 Overview of Evolutionary Algorithms;53
5.2.3.2;3.3.2 Genetic Algorithm vs. Genetic Programming;56
5.2.3.2.1;3.3.2.1 Genetic Algorithm;56
5.2.3.2.2;3.3.2.2 Genetic Programming;58
5.2.3.3;3.3.3 Artificial Bee Colony Algorithm;60
5.2.3.4;3.3.4 Particle Swarm Optimization Algorithm;61
5.2.3.5;3.3.5 Ant Colony Optimization (ACO);63
5.2.3.6;3.3.6 Grey Wolf Optimizer (GWO);64
5.2.3.7;3.3.7 Coyote Optimization Algorithm (COA);65
5.2.3.8;3.3.8 Other Optimization Algorithms;65
5.2.4;3.4 Conclusion;67
5.2.5;References;68
5.3;4 Applications of Nature-Inspired Algorithms for Dimension Reduction: Enabling Efficient Data Analytics;73
5.3.1;4.1 Introduction;74
5.3.1.1;4.1.1 Overview;74
5.3.1.2;4.1.2 Organization;75
5.3.2;4.2 Application of Evolutionary Algorithms;75
5.3.2.1;4.2.1 Feature Extraction Optimization;78
5.3.2.1.1;4.2.1.1 Feature Selection for Image Classification;78
5.3.2.2;4.2.2 Feature Selection for Network Traffic Classification;83
5.3.2.3;4.2.3 Feature Selection Benchmarks;85
5.3.3;4.3 Discussion;86
5.3.4;4.4 Conclusion;86
5.3.5;References;87
5.4;5 Feature Selection in High-Dimensional Data;91
5.4.1;5.1 Overview;92
5.4.2;5.2 Intrinsic Characteristics of High-Dimensional Data;93
5.4.2.1;5.2.1 Large Number of Features;93
5.4.2.2;5.2.2 Small Number of Samples;94
5.4.2.3;5.2.3 Class Imbalance;94
5.4.2.4;5.2.4 Label Noise;96
5.4.2.5;5.2.5 Intrinsic Characteristics of Microarray Data;97
5.4.3;5.3 Feature Selection;98
5.4.4;5.4 Filter Methods;99
5.4.4.1;5.4.1 Similarity-Based Methods;99
5.4.4.1.1;5.4.1.1 Relief and ReliefF;100
5.4.4.1.2;5.4.1.2 Fisher Score;100
5.4.4.1.3;5.4.1.3 Laplacian Score;101
5.4.4.2;5.4.2 Statistical-Based Methods;101
5.4.4.2.1;5.4.2.1 Correlation-Based Feature Selection (CFS);102
5.4.4.2.2;5.4.2.2 Low Variance;102
5.4.4.2.3;5.4.2.3 T-Score;102
5.4.4.2.4;5.4.2.4 Information Theoretical-Based Methods;103
5.4.4.2.5;5.4.2.5 FCBF;103
5.4.4.2.6;5.4.2.6 Minimum-Redundancy-Maximum-Relevance (mRMR);103
5.4.4.2.7;5.4.2.7 Information Gain;104
5.4.5;5.5 Wrapper Methods;104
5.4.5.1;5.5.1 ABACOH and ACO;105
5.4.5.2;5.5.2 PSO;107
5.4.5.3;5.5.3 IBGSA;108
5.4.6;5.6 Hybrid Method;110
5.4.7;5.7 Embedded Methods;111
5.4.8;5.8 Ensemble Techniques;112
5.4.9;5.9 Practical Evaluation;117
5.4.9.1;5.9.1 Dataset;117
5.4.9.2;5.9.2 Performance Evaluation Criteria;117
5.4.9.3;5.9.3 Data Normalization;119
5.4.9.4;5.9.4 Analysis of Filter Algorithms;119
5.4.9.5;5.9.5 Analysis of Hybrid-Ensemble Methods;122
5.4.9.5.1;5.9.5.1 Hybrid-Ensemble 1;122
5.4.9.5.2;5.9.5.2 Hybrid-Ensemble 2;126
5.4.10;5.10 Summary;128
5.4.11;References;130
5.5;6 An Introduction to Advanced Machine Learning: Meta-Learning Algorithms, Applications, and Promises;135
5.5.1;6.1 Introduction;136
5.5.2;6.2 Machine Learning: Challenges and Drawbacks;137
5.5.3;6.3 Meta-Learning Algorithms;139
5.5.3.1;6.3.1 Model-Based MTL;139
5.5.3.2;6.3.2 Metric-Based Learning;140
5.5.3.3;6.3.3 Gradient Decent-Based Learning;141
5.5.4;6.4 Promises of Meta-Learning;141
5.5.4.1;6.4.1 Few-Shot Learning;144
5.5.4.2;6.4.2 One-Shot Learning;145
5.5.4.3;6.4.3 Zero-Shot Learning;145
5.5.5;6.5 Discussion;146
5.5.6;6.6 Conclusion;147
5.5.7;References;148
6;Part II Application of Optimization, Learning and Control in Interdependent Complex Networks;151
6.1;7 Predictive Analytics in Future Power Systems: A Panorama and State-Of-The-Art of Deep Learning Applications;152
6.1.1;7.1 Introduction;153
6.1.1.1;7.1.1 Motivation;154
6.1.1.2;7.1.2 Classification of Power Systems Forecasting Models;155
6.1.1.2.1;7.1.2.1 Classification Based on the Domain of Application in Power Systems;156
6.1.1.2.2;7.1.2.2 Classification Based on Timescale;159
6.1.1.3;7.1.3 Organization of the Chapter;160
6.1.2;7.2 Forecasting in Power Systems Using Classical Approaches;161
6.1.2.1;7.2.1 Time Series Data;161
6.1.2.2;7.2.2 Statistical Forecasting Approaches;163
6.1.2.2.1;7.2.2.1 Naïve Model Approach;163
6.1.2.2.2;7.2.2.2 Exponential Smoothing;164
6.1.2.2.3;7.2.2.3 Autoregressive Moving Average (ARMA) Models;164
6.1.2.2.4;7.2.2.4 Autoregressive Moving Integrated Average (ARIMA) Models;166
6.1.2.3;7.2.3 Machine Learning Forecasting Approaches;166
6.1.2.3.1;7.2.3.1 Support Vector Regression;167
6.1.2.3.2;7.2.3.2 Gaussian Process Regression;168
6.1.2.4;7.2.4 Shortcomings of Classical Approaches;169
6.1.3;7.3 Forecasting in Power Systems Using Deep Learning;169
6.1.3.1;7.3.1 Deep Learning;169
6.1.3.1.1;7.3.1.1 Recurrent Neural Network;170
6.1.3.1.2;7.3.1.2 Long Short-Term Memory Network;171
6.1.3.1.3;7.3.1.3 Other Relevant Models;173
6.1.3.2;7.3.2 Deep Learning Applications;173
6.1.3.2.1;7.3.2.1 Load Forecasting;173
6.1.3.2.2;7.3.2.2 Generation Forecasting;174
6.1.3.2.3;7.3.2.3 Electricity Price Forecasting and Electric Vehicle Charging;174
6.1.3.3;7.3.3 Deep Learning Strengths and Shortcomings;174
6.1.3.3.1;7.3.3.1 Strengths;175
6.1.3.3.2;7.3.3.2 Shortcomings;175
6.1.4;7.4 Case Study: Multi-Timescale Solar Irradiance Forecasting Using Deep Learning;175
6.1.4.1;7.4.1 Data;176
6.1.4.1.1;7.4.1.1 Global Horizontal Irradiance;177
6.1.4.1.2;7.4.1.2 Exogenous Input Variables;177
6.1.4.1.3;7.4.1.3 Data Preprocessing and Postprocessing;178
6.1.4.2;7.4.2 Model Architecture and Training;178
6.1.4.3;7.4.3 Results;179
6.1.4.3.1;7.4.3.1 Single Time Horizon Model;179
6.1.4.3.2;7.4.3.2 Multi-Time-Horizon Model;179
6.1.5;7.5 Summary and Future Work;182
6.1.5.1;7.5.1 Deterministic Versus Probabilistic Forecasting;182
6.1.5.2;7.5.2 Other Potential Applications;183
6.1.6;References;183
6.2;8 Bi-level Adversary-Operator Cyberattack Framework and Algorithms for Transmission Networks in Smart Grids;188
6.2.1;8.1 Introduction;189
6.2.1.1;8.1.1 Overview;189
6.2.2;8.2 DC Power Flow Model;191
6.2.3;8.3 False Data Injection Attacks Based on DC State Estimation;193
6.2.4;8.4 Attacker's Problem: Finding the Optimal Set of Target Transmission Lines using MILP;195
6.2.4.1;8.4.1 Identifying Feasible Attacks;198
6.2.5;8.5 Operator's Problem: Bad Data Detection to Prevent Outages Caused by Cyberattack;198
6.2.6;8.6 Case Studies;201
6.2.6.1;8.6.1 Feasibility of Line Overflow;202
6.2.6.2;8.6.2 Targeted Attack on Line 15;203
6.2.6.3;8.6.3 Severe Attack on an Area;205
6.2.7;8.7 Conclusion;205
6.2.8;References;206
6.3;9 Toward Operational Resilience of Smart Energy Networks in Complex Infrastructures;208
6.3.1;9.1 Introduction;209
6.3.1.1;9.1.1 Overview;209
6.3.2;9.2 Resilience Enhancement Scheme;210
6.3.3;9.3 Real-Time Decision Making Process;212
6.3.4;9.4 Optimization Model;213
6.3.4.1;9.4.1 Pre-event Preparation Strategy;213
6.3.4.2;9.4.2 Mid-Event Monitoring;218
6.3.4.3;9.4.3 Post-event Restoration Problem;219
6.3.5;9.5 Simulation Results;221
6.3.6;9.6 Conclusion;231
6.3.7;References;232
6.4;10 Control of Cooperative Unmanned Aerial Vehicles: Review of Applications, Challenges, and Algorithms;234
6.4.1;Abbreviations;234
6.4.2;10.1 Introduction;235
6.4.3;10.2 Applications and Literature Review;236
6.4.3.1;10.2.1 Search and Rescue;237
6.4.3.2;10.2.2 Surveillance;238
6.4.3.3;10.2.3 Localization and Mapping;240
6.4.3.4;10.2.4 Military Applications;241
6.4.3.4.1;10.2.4.1 Reconnaissance Strategy;242
6.4.3.4.2;10.2.4.2 Penetrating Strategy;242
6.4.4;10.3 Challenges;243
6.4.5;10.4 Algorithms;245
6.4.5.1;10.4.1 Consensus Strategies;245
6.4.5.1.1;10.4.1.1 Graph Theory Basics in Communication Systems;246
6.4.5.1.2;10.4.1.2 Consensus Control Theory;247
6.4.5.1.3;10.4.1.3 Consensus Recent Researches;248
6.4.5.2;10.4.2 Flocking Based Strategies;250
6.4.5.2.1;10.4.2.1 Flocking Control Theory;250
6.4.5.2.2;10.4.2.2 Flocking Recent Researches;251
6.4.5.3;10.4.3 Guidance Law Based Cooperative Control;253
6.4.5.3.1;10.4.3.1 Guidance Law Based Recent Researches;254
6.4.6;10.5 Summary and Conclusion;255
6.4.7;Bibliography;255
6.5;11 An Optimal Approach for Load-Frequency Control of Islanded Microgrids Based on Nonlinear Model;261
6.5.1;Nomenclature;261
6.5.2;11.1 Introduction;262
6.5.3;11.2 Dynamic Model of Microgrid;265
6.5.4;11.3 The Proposed Intelligent Control Method;267
6.5.5;11.4 Simulation and Results;271
6.5.6;11.5 Conclusion;276
6.5.7;References;277
6.6;12 Photovoltaic Design for Smart Cities and Demand Forecasting Using a Truncated Conjugate Gradient Algorithm;280
6.6.1;Abbreviations;281
6.6.2;12.1 Introduction;282
6.6.3;12.2 Objectives and Targets;283
6.6.4;12.3 Literature Review;283
6.6.5;12.4 Rule-Based Neural Network Structure;289
6.6.6;12.5 The Proposed Model;290
6.6.7;12.6 Results and Discussion;291
6.6.8;12.7 Conclusion;296
6.6.9;References;297
7;Index;299