Big Data Application in Power Systems

 
 
Elsevier Science (Verlag)
  • 1. Auflage
  • |
  • erschienen am 27. November 2017
  • |
  • 480 Seiten
 
E-Book | ePUB mit Adobe DRM | Systemvoraussetzungen
E-Book | PDF mit Adobe DRM | Systemvoraussetzungen
978-0-12-811969-3 (ISBN)
 

Big Data Application in Power Systems brings together experts from academia, industry and regulatory agencies who share their understanding and discuss the big data analytics applications for power systems diagnostics, operation and control. Recent developments in monitoring systems and sensor networks dramatically increase the variety, volume and velocity of measurement data in electricity transmission and distribution level. The book focuses on rapidly modernizing monitoring systems, measurement data availability, big data handling and machine learning approaches to process high dimensional, heterogeneous and spatiotemporal data. The book chapters discuss challenges, opportunities, success stories and pathways for utilizing big data value in smart grids.

  • Provides expert analysis of the latest developments by global authorities
  • Contains detailed references for further reading and extended research
  • Provides additional cross-disciplinary lessons learned from broad disciplines such as statistics, computer science and bioinformatics
  • Focuses on rapidly modernizing monitoring systems, measurement data availability, big data handling and machine learning approaches to process high dimensional, heterogeneous and spatiotemporal data
  • Englisch
  • Saint Louis
  • |
  • USA
  • 42,21 MB
978-0-12-811969-3 (9780128119693)
0128119691 (0128119691)
weitere Ausgaben werden ermittelt
  • Front Cover
  • Big Data Application in Power Systems
  • Copyright
  • Contents
  • Contributors
  • About the Editors
  • Preface: Objective and Overview of the Book
  • Section One: Harness the Big Data From Power Systems
  • Section Two: Harness the Power of Big Data
  • Section Three: Put the Power of Big Data Into Power Systems
  • Acknowledgments
  • Section 1: Harness the Big Data From Power Systems
  • Chapter 1: A Holistic Approach to Becoming a Data-Driven Utility
  • 1. Introduction
  • 2. Aligning Internal and External Stakeholders
  • 3. Taking a Holistic Approach
  • 4. ``Strong´´ First, Then ``Smart´´
  • 5. Increasing Visibility With IEDs
  • 6. Network Response Requirements
  • 7. Integration Before Automation
  • 8. Functional Data Paths: Keep it Simple
  • 9. From Sensor to End User: The Process
  • 10. Consumers/Customers: Another Source of Data
  • 11. Extracting Value From Data, and Presenting It
  • 12. The Transformation
  • 13. Three Case Studies
  • 13.1. Frankfort, Kentucky, and Greenfield SCADA, SA
  • 13.2. Ketchikan, Alaska, Deals With Unsupported, Legacy RTUs
  • 13.3. North Carolina Agency Pursues New SCADA, Boosts Revenue
  • 14. Conclusion
  • 14.1. Looking Ahead
  • References
  • Chapter 2: Emerging Security and Data Privacy Challenges for Utilities: Case Studies and Solutions
  • 1. Introduction
  • 2. Case Studies: The State and Scope of the Threat
  • 2.1. Coordinated Cyberattack Causes Outage in the Ukraine
  • 2.2. Severe Financial Impacts at Saudi Aramco
  • 2.3. The Misunderstood Near Miss: Burlington Electric and Grizzly Steppe
  • 2.4. Impact on Practices in the Utility Industry
  • 3. The Digitized Network Increases Vulnerability
  • 3.1. Attack Scenarios
  • 4. The Role of Data Analytics
  • 4.1. The Role of Privacy
  • 5. Conclusion
  • References
  • Chapter 3: The Role of Big Data and Analytics in Utility Innovation
  • 1. Introduction of Big Data and Analytics as an Accelerator of Innovation
  • 2. Approaches to Data Driven Innovation
  • 3. Integration of Renewable Energy
  • 4. Grid Operations
  • 5. Cognitive Computing on Big Data
  • 6. Weather, the Biggest Data Topic for Power Systems
  • References
  • Further Reading
  • Chapter 4: Frameworks for Big Data Integration, Warehousing, and Analytics
  • 1. Introduction
  • 2. Frameworks for Big Data Platform
  • 2.1. Architecture
  • 2.2. Storage
  • 2.3. Security
  • 3. Big Data With HPC
  • 3.1. System Architecture (Fig. 3)
  • 3.2. Service Type
  • 3.3. Internet of Things
  • 3.4. HPC Platform for Smart Grid
  • 4. Big Data With Complex Event Processing
  • 5. Application of Big Data Techniques for Power Systems
  • 6. Conclusion
  • Acknowledgment
  • References
  • Further Reading
  • Section 2: Harness the Power of Big data
  • Chapter 5: Moving Toward Agile Machine Learning for Data Analytics in Power Systems
  • 1. Introduction
  • 2. Classic Supervised and Unsupervised Learning
  • 2.1. Supervised Learning Overview
  • 2.1.1. Examples of Supervised Learning as a Regularization Empirical Risk Minimization
  • Linear/Ridge Regression
  • Logistic Regression
  • Support Vector Machine
  • Nonparametric Regression
  • Decision Tree
  • 2.1.2. Bayesian Perspectives
  • Linear/Ridge Regression Revisited
  • Example: HMM With Autoregressive Emissions
  • 2.2. Unsupervised Learning Overview
  • Principle Component Analysis
  • k-Means Clustering
  • 3. Model Selection (Hyperparameter Selection)
  • 3.1. Theoretical Intuition
  • Generalization Bound
  • Bias-Variance Trade-Off
  • 3.2. Practical Model Selection Techniques
  • Cross-Validation
  • Being a Bayesian
  • Regularization Path Algorithms
  • Bayesian Optimization
  • 4. Feature Selection
  • 4.1. Overview
  • Filter Method
  • Wrapper Method
  • Embedded Method
  • 4.2. An Practical Example of FS Using Information Theory Criterion
  • Single Stream Features Extraction
  • Interstream Features
  • 5. Other Promising Research Directions
  • Leverage Unlabeled Data With Semisupervised Learning
  • Knowledge Transfer With Multitask Learning
  • Information Fusion With Multiview Learning
  • Other Promising Directions
  • References
  • Chapter 6: Unsupervised Learning Methods for Power System Data Analysis
  • 1. Introduction
  • 2. Smart Meter Data Preparation
  • 2.1. Statistical Analysis
  • 3. Clustering Algorithm
  • 4. Clustering Approach and Visualization
  • 4.1. Features Extraction
  • 4.2. Typical Daily Patterns
  • 4.3. Visualization Tool
  • 5. Conclusions
  • References
  • Chapter 7: Deep Learning for Power System Data Analysis
  • 1. Introduction
  • 1.1. From Neural Network Towards Deep Learning
  • 1.2. Deep Learning Methods
  • 2. Supervised Energy Prediction Using Deep Learning
  • 2.1. Conditional Restricted Boltzmann Machine
  • 2.1.1. Inference in CRBM
  • 2.1.2. Learning for CRBM Using Contrastive Divergence
  • 2.2. Factored Conditional Restricted Boltzmann Machine
  • 2.2.1. Total Energy for FCRBM
  • 2.2.2. Inference in FCRBM
  • 2.2.3. Learning and Update Rules for FCRBMs
  • 2.3. Experiments and Results
  • 3. Unsupervised Energy Prediction Using Deep Learning
  • 3.1. Problem Formulation
  • 3.2. Reinforcement Learning
  • 3.2.1. Markov Decision Process
  • 3.2.2. Q-Learning
  • 3.2.3. SARSA
  • 3.3. States Estimation via DBNs
  • 3.3.1. Deep Belief Networks
  • 3.4. Numerical Results
  • 3.4.1. Commercial to Residential Transfer
  • 3.4.2. Residential to Residential Transfer
  • 4. Conclusions
  • References
  • Further Reading
  • Chapter 8: Compressive Sensing for Power System Data Analysis
  • 1. Introduction
  • 2. Mathematical Modeling of a Compressive Sensing-Sparse Recovery Problem
  • 2.1. Compressive Sensing
  • 2.2. Sparse Recovery Problem
  • 3. Applications of CS-SR Techniques in Smart Grids
  • 4. Sparse Recovery-Based DSSE in Smart Grid
  • 5. Sparse Recovery-Based Fault Location in Smart Distribution and Transmission Networks
  • 6. Compressive Sensing-Based PD Pattern Recognition
  • 7. Conclusions and Future of the CS-SR in Smart Grids
  • References
  • Chapter 9: Time-Series Classification Methods: Review and Applications to Power Systems Data
  • 1. Introduction
  • 1.1. Contribution
  • 1.2. Notation
  • 2. The Classification Problem
  • 2.1. Classification Methods Taxonomy
  • 2.2. Computational Issues
  • 3. Data Sources
  • 3.1. Dimensionality Reduction
  • 3.1.1. DR Techniques Review
  • 3.2. Numerosity Reduction
  • 3.2.1. NR Techniques Review
  • 4. Classification Methods
  • 4.1. Feature-Based Methods
  • 4.1.1. Metrics-Based Approaches
  • 4.1.2. Occurrence Counting Approaches
  • 4.1.3. Dynamics-Based Approaches
  • 4.2. Distance-Based Methods
  • 4.2.1. Purely Distance-Based Methods
  • 4.2.2. Reduction Distance-Based Methods
  • 4.2.3. Dictionary Learning
  • 4.2.4. Parametric Distance-Based Methods
  • 4.3. Methods Comparison
  • 5. Applications
  • 6. Concluding Remarks
  • References
  • Section 3: Put the Power of Big Data into Power Systems
  • Chapter 10: Future Trends for Big Data Application in Power Systems
  • 1. Introduction
  • 2. Transmission System
  • 2.1. Dynamic Behavior Analysis
  • 2.2. Steady-State Analysis
  • 2.3. TSO-DSO Cooperation
  • 3. Distribution System
  • 3.1. Monitoring and Situational Awareness
  • 3.2. Predictive Control and Management
  • 4. Asset Management
  • 5. Electricity Markets
  • 6. Demand-Side Flexibility
  • 7. Conclusions and Future Challenges
  • Acknowledgments
  • References
  • Chapter 11: On Data-Driven Approaches for Demand Response
  • 1. Introduction
  • 2. Sources of Big Data in DR
  • 3. Big Data Applications in DR
  • 3.1. Assessment of Energy Consumption Behavior
  • 3.2. Electric Load Classification
  • 3.3. Demand and Renewable Energy Generation Forecasting
  • 3.4. Dynamic Pricing
  • 4. Real-World Applications and Research on Big Data-Driven Demand Response
  • 5. Summary and Future Prospects
  • Acknowledgment
  • References
  • Chapter 12: Topology Learning in Radial Distribution Grids
  • 1. Introduction
  • 1.1. Prior Work
  • 1.2. Technical Contribution
  • 2. Distribution Grid: Structure and Power Flows
  • Radial Structure
  • PF Model
  • 3. Properties of Voltage Magnitudes in Radial Grids
  • 4. Topology Learning With Full Observation
  • Algorithm Complexity
  • Extension to Multiple Trees
  • 5. Topology Learning With Missing Data
  • 5.1. Missing Nodes Separated by Three or More Hops
  • Complexity
  • Note
  • 5.2. All Nonleaf Nodes Are Missing
  • Computational Complexity
  • 6. Experiments
  • 7. Conclusions
  • References
  • Chapter 13: Grid Topology Identification via Distributed Statistical Hypothesis Testing
  • 1. Introduction
  • 1.1. Related Works
  • 2. Power Distribution Grid Model
  • 3. Voltage Correlation Analysis
  • 4. A Distributed Topology Test
  • 5. Numerical Experiments
  • 6. Conclusions
  • References
  • Chapter 14: Supervised Learning-Based Fault Location in Power Grids
  • 1. Fundamentals of SVM
  • 2. Power System Applications of SVM
  • 3. Fault Classification and Location for Three-Terminal Transmission Lines
  • 3.1. SVM-Based Fault Classification
  • 3.2. Single-Ended Traveling Wave-Based Fault Location
  • 3.3. Results and Discussion
  • 4. Fault Location for Hybrid HVAC Transmission Lines
  • 4.1. Single-Ended Traveling Wave-Based Fault Location
  • 4.2. Results and Discussion
  • 5. Summary
  • References
  • Chapter 15: Data-Driven Voltage Unbalance Analysis in Power Distribution Networks
  • Chapter Points
  • 1. Introduction
  • 2. Problem Statement
  • 2.1. Unbalance in Low-Voltage Distribution Networks
  • 2.2. Utilized Voltage Band
  • 3. Data Acquisition and Storage
  • 3.1. Smart Meter Data Acquisition System
  • 3.2. Distributed Database Storage
  • 4. Distributed Data Processing
  • 4.1. Statistical Method
  • 4.2. Distributed Queries and Functions
  • 5. Data Discovery
  • 5.1. Distribution of Voltages
  • 5.2. Relation Between Meters With High Unbalance Events
  • 5.3. Timely Distribution of High Unbalance Events
  • 5.4. Relation Between Different Network States
  • 5.5. Maximum and Minimum Voltage: Voltage Spread
  • 6. Performance Evaluations
  • 6.1. Comparison Requirements
  • 6.1.1. Code
  • 6.1.2. Data
  • 6.1.3. Database
  • 6.1.4. System
  • 6.2. Evaluation Setup
  • 6.3. MapReduce Function CalcEventsLongFormat
  • 6.4. MapReduce Function MeterMinMax
  • 7. Conclusion
  • References
  • Chapter 16: Predictive Analytics for Comprehensive Energy Systems State Estimation
  • 1. Introduction
  • 2. Resource Forecasting
  • 2.1. Renewable Forecasting
  • 2.2. Wind Forecasting
  • 2.2.1. Wind Forecasting Overview
  • 2.2.2. Big Data-Driven Wind Forecasting
  • Hours- to Day-Ahead NWP-Based Wind Forecasting
  • Minutes- to 2-Hour-Ahead Machine-Learning-Based Wind Forecasting
  • 2.2.3. Wind Forecasting Datasets
  • 2.3. Solar Forecasting
  • 2.3.1. Solar Forecasting Overview
  • 2.3.2. Big Data-Driven Solar Forecasting
  • Hours- to Day-Ahead NWP-Based Solar Forecasting
  • Minutes- to 2-Hour-Ahead Sky Imaging-Based Solar Forecasting
  • 2.4. Renewable Forecasting Performance Evaluation Metrics
  • 3. User Energy System State Estimation
  • 3.1. Overview
  • 3.2. Load Forecasting
  • 3.2.1. Conventional Methods
  • 3.2.2. Artificial Intelligence-Based Methods
  • 3.2.3. Gaussian Process-Based Method
  • 3.3. User Energy System State Estimation: Demand Response
  • 4. Power System State Estimation
  • 4.1. Overview
  • 4.2. Conventional Nonlinear State Estimation
  • 4.3. PMU Data-Based Linear State Estimation and Dynamic State Estimation
  • 4.4. Predictive State Estimation
  • 4.4.1. Forecasting-Aided State Estimation
  • 4.4.2. Predictive State Estimation
  • 4.5. Distribution System State Estimation
  • 5. Conclusions
  • References
  • Chapter 17: Data Analytics for Energy Disaggregation: Methods and Applications
  • 1. Introduction
  • 2. Appliance Categories
  • 2.1. Device Classifications Based on the Operational States
  • 2.1.1. On/Off
  • 2.1.2. Finite State Machines
  • 2.1.3. Continuous Variable Device
  • 2.1.4. Permanent Consumer
  • 2.2. Device Classifications Based on the Corresponding Load Characteristics
  • 3. NILM Methodology
  • 3.1. Device Signatures
  • 3.1.1. Macroscopic Signatures
  • 3.1.2. Microscopic Signatures
  • 3.1.3. Nontraditional Signatures
  • 3.2. Disaggregation Algorithms
  • 3.2.1. Supervised Algorithms
  • Pattern Recognition (Event-Based) Methods
  • Optimization (Eventless) Methods
  • 3.2.2. Unsupervised Algorithms
  • 3.3. Accuracy Metrics
  • 4. Available Open Datasets
  • 5. Available Energy Disaggregation Open-Source Tools
  • 6. Main Use Cases of Energy Disaggregation
  • 7. Conclusion
  • References
  • Chapter 18: Energy Disaggregation and the Utility-Privacy Tradeoff
  • 1. Introduction
  • 2. Background
  • 2.1. Energy Disaggregation Background
  • 2.2. Utility-Privacy Tradeoff Background
  • 3. Fundamental Limits of NILM
  • 3.1. Problem Statement
  • 3.2. Model of Energy Disaggregation Algorithms
  • 3.2.1. Aggregate Device Model
  • 3.2.2. NILM Algorithms
  • 3.3. Fundamental Limits of Energy Disaggregation
  • 3.3.1. Distinguishing Two Scenarios
  • 3.3.2. Distinguishing a Finite Number of Scenarios
  • 3.3.3. Distinguishing Two Collections of Scenarios
  • 3.4. Gaussian Case
  • 3.4.1. Two Scenarios
  • 3.4.2. K Scenarios
  • 3.4.3. Linear Systems
  • 4. Utility-Privacy Tradeoff
  • 4.1. Framework
  • 4.1.1. The Utility of Data
  • 4.1.2. The Privacy of Data
  • 4.1.3. User and Data Mechanism Model
  • 4.1.4. Adversary Model
  • 4.1.5. Inferential Privacy Metric
  • 4.2. Example: Direct Load Control
  • 4.2.1. DLC Model
  • 4.2.2. Thermostatically Controlled Load Model
  • 4.2.3. Direct Load Control Objective
  • 4.2.4. Direct Load Control Capabilities
  • 4.2.5. Direct Load Controller
  • 4.2.6. DLC Model Simulations
  • 4.2.7. DLC Privacy Analysis
  • 4.3. Closing Remarks on the Utility-Privacy Tradeoff
  • 5. Conclusions
  • References
  • Index
  • Back Cover

Dateiformat: EPUB
Kopierschutz: Adobe-DRM (Digital Rights Management)

Systemvoraussetzungen:

Computer (Windows; MacOS X; Linux): Installieren Sie bereits vor dem Download die kostenlose Software Adobe Digital Editions (siehe E-Book Hilfe).

Tablet/Smartphone (Android; iOS): Installieren Sie bereits vor dem Download die kostenlose App Adobe Digital Editions (siehe E-Book Hilfe).

E-Book-Reader: Bookeen, Kobo, Pocketbook, Sony, Tolino u.v.a.m. (nicht Kindle)

Das Dateiformat EPUB ist sehr gut für Romane und Sachbücher geeignet - also für "fließenden" Text ohne komplexes Layout. Bei E-Readern oder Smartphones passt sich der Zeilen- und Seitenumbruch automatisch den kleinen Displays an. Mit Adobe-DRM wird hier ein "harter" Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.

Weitere Informationen finden Sie in unserer E-Book Hilfe.


Dateiformat: PDF
Kopierschutz: Adobe-DRM (Digital Rights Management)

Systemvoraussetzungen:

Computer (Windows; MacOS X; Linux): Installieren Sie bereits vor dem Download die kostenlose Software Adobe Digital Editions (siehe E-Book Hilfe).

Tablet/Smartphone (Android; iOS): Installieren Sie bereits vor dem Download die kostenlose App Adobe Digital Editions (siehe E-Book Hilfe).

E-Book-Reader: Bookeen, Kobo, Pocketbook, Sony, Tolino u.v.a.m. (nicht Kindle)

Das Dateiformat PDF zeigt auf jeder Hardware eine Buchseite stets identisch an. Daher ist eine PDF auch für ein komplexes Layout geeignet, wie es bei Lehr- und Fachbüchern verwendet wird (Bilder, Tabellen, Spalten, Fußnoten). Bei kleinen Displays von E-Readern oder Smartphones sind PDF leider eher nervig, weil zu viel Scrollen notwendig ist. Mit Adobe-DRM wird hier ein "harter" Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.

Weitere Informationen finden Sie in unserer E-Book Hilfe.


Download (sofort verfügbar)

115,37 €
inkl. 19% MwSt.
Download / Einzel-Lizenz
ePUB mit Adobe DRM
siehe Systemvoraussetzungen
PDF mit Adobe DRM
siehe Systemvoraussetzungen
Hinweis: Die Auswahl des von Ihnen gewünschten Dateiformats und des Kopierschutzes erfolgt erst im System des E-Book Anbieters
E-Book bestellen

Unsere Web-Seiten verwenden Cookies. Mit der Nutzung dieser Web-Seiten erklären Sie sich damit einverstanden. Mehr Informationen finden Sie in unserem Datenschutzhinweis. Ok