Atnaujinkite slapukų nuostatas

El. knyga: Intelligent Data Mining and Analysis in Power and Energy Systems - Models and Applications for Smarter Efficient Power Systems [Wiley Online]

Edited by (Polytechnic of Porto - School of Engineering, Portugal), Edited by (Clemson University, SC, USA), Edited by (University of Trįs-os-Montes e Alto Douro, Portugal), Edited by (University of Tasmania, Australia)
Kitos knygos pagal šią temą:
  • Wiley Online
  • Kaina: 158,59 €*
  • * this price gives unlimited concurrent access for unlimited time
Intelligent Data Mining and Analysis in Power and Energy Systems - Models and Applications for Smarter Efficient Power SystemsDidesnis paveikslėlis
Kitos knygos pagal šią temą:
Wiley Online E-booksMore info about Wiley Online
Partnerių interneto svetainė: https://onlinelibrary.wiley.com/doi/book/10.1002/9781119834052

A hands-on and current review of data mining and analysis and their applications to power and energy systems

In Intelligent Data Mining and Analysis in Power and Energy Systems: Models and Applications for Smarter Efficient Power Systems, the editors assemble a team of distinguished engineers to deliver a practical and incisive review of cutting-edge information on data mining and intelligent data analysis models as they relate to power and energy systems. You’ll find accessible descriptions of state-of-the-art advances in intelligent data mining and analysis and see how they drive innovation and evolution in the development of new technologies.

The book combines perspectives from authors distributed around the world with expertise gained in academia and industry. It facilitates review work and identification of critical points in the research and offers insightful commentary on likely future developments in the field. It also provides:

  • A thorough introduction to data mining and analysis, including the foundations of data preparation and a review of various analysis models and methods
  • In-depth explorations of clustering, classification, and forecasting
  • Intensive discussions of machine learning applications in power and energy systems
  • Insightful treatments of related applications, including vibration elimination in transmission lines and the design of power distribution networks

Perfect for power and energy systems designers, planners, operators, and consultants, Intelligent Data Mining and Analysis in Power and Energy Systems will also earn a place in the libraries of software developers, researchers, and students with an interest in data mining and analysis problems.

About the Editors xix
List of Contributors
xxi
Foreword xxvii
Introduction 1(4)
References
3(2)
Part I Data Mining and Analysis Fundamentals
5(64)
1 Foundations
7(18)
Ansel Y. Rodriguez-Gonzalez
Angel Diaz-Pacheco
Ramon Aranda
Miguel A. Alvarez-Carmona
Acronyms
7(1)
1.1 Data Mining: Why and What?
7(1)
1.2 Data Mining into KDD
8(1)
1.3 The Data Mining Process
9(3)
1.3.1 Data Cleaning
10(1)
1.3.2 Data Integration
10(1)
1.3.3 Data Reduction
11(1)
1.3.4 Data Transformation
12(1)
1.4 Data Mining Task and Techniques
12(6)
1.4.1 Techniques
14(1)
1.4.1.1 Techniques in the "Description" Branch
14(1)
1.4.1.2 Regression Techniques
14(1)
1.4.1.3 Classification Techniques
15(2)
1.4.2 Applications
17(1)
1.5 Data Mining Issues and Considerations
18(1)
1.5.1 Scalability of Algorithms
18(1)
1.5.2 High Dimensionality
18(1)
1.5.3 Improving Interpretability
18(1)
1.5.4 Handling Uncertainty
19(1)
1.5.5 Privacy and Security Concerns
19(1)
1.6 Summary
19(1)
References
20(5)
2 Data Mining and Analysis in Power and Energy Systems: An Introduction to Algorithms and Applications
25(1)
Fernando Lezama
Acronyms
25(1)
2.1 Introduction
25(1)
2.2 Data Mining Technologies
26(2)
2.2.1 Supervised Methods
26(1)
2.2.1.1 Regression-Based Methods
27(1)
2.2.1.2 Classification-Based Methods
27(1)
2.2.2 Unsupervised Methods
27(1)
2.2.2.1 Association Rule Mining
28(1)
2.2.2.2 Clustering-Based Methods
28(1)
2.3 Data Mining Applications in Power Systems
28(7)
2.3.1 Profiling
29(2)
2.3.2 Forecasting
31(2)
2.3.3 Fault Detection and Diagnosis
33(1)
2.3.4 Other Applications
34(1)
2.4 Discussion and Final Remarks
35(10)
References
37(8)
3 Deep Learning in Intelligent Power and Energy Systems
45(24)
Bruno Mota
Tiago Pinto
Zita Vale
Carlos Ramos
Acronyms
45(1)
3.1 Introduction
46(3)
3.2 Deep Learning
49(9)
3.2.1 Regression Problems
49(1)
3.2.1.1 Photovoltaic Energy Forecast
49(1)
3.2.1.2 Wind Power Forecast
50(1)
3.2.1.3 Building Energy Consumption Prediction
50(1)
3.2.1.4 Electricity Price Forecast
51(1)
3.2.1.5 Other Regression Works
52(1)
3.2.2 Classification Problems
52(1)
3.2.2.1 Power Quality Disturbances Detection/Classification
53(1)
3.2.2.2 Fault Detection/Classification
54(1)
3.2.2.3 Feature Engineering
55(1)
3.2.2.4 Other Classification Works
55(1)
3.2.3 Decision-Making Problems
56(1)
3.2.3.1 Energy Management
56(1)
3.2.3.2 Demand Response
57(1)
3.2.3.3 Electricity Market
57(1)
3.2.3.4 Other Decision-Making Works
58(1)
3.3 Accomplishments, Limitations, and Challenges
58(2)
3.4 Conclusions
60(9)
References
60(9)
Part II Clustering
69(80)
4 Data Mining Techniques Applied to Power Systems
71(34)
Sergio Ramos
Joao Soares
Zahra Forouzandeh
Zita Vale
Acronyms
71(1)
4.1 Introduction
71(4)
4.1.1 Data Selection
72(1)
4.1.2 Data Pre-processing
73(1)
4.1.3 Data Mining
73(1)
4.1.4 Analysis and Interpretation
74(1)
4.2 Data Mining Techniques
75(7)
4.2.1 Clustering Algorithms
76(3)
4.2.2 Clustering Validity Indices
79(1)
4.2.3 Classification Algorithms
80(2)
4.3 Data Mining Techniques Applied to Power Systems
82(8)
4.3.1 Electrical Consumers Characterization
83(1)
4.3.1.1 Typical Load Profile
83(3)
4.3.2 Electrical Consumers Characterization - Classification
86(3)
4.3.3 Conclusions
89(1)
4.4 Electrical Tariffs Design Based on Data Mining Techniques
90(3)
4.4.1 Electrical Tariffs Design
90(3)
4.4.2 Conclusions
93(1)
4.5 Data Mining Contributions to Characterize Zonal Prices
93(5)
4.5.1 Zonal Prices Characterization
93(4)
4.5.2 Conclusions
97(1)
4.6 Data Mining-Based Methodology for Wind Forecasting
98(3)
4.6.1 Wind Forecasting
98(2)
4.6.2 Conclusions
100(1)
4.7 Final Remarks
101(4)
References
101(4)
5 Synchrophasor Data Analytics for Anomaly and Event Detection, Classification, and Localization
105(24)
Sajan K. Sadanandan
Arman Ahmed
Shikhar Pandey
Anurag K. Srivastava
5.1 Introduction
105(1)
5.2 Synchrophasor Data Quality Issues and Challenges
106(2)
5.2.1 PMU Data Flow: Data Quality Issues
107(1)
5.2.2 PMU Data Anomalies
108(1)
5.3 ML-Based Anomaly Detection, Classification, and Localization (ADCL) Over Data Drifting Multivariate Synchrophasor Data Streams
108(6)
5.3.1 Data Drift in Synchrophasor Measurements
109(1)
5.3.2 PMUNET Framework
110(1)
5.3.2.1 Data Pre-Processing (DPP) Module
110(1)
5.3.2.2 Data-Drift (DD) Module
110(2)
5.3.2.3 Save-Load (SL) Module
112(1)
5.3.3 Anomaly Detector (AD) Module
112(1)
5.3.3.1 Anomaly Classification
113(1)
5.3.3.2 Anomaly Localization
113(1)
5.3.4 Distributed Deep Autoencoder Learning
113(1)
5.4 Synchrophasor Data Anomaly and Event Detection, Localization, and Classification (SyncAED)
114(5)
5.4.1 Synchrophasor Data Anomaly Detection (SyncAD)
114(1)
5.4.1.1 Base Detectors
115(1)
5.4.1.2 Ensemble Method
115(1)
5.4.1.3 Prony-Based Transient Window Estimation
115(1)
5.4.2 Event Detection, Classification, and Localization
116(1)
5.4.2.1 Event Detection
117(1)
5.4.2.2 Event Classification
117(1)
5.4.2.3 Event Localization
117(2)
5.5 Test-Bed and Test Cases
119(1)
5.5.1 Cyber-Power Test-Bed Architecture
119(1)
5.5.1.1 Test Case
119(1)
5.6 Results and Discussion
120(5)
5.6.1 Simulation Results for PMUNET
120(1)
5.6.1.1 Performance Evaluation Metrics
120(1)
5.6.1.2 Experimental Analysis
121(1)
5.6.2 Simulation Results for SyncAED
122(1)
5.6.2.1 Anomaly Detection
122(1)
5.6.2.2 Event Detection and Classification Using Clustering and Decision Tree
122(3)
5.7 Summary
125(4)
Acknowledgments
125(1)
References
125(4)
6 Clustering Methods for the Profiling of Electricity Consumers Owning Energy Storage System
129(20)
Catia Silva
Pedro Faria
Juan M. Corchado
Zita Vale
Acronyms
129(1)
6.1 Introduction
129(2)
6.2 Methodology Definition
131(4)
6.3 Clustering of Consumers with ESS
135(10)
6.3.1 Optimal Number of Clusters
135(1)
6.3.1.1 Average Silhouette Method
136(1)
6.3.1.2 Elbow Method
136(1)
6.3.1.3 Gap Statistic Method
137(1)
6.3.2 Clustering Methods
137(1)
6.3.2.1 Partitional Clustering
138(3)
6.3.2.2 Fuzzy Clustering
141(1)
6.3.2.3 Hierarchical Clustering
142(3)
6.4 Conclusion
145(4)
Acknowledgments
146(1)
References
146(3)
Part III Classification
149(52)
7 A Novel Framework for NTL Detection in Electric Distribution Systems
151(20)
Chia-Chi Chu
Nelson Fabian Avila
Gerardo Figueroa
Wen-Kai Lu
Acronyms
151(1)
7.1 Introduction
151(3)
7.1.1 State-of-the-Art
152(1)
7.1.2 Proposed Framework
153(1)
7.2 Data Acquisition and Pre-Processing
154(2)
7.2.1 Data Acquisition
154(1)
7.2.2 Pre-Processing
155(1)
7.3 Feature Extraction
156(2)
7.3.1 Overview
156(1)
7.3.2 MODWPT
156(1)
7.3.3 Feature Extraction Mechanism
156(2)
7.4 Classification Strategies
158(2)
7.4.1 Random Under-Sampling (RUS) and Random Over-Sampling (ROS) Techniques
158(1)
7.4.2 Adaptive Boosting Algorithm
158(1)
7.4.3 Random Under-Sampling Boosting Algorithm
159(1)
7.5 Evaluation
160(1)
7.6 Experiments
161(5)
7.6.1 Outlier Detection Using Smoothing Splines
161(2)
7.6.2 MODWPT-Based Signal Decomposition
163(1)
7.6.3 RusBoost NTL Detection Technique
163(1)
7.6.4 Comparison with Existing Approaches
164(2)
7.7 Conclusion
166(5)
References
167(4)
8 Electricity Market Participation Profiles Classification for Decision Support in Market Negotiation
171(16)
Tiago Pinto
Zita Vale
Acronyms
171(1)
8.1 Introduction
171(1)
8.2 Bilateral Negotiation
172(2)
8.3 Decision Support for Bilateral Negotiations
174(4)
8.3.1 Clustering of Players Profiles
176(1)
8.3.2 Classification of New Players
177(1)
8.3.2.1 Artificial Neural Networks
177(1)
8.3.2.2 Support Vector Machines
177(1)
8.4 Illustrative Results
178(5)
8.5 Conclusion
183(4)
References
184(3)
9 Socio-demographic, Economic, and Behavioral Analysis of Electric Vehicles
187(14)
Ruben Barreto
Tiago Pinto
Zita Vale
Acronyms
187(1)
9.1 Introduction
187(1)
9.2 Electric Vehicle Outlook
188(3)
9.2.1 Electric Mobility Market
188(1)
9.2.2 Economic Aspects
189(1)
9.2.3 Socio-demographic Aspects
190(1)
9.2.4 Recommendations for Policymakers
191(1)
9.3 Data Mining Models for EVs
191(6)
9.3.1 Charging Behavior
191(1)
9.3.2 EV User Behavior
192(1)
9.3.3 Driving Range
193(1)
9.3.4 Speed
194(1)
9.3.5 Electric Vehicle Battery
195(1)
9.3.6 Charging Station Planning
195(1)
9.3.7 Summary
196(1)
9.4 Conclusions
197(4)
References
197(4)
Part IV Forecasting
201(56)
10 A Multivariate Stochastic Spatiotemporal Wind Power Scenario Forecasting Model
203(20)
Wentei Bai
Duehee Lee
Kwang Y. Lee
Acronyms
203(1)
Nomenclature
203(1)
10.1 Introduction
204(2)
10.2 Generalized Dynamic Factor Model
206(13)
10.2.1 Derivation of the GDFM
206(2)
10.2.2 Estimation of the GDFM
208(2)
10.2.3 Forecast of the GDFM
210(2)
10.2.4 Verification of the GDFM
212(4)
10.2.5 Application of the GDFM
216(3)
10.3 Conclusion
219(4)
References
221(2)
11 Spatiotemporal Solar Irradiance and Temperature Data Predictive Estimation
223(14)
Chirath Pathiravasam
Ganesh Kumar Venayagamoorthy
Acronyms
223(1)
11.1 Introduction
223(2)
11.2 Virtual Weather Stations
225(2)
11.3 Distributed Weather Forecasting
227(1)
11.3.1 Spatiotemporal Prediction Network
227(1)
11.3.2 Computational Units
228(1)
11.4 Results and Discussion
228(4)
11.4.1 Weather Data Estimation
229(1)
11.4.2 Weather Data Prediction
230(2)
11.5 Summary
232(5)
Acknowledgment
234(3)
12 Application of Decomposition-Based Hybrid Wind Power Forecasting in Isolated Power Systems with High Renewable Energy Penetration
237(20)
Evgenii Semshikov
Michael Negnevitsky
James Hamilton
Xiaolin Wang
12.1 Introduction
237(1)
12.2 Decomposition Techniques
238(3)
12.2.1 Variational Mode Decomposition
239(1)
12.2.2 Decomposition of Wind Power Time Series
239(2)
12.3 Decomposition-Based Neural Network Forecasting
241(2)
12.3.1 Theory Behind LSTM
242(1)
12.3.2 VMD-LSTM for Wind Power Forecasting
242(1)
12.4 Forecast-Based Dispatch in Isolated Power Systems
243(6)
12.4.1 Control Strategy
244(2)
12.4.2 Regulation and Load Following Reserves
246(3)
12.5 Case Studies
249(4)
12.5.1 King Island Isolated Power System
249(1)
12.5.2 Case Study I (Control Strategy with No RE Forecast)
250(1)
12.5.3 Case Study II (Control Strategy Involving Persistence Model RE Forecast)
251(1)
12.5.4 Case Study III (Control Strategy Involving VMD-LSTM-Based RE Forecast)
251(1)
12.5.5 Economic Assessment Over a Year of Operation
252(1)
12.6 Conclusions and Discussions
253(4)
References
253(4)
Part V Data Analysis
257(86)
13 Harmonic Dynamic Response Study of Overhead Transmission Lines
259(22)
Dharmbir Prasad
Rudra P. Singh
Irfan Khan
Sushri Mukherjee
Acronyms
259(1)
Nomenclature
259(1)
13.1 Introduction to Methodology
260(4)
13.1.1 General
261(1)
13.1.2 Selection Aspects of Dampers
261(1)
13.1.3 Literature Review
262(2)
13.2 Problem Formulation
264(2)
13.2.1 Design Aspect
265(1)
13.2.2 Mathematical Modeling
265(1)
13.3 Numerical Analysis
266(7)
13.3.1 Simulation Inputs
267(1)
13.3.1.1 Model Description
267(1)
13.3.1.2 Load Excitation
268(1)
13.3.1.3 Span Wise Phase Lag
268(3)
13.3.2 Analysis Findings
271(2)
13.4 Conclusion
273(1)
13.A Appendix
274(7)
References
277(4)
14 Evaluation of Shortest Path to Optimize Distribution Network Cost and Power Losses in Hilly Areas: A Case Study
281(18)
Subho Upadhyay
Rajeev K. Chauhan
Mahendra P. Sharma
Acronyms
281(1)
14.1 Introduction
282(1)
14.2 Design of Power Distribution Network
282(1)
14.3 Digital Elevation Map
283(1)
14.4 Placement of Generators and Load Centers
283(2)
14.5 Single Line Diagram of 9-Bus System
285(1)
14.6 Finding Shortest Path Between Load/Generating Centers
286(4)
14.6.1 Objective Function
287(2)
14.6.2 Distribution Network Distance
289(1)
14.7 Selection of Conductor Using Newton Raphson Method
290(3)
14.7.1 Estimation of Conductor Cost
292(1)
14.8 Calculation of CO2 Emission Cost Saving
293(1)
14.9 Overall Cost Estimation of Distribution System
294(1)
14.10 Sensitivity Analysis
294(1)
14.10.1 Change in Diesel Fuel Price
295(1)
14.10.2 Change in Solar Radiation
295(1)
14.10.3 Change in Demand
295(1)
14.10.4 Change in Energy Index Ratio
295(1)
14.11 Conclusion
295(4)
References
296(3)
15 Intelligent Approaches to Support Demand Response in Microgrid Planning
299(20)
Rahmat Khezri
Amin Mahmoudi
Hirohisa Aki
Acronyms
299(1)
15.1 Introduction
299(1)
15.2 Microgrid Planning
300(6)
15.2.1 Problem Overview
301(1)
15.2.2 Objective Functions
302(1)
15.2.3 Data Analysis
303(1)
15.2.3.1 Weather Data
304(1)
15.2.3.2 Load Data
304(1)
15.2.3.3 Electricity Price
304(1)
15.2.4 Microgrid Components
305(1)
15.2.4.1 Distributed Energy Resources
305(1)
15.2.4.2 Energy Storage Systems
305(1)
15.2.5 Microgrid Operation
306(1)
15.3 Demand Response in Microgrids
306(3)
15.3.1 Overview on Demand Response Application for Microgrids
306(1)
15.3.2 Demand Response: Types and Characteristics
307(1)
15.3.3 Incentive DR
308(1)
15.3.4 Time-Based DR
309(1)
15.4 Intelligent Approaches to Support Demand Response
309(6)
15.4.1 Data Mining Methods in DR
310(1)
15.4.1.1 Supervised Data Mining
310(2)
15.4.1.2 Unsupervised Data Mining
312(1)
15.4.2 Fuzzy Logic-Based DR
313(1)
15.4.3 Applications in Microgrid Planning
313(1)
15.4.3.1 Cost Reduction
313(1)
15.4.3.2 Resiliency Enhancement
314(1)
15.4.3.3 Flexibility Improvement
314(1)
15.4.3.4 Battery Capacity Reduction
314(1)
15.5 Conclusion
315(4)
References
315(4)
16 Socioeconomic Analysis of Renewable Energy Interventions: Developing Affordable Small-scale Household Sustainable Technologies in Northern Uganda
319(24)
Jens B. Holm-Nielsen
Achora P.O. Mamur
Samson Masebinu
Acronyms
319(1)
16.1 Introduction
319(2)
16.2 Renewable Energy Technologies
321(2)
16.2.1 Bio-oil
321(1)
16.2.2 Bio-pellets
322(1)
16.2.3 Biogas
322(1)
16.2.4 Solar Cookers
322(1)
16.2.5 Solar PV
323(1)
16.3 Methodology
323(1)
16.3.1 Driver Pressure Impact State Response Framework
323(1)
16.3.2 Cost-Benefit Analysis
324(1)
16.4 Application of the Method
324(3)
16.5 Case Study Results for Product Development
327(6)
16.5.1 Field Study
327(1)
16.5.2 Source of Energy for Cooking
328(1)
16.5.3 Source of Energy for Lighting
328(1)
16.5.4 Household Income Level
328(1)
16.5.5 Challenges for Firewood and Charcoal Use
329(1)
16.5.6 The Rank of Adoption Toward Sustainable Renewable Energy Technologies
329(1)
16.5.7 Household Opinions for Modern Energy Technologies
330(1)
16.5.8 Level of Awareness of the Population
331(1)
16.5.9 Medium of Information
331(1)
16.5.10 Promotion to Purchase Alternative Renewable Energy Technologies
331(1)
16.5.11 Sources of Fund for Investment in Northern Uganda Toward Renewable Energy Technologies for Households
332(1)
16.6 Cost--Benefit Analysis (CBA)
333(4)
16.6.1 Benefits to Better Health
333(1)
16.6.2 Benefits on Greenhouse Gas Emissions Reduction
334(1)
16.6.3 Benefits of the District Forest Resources Preservation
334(1)
16.6.4 Outcomes of Cost--Benefit Analysis
334(3)
16.7 Conclusion
337(6)
References
338(5)
Part VI Other Machine Learning Applications
343(90)
17 Non-Intrusive Load Monitoring Using A Parallel Bidirectional Long Short-Term Memory Model
345(26)
Victor Andrean
Kuo-Lung Lian
Nomenclature
345(1)
17.1 Introduction
346(3)
17.1.1 Optimization-Based Approach
346(1)
17.1.2 Learning-Based Approach
347(2)
17.2 NILM System and Data Preprocessing
349(3)
17.2.1 Data Scaling
349(1)
17.2.2 Window Length Selection
350(1)
17.2.3 Input-to-Output Relation (IOR)
350(1)
17.2.3.1 IOR1
351(1)
17.2.3.2 IOR2
351(1)
17.2.3.3 IOR3
351(1)
17.2.3.4 IOR4
351(1)
17.3 Proposed Method
352(6)
17.3.1 Feature Extractor
353(2)
17.3.2 Elements of the PBLSTM
355(1)
17.3.2.1 Convolution Neural Network (CNN)
355(1)
17.3.2.2 Bidirectional Long Short-Term Memory (BLSTM)
356(1)
17.3.2.3 Dense Layer
357(1)
17.3.2.4 Deep Neural Network Training
358(1)
17.4 Validation
358(10)
17.5 Conclusion
368(3)
References
368(3)
18 Reinforcement Learning for Intelligent Building Energy Management System Control
371(16)
Olivera Kotevska
Philipp Andelfinger
Chapter Objectives
371(1)
18.1 Introduction
371(1)
18.2 Reinforcement Learning
372(4)
18.2.1 Deep Reinforcement Learning
374(1)
18.2.2 Advanced Reinforcement Learning
375(1)
18.3 Applications of Deep Reinforcement Learning in Building Energy Management Systems Control
376(4)
18.3.1 Heating, Ventilation, and Air Conditioning
377(2)
18.3.2 Water Heater
379(1)
18.3.3 Other Devices
380(1)
18.4 Challenges and Research Directions
380(3)
18.5 Conclusions
383(4)
References
383(4)
19 Federated Deep Learning Technique for Power and Energy Systems Data Analysis
387(18)
Hamed Moayyed
Arash Moradzadeh
Behnam Mohammadi-Ivatioo
Reza Ghorbani
Nomenclature
387(1)
Acronyms
387(1)
Symbols
387(1)
19.1 Introduction
388(1)
19.2 Federated Learning (FL)
388(8)
19.2.1 Federated Learning Motivation
389(1)
19.2.2 Performance Evaluation Metrics
390(1)
19.2.3 Federated Learning vs. Distributed Machine Learning Approaches
391(1)
19.2.4 The Federated Averaging Algorithm
391(2)
19.2.5 Applications of Federated Learning
393(2)
19.2.6 Challenges of Federated Learning
395(1)
19.3 Power Systems Challenges and the Performance of Artificial Intelligence Techniques in It
396(3)
19.3.1 AI-Based Forecasting in Power Systems
396(1)
19.3.2 AI-Based Condition Monitoring in Power Systems
397(2)
19.4 Application of Federated Deep Learning in Power and Energy Systems
399(1)
19.4.1 Electric Vehicle Networks
399(1)
19.4.2 False Data Injection Attacks in Solar Farms
399(1)
19.4.3 Solar Irradiation Forecasting
400(1)
19.4.4 Heating Load Demand Forecasting
400(1)
19.5 Conclusion
400(5)
References
401(4)
20 Data Mining and Machine Learning for Power System Monitoring, Understanding, and Impact Evaluation
405(28)
Xinda Ke
Huiying Ren
Qiuhua Huang
Pavel Etingov
Zhangshuan Hou
Acronyms
405(1)
20.1 Introduction
406(1)
20.2 Power System Monitoring with Phasor Measurement Unit Data
407(4)
20.2.1 PMU Anomaly Detection Framework
407(1)
20.2.2 Anomaly Detection and Classification
408(3)
20.3 Power System Mechanistic and Predictive Understanding
411(12)
20.3.1 Spatiotemporal Pattern Recognition in PMU Signals
412(1)
20.3.1.1 Time Series Pattern Recognition
412(3)
20.3.1.2 Similarities and Variations Across Units
415(2)
20.3.1.3 Similarities/Discrepancies Between Days/Months
417(1)
20.3.2 Events Classification and Localization Through Convolutional Neural Network
417(1)
20.3.2.1 Polish System Testbed and Data Preparation
417(2)
20.3.2.2 Fault Types and Implementation
419(1)
20.3.2.3 CNN Model Development
419(1)
20.3.2.4 CNN Model Evaluation
420(1)
20.3.2.5 Fault Localization
421(1)
20.3.2.6 Fault Classification
422(1)
20.4 Characterization and Modelling of Weather and Power Extremes
423(7)
20.4.1 Data Sources
424(1)
20.4.2 Spatiotemporal Analysis
425(3)
20.4.3 Probabilistic Modelling of Lines Outage
428(2)
20.5 Conclusion
430(3)
References
430(3)
Conclusions 433(2)
Zita Vale, Tiago Pinto, Michael Negnevitsky, and Ganesh Kumar Venayagamoorthy Index 435
Zita Vale, PhD, is a Full Professor in the Electrical Engineering Department at the School of Engineering of the Polytechnic of Porto and Director of the GECAD Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development. She is the Chair of the IEEE PES Working Group on Intelligent Data Mining and Analysis.

Tiago Pinto, PhD, is an Assistant Professor at the University of Trįs-os-Montes e Alto Douro, and a senior researcher at INESC-TEC, Portugal. During the development of this book he was with the GECAD Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development.

Michael Negnevitsky, PhD, is the Chair Professor in Power Engineering and Computational Intelligence, and Director of the Centre for Renewable Energy and Power Systems of the University of Tasmania, Australia.

Ganesh Kumar Venayagamoorthy, PhD, is the Duke Energy Distinguished Professor of Electrical and Computer Engineering at Clemson University. He is a Fellow of the IEEE, Institution of Engineering and Technology, South African Institute of Electrical Engineers and Asia-Pacific Artificial Intelligence Association.
Pastovi nuoroda: https://www.kriso.lt/db/9781119834052_pe.html
Raktažodžiai: