| Nota di contenuto |
Intro -- Preface -- Contents -- Chapter 1: Power System Challenges and Issues -- 1.1 Introduction -- 1.2 Present and Future Challenges -- 1.2.1 Greenhouse Gases Emission -- 1.2.2 Distributed Generation and Renewables -- 1.2.3 Energy Storages Integrity -- 1.2.4 Electric Vehicles -- 1.2.5 Decentralization and Smart Contract -- 1.2.6 Reliability and Security Problems -- 1.2.7 Load Forecasting Problems -- 1.2.8 Big Data -- 1.3 Machine Learning (ML) Application and Challenges -- 1.4 Conclusion -- References -- Chapter 2: Introduction and Literature Review of Power System Challenges and Issues -- 2.1 Introduction -- 2.2 Power System Planning -- 2.3 Power System Operation Challenges -- 2.3.1 Climate Change Impact on Power System Operation -- 2.3.2 Disturbance/Unexpected Events Impact on Power System Operation -- 2.3.3 Cyberattack Impact on Power System Operation -- 2.4 Power System Control -- 2.4.1 Power Grid Criteria for Control and Stability -- 2.4.2 Regular Contingencies -- 2.4.3 Extreme Contingencies -- 2.4.4 Frequency Control -- 2.4.5 Voltage and Angle Control -- References -- Chapter 3: Machine Learning and Power System Planning: Opportunities and Challenges -- 3.1 Introduction -- 3.1.1 Machine Learning Methods -- 3.2 Literature Review -- 3.3 Load Forecasting -- 3.3.1 SVM (Support Vector Machine) -- 3.3.2 Long Short-Term Memory Network (LSTM) -- 3.3.3 Results of Load Forecasting Using Machine Learning -- 3.4 ML in Power Systems Optimization Problems -- 3.5 Conclusion -- References -- Chapter 4: Introduction to Machine Learning Methods in Energy Engineering -- 4.1 Introduction -- 4.2 Data Mining and Its Applications in Energy Engineering -- 4.3 Machine Learning Schemes in Energy Engineering -- 4.3.1 Machine Learning Methods: Application, Formulation, and Structure -- 4.3.1.1 Support Vector Machine (SMV) -- 4.3.1.2 Group Method Data Handling (GMDH).
4.3.1.3 Support Vector Regression (SVR) -- 4.3.1.4 General Regression Neural Network (GRNN) -- 4.3.1.5 Decision Tree -- 4.3.1.6 k-Means -- 4.4 Deep Learning Schemes in Energy Engineering -- 4.4.1 Deep Learning Methods: Application, Formulation, and Structure -- 4.4.1.1 Convolutional Neural Network (CNN) -- 4.4.1.2 Autoencoders -- 4.4.1.3 Recurrent Neural Network (RNN) -- 4.4.1.4 Restricted Boltzmann Machine (RBM) -- 4.5 Evaluating the Results of Regression and Classification Applications -- 4.6 Conclusions -- References -- Chapter 5: Introduction and Literature Review of the Application of Machine Learning/Deep Learning to Control Problems of Powe... -- 5.1 Introduction -- 5.1.1 Reliability and Security -- 5.1.2 Stability -- 5.2 Overview of Machine Learning and Deep Learning -- 5.2.1 Machine Learning Technique -- 5.2.2 Deep Learning Technique -- 5.2.3 Categorization of ML and DL -- 5.3 Overview of Power System Control Problems -- 5.4 Evaluation of Operating Modes of Power System Control Using Machine Learning Methods -- 5.4.1 Preventive Mode -- 5.4.2 Normal Mode -- 5.4.3 Emergency Mode -- 5.4.4 Restoration Mode -- 5.5 Application of Machine Learning Methods in Evaluating the Security and Stability of the Power System -- 5.5.1 Transient Stability Assessment -- 5.5.2 Voltage Stability Assessment -- 5.5.3 Power Quality Disturbances Assessment -- 5.5.4 Frequency Stability Assessment -- 5.6 Challenges, Comparative Discussion, and Future Perspectives -- 5.7 Conclusions -- References -- Chapter 6: Introduction and Literature Review of the Application of Machine Learning/Deep Learning to Load Forecasting in Powe... -- 6.1 Introduction -- 6.2 Most Important Challenges in Power Systems Short-, Medium-, and Long-Term Load Forecasting -- 6.2.1 Short-Term Load Forecasting -- 6.2.2 Midterm Load Forecasting -- 6.2.3 Long-Term Load Forecasting.
6.3 Machine Learning and Deep Learning Applications in Load Forecasting of Power System -- 6.3.1 Machine Learning and Deep Learning Algorithms Used for Load Forecasting -- 6.3.2 Performance Assessment of Algorithms -- 6.4 Conclusions -- References -- Chapter 7: A Survey of Recent Particle Swarm Optimization (PSO)-Based Clustering Approaches to Energy Efficiency in Wireless S... -- 7.1 Introduction -- 7.2 Background -- 7.2.1 Structure of WSNs -- 7.2.2 Particle Swarm Optimization -- 7.2.3 Problem Definition -- 7.3 PSO-Based Approaches -- 7.4 Conclusions -- References -- Chapter 8: Clustering in Power Systems Using Innovative Machine Learning/Deep Learning Methods -- 8.1 Introduction -- 8.2 Power System Clustering Using Feature Extraction Methods -- 8.2.1 Principal Component Analysis -- 8.2.2 Independent Component Analysis -- 8.3 Power System Clustering Using Supervised Learning Methods -- 8.3.1 Artificial Neural Networks -- 8.3.2 Decision Trees -- 8.4 Power System Clustering Using Unsupervised Learning Methods -- 8.4.1 K-Means Clustering Algorithm -- 8.4.2 Partitioning around Medoid Algorithm -- 8.4.3 Fuzzy C-Means Clustering Algorithm -- 8.4.4 Fuzzy C-Medoids Clustering Algorithm -- 8.4.5 Subtractive Clustering Algorithm -- 8.4.6 Density-Based Spatial Clustering of Applications with Noise -- 8.4.7 Support Vector Clustering Algorithm -- 8.5 A Discussion on the Use of Machine Learning for Power System Clustering and Possible Future Works -- 8.6 Conclusions -- References -- Chapter 9: Voltage Stability Assessment in Power Grids Using Novel Machine Learning-Based Methods -- 9.1 Introduction -- 9.1.1 Literature Review -- 9.1.2 Contributions and Novelties -- 9.1.3 Structure of Chapter -- 9.2 Voltage Stability Problem Statement -- 9.3 The Proposed Framework -- 9.3.1 Database Generation -- 9.3.1.1 Sampling -- 9.3.1.2 Importance Sampling.
9.3.2 Training the Machine Learning Technique -- 9.3.2.1 Ensemble Method -- Bagged Tree -- AdaBoost -- 9.3.2.2 Dimensionality Reduction -- Feature Selection -- Feature Extraction -- 9.3.2.3 Hyperparameter´s Tuning -- 9.3.3 Performance Evaluation -- 9.3.3.1 PMU Uncertainly -- 9.3.4 Online Application -- 9.4 Simulations and Results -- 9.4.1 IEEE 39-Bus Test System -- 9.4.1.1 Database Generation -- 9.4.1.2 Simple ML Model Training -- 9.4.1.3 Optimal Dataset for Training -- 9.4.1.4 ML Techniques Performance -- 9.4.1.5 Dimensionally Reduction -- 9.4.1.6 Hyperparameters Tuning -- 9.4.1.7 Performance Evaluation -- 9.4.1.8 Online Application -- 9.4.2 118-Bus Test System -- 9.5 Conclusion -- References -- Chapter 10: Evaluation and Classification of Cascading Failure Occurrence Potential Due to Line Outage -- 10.1 Introduction -- 10.2 Overview of the Proposed Method -- 10.3 Cascading Failure Severity Predictor DT -- 10.3.1 C4.5 Algorithm -- 10.3.1.1 Entropy -- 10.3.1.2 Information Gain -- 10.3.2 Considering Continuous Attributes -- 10.3.2.1 Gain Ratio -- 10.4 Dominant Operating Variables -- 10.4.1 DOVs´ Identification Algorithm -- 10.5 The Proposed Method -- 10.6 Simulation Studies -- 10.6.1 Preparing Scenarios -- 10.6.2 Evaluating the Criticality of the Lines -- 10.6.2.1 Evaluating Criticality of Line 17-18 -- 10.6.2.2 Identifying the DOVs and Training the CSPDTs for Lines 17-18 -- 10.6.2.3 Evaluating the Criticality of Lines 21-22 -- 10.6.2.4 Identifying the DOVs and Training the CSPDTs for Lines 21-22 -- 10.6.3 Performance Validation -- 10.6.4 Global Performance -- 10.7 Conclusion -- 10.8 Suggestion for Future Research -- References -- Chapter 11: LSTM-Assisted Heating Energy Demand Management in Residential Buildings -- 11.1 Introduction -- 11.2 Dataset -- 11.3 LSTM Mathematical Model -- 11.4 Simulation and Numerical Results -- 11.5 Conclusion.
References -- Chapter 12: Wind Speed Forecasting Using Innovative Regression Applications of Machine Learning Techniques -- 12.1 Introduction -- 12.2 Data Set -- 12.3 Methods -- 12.3.1 Multilayer Perceptron (MLP) -- 12.4 Simulation and Numerical Results -- 12.5 Conclusion -- References -- Chapter 13: Effective Load Pattern Classification by Processing the Smart Meter Data Based on Event-Driven Processing and Mach... -- 13.1 Introduction -- 13.2 Background and Literature Review -- 13.2.1 Smart Metering -- 13.2.2 Smart Meter Data Acquisition -- 13.2.3 Feature Extraction -- 13.2.4 Pattern Recognition -- 13.3 Materials and Methods -- 13.3.1 Smart Meter Database -- 13.3.2 Signal Reconstruction -- 13.3.3 Event-Driven Sensing (EDS) -- 13.3.4 Event-Driven Segmentation -- 13.3.5 Feature Extraction -- 13.3.6 Classification Techniques -- 13.3.6.1 K-Nearest Neighbor (KNN) -- 13.3.6.2 Artificial Neural Network (ANN) -- 13.3.6.3 Naïve Bayes -- 13.4 Results -- 13.5 Discussion -- 13.6 Conclusion -- References -- Chapter 14: Prediction of Out-of-Step Condition for Synchronous Generators Using Decision Tree Based on the Dynamic Data by WA... -- 14.1 Introduction -- 14.2 The Framework of the Proposed Method -- 14.3 The Proposed Method -- 14.3.1 Decision Tree -- 14.3.2 Fault Detection by FDDT -- 14.3.3 Fault Clearance Detection by CDDT -- 14.3.4 Prediction of Instability by IPDT -- 14.3.5 Nature of Operating Variables Used by DT -- 14.4 Simulation -- 14.4.1 Producing Training Scenarios of DT -- 14.4.2 Time Windows Data -- 14.4.3 FDDT Training -- 14.4.4 CDDT Training -- 14.4.5 IPDT Training -- 14.4.6 Over-/Under-Fitting Evaluation of IPDT -- 14.4.7 Comparison of DT Performance with SVM and ANN -- 14.5 Validation of the Proposed Scheme Performance -- 14.5.1 Validation with Noisy Data -- 14.6 Conclusion -- References.
Chapter 15: The Adaptive Neuro-Fuzzy Inference System Model for Short-Term Load, Price, and Topology Forecasting of Distributi.
|
Info
2018 International Conference on Computation of Power, Energy, Information and Communication : 28-29 March 2018, Chennai, India / / Institute of Electrical and Electronics Engineers
