| Description |
1 online resource (356 p.) |
| Contents |
Front Cover -- Monitoring and Control of Electrical Power Systems Using Machine Learning Techniques -- Copyright -- Contents -- Contributors -- Preface -- 1 Derivation of generic equivalent models for distribution network analysis using artificial intelligence techniques -- 1.1 Introduction -- 1.2 Examined equivalent models -- 1.2.1 Structure of the examined equivalent models -- 1.2.1.1 The ZIP model -- 1.2.1.2 The modified ERM -- 1.2.2 Parameter estimation -- 1.3 Derivation of generic equivalent models -- 1.3.1 Examined GAs -- 1.3.1.1 Generalization via statistical analysis |
|
1.3.1.2 Generalization via clustering techniques and statistical analysis -- 1.3.1.3 Generalization using ANNs -- 1.3.1.4 Generalization using clustering techniques and ANNs -- 1.3.1.5 Summary of the considered GAs -- 1.3.2 Evaluation metrics -- 1.4 Methods evaluation using laboratory measurements -- 1.4.1 Description of the lab setup -- 1.4.2 Parameter identification and derivation of generic models -- 1.4.3 Evaluation results -- 1.5 Implementation of the examined GAs using Matlab -- 1.5.1 Matlab files for the derivation of generic equivalent models -- 1.5.2 Lab measurements |
|
1.5.3 Didactic example -- 1.6 Conclusions -- Acknowledgment -- References -- 2 Disturbance dataset development for machine-learning-based power quality monitoring in distributed generation systems: a practical guide -- 2.1 Relevance of the disturbance dataset in the training/assessing of machine-learning-based models for power quality monitoring -- 2.1.1 Power quality monitoring in distributed generation systems -- 2.1.2 Machine-learning-based strategies for the classification of PQ disturbances -- 2.2 Development of PQ disturbance datasets for training/assessing of the model |
|
2.3 Generation and development of synthetic disturbance dataset -- 2.3.1 Numerical models for the generation of PQ disturbances -- 2.3.2 Typical parameters variation of disturbances according to PQ monitoring standards -- 2.3.3 Example of PQ disturbance generation using disturbances numerical models and Matlab programing -- 2.4 Development of PQ disturbance datasets with simulation software -- 2.4.1 Features of the simulation software -- 2.4.2 Example of disturbances generation by simulation software for dataset development -- 2.5 Real-world datasets for PQ disturbance classification |
|
2.5.1 PQ monitoring recommendations for the development of real-world disturbance datasets -- 2.5.1.1 Variables to be measured -- 2.5.1.2 Monitoring devices -- 2.5.1.3 Monitoring location -- 2.5.1.4 Data acquisition -- 2.5.2 Available open real-world datasets for PQ disturbance classification -- 2.6 Effect of the class imbalance issue on machine learning models trained for PQ disturbance classification -- 2.6.1 Example of PQ disturbances classification, influenced by unbalanced data-based training -- 2.6.1.1 Disturbance dataset description -- 2.6.1.2 Training of the classification models |
| Notes |
Description based upon print version of record |
|
2.6.1.3 Definition of the evaluation metrics |
| Form |
Electronic book
|
| Author |
Segundo Sevilla, Felix Rafael
|
|
Korba, Petr
|
| ISBN |
9780323984041 |
|
0323984045 |
|
