Statistical Relational Artificial Intelligence in Photovoltaic Power Uncertainty Analysis addresses uncertainty issues in photovoltaic power generation while also supporting the collaborative enhancement of understanding and applying theory and methods through the integration of models, cases, and code. The book employs StaRAI to address uncertainty analysis and modeling issues at different time scales in photovoltaic power generation, including photovoltaic power prediction, probabilistic power flow, stochastic planning, and more. Chapters cover uncertainty of PV power generation from short to long time scales, including day-ahead scheduling (24 hours in advance), intraday scheduling (minute to hour rolling), and grid planning (15 years).
Other sections study the impact of photovoltaic uncertainty on the power grid, offering the most classic cases of probabilistic load flow and PV stochastic planning.
The theoretical content of this book is not only systematic but supplemented with concrete examples and MATLAB/Python codes. Its contents will be of interest to all those working on photovoltaic planning, power generation, power plants, and applications of AI, including researchers, advanced students, faculty engineers, R&D, and designers.
1. 7.1 Introduction - p. 225 2. 7.2 Methodology - p. 227 3. 7.3 Case analysis - p. 244 4. 7.4 Conclusion - p. 271 5. 7.5 Study questions - p. 272 6. 8. Statistical machine learning–based stochastic planning for photovoltaics - p. 275 7. 8.1 Introduction - p. 275 8. 8.2 Methodology - p. 276 9. 8.3 Case analysis - p. 302 10. 8.4 Conclusion - p. 325 11. 8.5 Study questions - p. 326 12. 9. Future predictions and summary - p. 329 13. Index - p. 337
Statistical Relational Artificial Intelligence in Photovoltaic Power Uncertainty Analysis addresses uncertainty issues in photovoltaic power generation while also supporting the collaborative enhancement of understanding and applying theory and methods through the integration of models, cases, and code. The book employs StaRAI to address uncertainty analysis and modeling issues at different time scales in photovoltaic power generation, including photovoltaic power prediction, probabilistic power flow, stochastic planning, and more. Chapters cover uncertainty of PV power generation from short to long time scales, including day-ahead scheduling (24 hours in advance), intraday scheduling (minute to hour rolling), and grid planning (15 years).
Other sections study the impact of photovoltaic uncertainty on the power grid, offering the most classic cases of probabilistic load flow and PV stochastic planning.
The theoretical content of this book is not only systematic but supplemented with concrete examples and MATLAB/Python codes. Its contents will be of interest to all those working on photovoltaic planning, power generation, power plants, and applications of AI, including researchers, advanced students, faculty engineers, R&D, and designers.
1. 7.1 Introduction - p. 225 2. 7.2 Methodology - p. 227 3. 7.3 Case analysis - p. 244 4. 7.4 Conclusion - p. 271 5. 7.5 Study questions - p. 272 6. 8. Statistical machine learning–based stochastic planning for photovoltaics - p. 275 7. 8.1 Introduction - p. 275 8. 8.2 Methodology - p. 276 9. 8.3 Case analysis - p. 302 10. 8.4 Conclusion - p. 325 11. 8.5 Study questions - p. 326 12. 9. Future predictions and summary - p. 329 13. Index - p. 337
