Machine Learning and Data Analysis for Energy Efficiency in Buildings: Intelligent Operation, Maintenance, and Optimization of Building Energy Systems introduces data basics, from selecting and evaluating data to the identification and repair of abnormalities. Other sections cover data mining applied to energy forecasting, including long- and short-term predictions, the introduction of occupant-focused behavior analysis, and current methods for supply and demand applications. Case studies are included in each part to assist in evaluation and implementation of these techniques across building energy systems.
Working from the fundamentals of big data analysis to a complete method for building energy assessment, flexibility, and management, this book provides students, researchers, and professionals with an essential, cutting-edge resource on this important technology.
1. Chapter 1 Introduction - p. 3 2. Chapter 2 Data preparation - p. 11 3. Chapter 3 Abnormal data identification and repair - p. 35 4. Chapter 4 Classification and definition of data type - p. 51 5. Chapter 5 Identification and repair of abnormal energy consumption data - p. 55 6. Chapter 6 Case studies in different buildings - p. 93 7. Part II Data mining - p. 147 8. Chapter 7 Energy consumption forecasting - p. 149 9. Chapter 8 Short-time-scale energy consumption prediction (for O&M regulation) - p. 161 10. Chapter 9 Long-time-scale energy consumption prediction (for design evaluation) - p. 173 11. Chapter 10 Case studies in different scenarios - p. 219 12. Part III Data application - p. 295 13. Chapter 11 Review of evaluation and methods for energy supply and demand matching - p. 297 14. Chapter 12 Energy supply and demand matching evaluation methods: Power load matching coefficient - p. 327 15. Chapter 13 Optimization of supply-side energy schemes - p. 341 16. Chapter 14 Optimization of demand-side energy use solutions - p. 385 17. Chapter 15 Conclusions - p. 411 18. Index - p. 413
Machine Learning and Data Analysis for Energy Efficiency in Buildings: Intelligent Operation, Maintenance, and Optimization of Building Energy Systems introduces data basics, from selecting and evaluating data to the identification and repair of abnormalities. Other sections cover data mining applied to energy forecasting, including long- and short-term predictions, the introduction of occupant-focused behavior analysis, and current methods for supply and demand applications. Case studies are included in each part to assist in evaluation and implementation of these techniques across building energy systems.
Working from the fundamentals of big data analysis to a complete method for building energy assessment, flexibility, and management, this book provides students, researchers, and professionals with an essential, cutting-edge resource on this important technology.
1. Chapter 1 Introduction - p. 3 2. Chapter 2 Data preparation - p. 11 3. Chapter 3 Abnormal data identification and repair - p. 35 4. Chapter 4 Classification and definition of data type - p. 51 5. Chapter 5 Identification and repair of abnormal energy consumption data - p. 55 6. Chapter 6 Case studies in different buildings - p. 93 7. Part II Data mining - p. 147 8. Chapter 7 Energy consumption forecasting - p. 149 9. Chapter 8 Short-time-scale energy consumption prediction (for O&M regulation) - p. 161 10. Chapter 9 Long-time-scale energy consumption prediction (for design evaluation) - p. 173 11. Chapter 10 Case studies in different scenarios - p. 219 12. Part III Data application - p. 295 13. Chapter 11 Review of evaluation and methods for energy supply and demand matching - p. 297 14. Chapter 12 Energy supply and demand matching evaluation methods: Power load matching coefficient - p. 327 15. Chapter 13 Optimization of supply-side energy schemes - p. 341 16. Chapter 14 Optimization of demand-side energy use solutions - p. 385 17. Chapter 15 Conclusions - p. 411 18. Index - p. 413
