Machine Learning and Data Analysis for Energy Efficiency in Buildings : Intelligent Operation, Maintenance, and Optimization of Building Energy Systems.

Format:

Book

Author/Creator:

Zhao, Tianyi.

Contributor:

Zhang, Chengyu.

Jiang, Ben.

Series:

Advances in Intelligent Energy Systems Series

Language:

English

Physical Description:

1 online resource (354 pages)

Edition:

1st ed.

Place of Publication:

Chantilly : Elsevier, 2025.

Summary:

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.

Contents:

Front Cover

Front Matter

Copyright

Contents

Foreword

Preface

Part I Data basics

Chapter 1 Introduction

1.1 Introduction

1.1.1 Background

1.1.2 Research progress

1.1.3 Architecture

References

Chapter 2 Data preparation

2.1 Data preparation

2.1.1 Basic information about the building (Clusters)

2.2 Introduction to energy consumption data acquisition - Construction of the energy consumption data platform

2.2.1 Basic information on the construction of the platform

2.2.2 Functions that can be realized by the platform

2.3 Description of access to non-energy data

2.3.1 Outdoor environment and outdoor meteorological data acquisition

2.3.2 Building user behavior data acquisition

2.4 Preliminary analysis of time-varying characteristics of electricity consumption in buildings

2.5 Summary of this chapter

Chapter 3 Abnormal data identification and repair

3.1 A review of energy consumption data anomalies and categorization

3.2 Overview of energy consumption data anomaly identification

3.3 Overview of energy consumption data anomaly remediation

3.4 Summary of this chapter

Chapter 4 Classification and definition of data type

4.1 Data classification

4.2 Summary of this chapter

Chapter 5 Identification and repair of abnormal energy consumption data

5.1 Methodology for identifying energy consumption data abnormalities

5.1.1 Identification of abnormalities in lighting and socket energy consumption data

5.1.2 Identification of centralized air conditioning data abnormalities

5.2 Methodologies for repairing energy consumption data abnormalities

5.2.1 Lighting socket data abnormality repair

5.2.2 Centralized air-conditioning data abnormality repair

5.3 Summary of this chapter

References.

Chapter 6 Case studies in different buildings

6.1 Lighting socket energy consumption data abnormality identification and repair cases

6.1.1 Example of repairing apparent abnormalities in energy consumption data of lighting sockets

6.1.2 Case of repairing hidden abnormalities in energy consumption data of lighting sockets

6.2 Centralized air conditioning energy consumption data abnormality identification and repair cases

6.3 Summary of this chapter

Part II Data mining

Chapter 7 Energy consumption forecasting

7.1 Energy consumption forecasting

7.2 Physical modeling approach

7.3 Data-driven approach

7.4 Summary of this chapter

Chapter 8 Short-time-scale energy consumption prediction (for O&amp

M regulation)

8.1 Input improvement methods

8.1.1 Definition and classification of occupant behavior probability

8.1.2 Modeling of occupant behavior probability

8.2 Algorithm improvement methods

8.2.1 Convolutional neural networks and long and short-term memory neural networks

8.2.2 Sparrow search algorithm

8.2.3 Squeeze-and-excitation block attention mechanism

8.3 Summary

Chapter 9 Long-time-scale energy consumption prediction (for design evaluation)

9.1 Introduction

9.2 Building classification

9.3 Physical model of prototype building with using eQUEST as an example

9.3.1 Building information research

9.3.2 eQUEST modeling (Wizard mode)

9.3.3 eQUEST modeling (Detailed mode)

9.3.4 Correcting the model

9.4 EUI modified based on bayesian theory

9.5 Bottom-up analysis

9.6 Summary

Chapter 10 Case studies in different scenarios

10.1 Case studies for energy consumption forecasting in different scenarios

10.2 Case studies for short-time-scale building energy consumption forecasting.

10.2.1 Example building introduction

10.2.2 Cases and results

10.2.3 Discussions

10.3 Case studies for long-time-scale building energy consumption forecasting

10.3.1 Example building introduction

10.3.2 Cases and results

10.3.3 Discussions

10.4 Case studies for ac and plug-load energy consumption forecasting

10.4.1 AC energy consumption

10.4.2 Plug-load energy consumption

10.5 Summary of this chapter

Part III Data Application

Chapter 11 Review of evaluation and methods for energy supply and demand matching

11.1 Review of evaluation and methods for energy supply and demand optimization

11.2 Evaluation and objective functions for energy supply and demand optimization

11.2.1 Evaluation

11.2.2 Objective functions

11.2.3 Constraints

11.2.4 Algorithms

11.3 Methods for energy supply and demand optimization

11.3.1 Energy demand optimization

11.3.2 Energy supply optimization

11.3.3 Energy demand-supply matching and optimization

11.4 Summary of this chapter

Chapter 12 Energy supply and demand matching evaluation methods: Power load matching coefficient

12.1 Supply demand optimization evaluation and objective functions

12.2 Supply demand optimization constraints

12.2.1 Electricity supply and demand balance constraints

12.2.2 Fluctuation and standby constraints

12.2.3 Battery constraints

12.2.4 EV constraints

12.2.5 PV constraints

12.2.6 Thermal comfort constraints

12.3 Supply demand optimization solving algorithms

12.4 Supply demand optimization methods and key parameters

12.5 Summary of this chapter

Chapter 13 Optimization of supply-side energy schemes

13.1 Example building introduction

13.2 Methods of supply-side optimization based on occupant behavior models.

13.2.1 Flexible regulation for start-up temperature of split ACs

13.2.2 Organized charging of electric vehicles

13.2.3 Lighting management and course optimization in educational buildings

13.2.4 Lighting and plug management in dormitory buildings

13.3 Cases and results

13.3.1 Results of flexible energy-use regulation in single buildings

13.3.2 Results of flexible energy-use regulation in the whole community

13.3.3 Results of microgrid operation scheduling optimization

13.4 Discussions and conclusions

13.5 Summary of this chapter

Chapter 14 Optimization of demand-side energy use solutions

14.1 Optimization of demand-side energy use solutions

14.2 Methods of demand-side optimization

14.2.1 PV power generation forecasting

14.2.2 Battery charging and discharging calculation

14.2.3 PV-Battery design, operation, and optimization

14.3 Cases and results

14.4 Discussions and conclusions

Chapter 15 Conclusions

15.1 Conclusions

Index

Back Cover

Part III Data Application.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

0-443-28954-9

OCLC:

1543207862