Energy Optimization and Prediction in Office Buildings

A Case Study of Office Building Design in Chile
1. Auflage 2018
ISBN: 978-3-319-90145-9
Verlag: Springer

Buch, Englisch, 78 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 1474 g

Reihe: SpringerBriefs in Energy

This book explains how energy demand and energy consumption in new buildings can be predicted and how these aspects and the resulting CO2 emissions can be reduced. It is based upon the authors’ extensive research into the design and energy optimization of office buildings in Chile.

The authors first introduce a calculation procedure that can be used for the optimization of energy parameters in office buildings, and to predict how a changing climate may affect energy demand. The prediction of energy demand, consumption and CO2 emissions is demonstrated by solving simple equations using the example of Chilean buildings, and the findings are subsequently applied to buildings around the globe.

An optimization process based on Artificial Neural Networks is discussed in detail, which predicts heating and cooling energy demands, energy consumption and CO2 emissions. Taken together, these processes will show readers how to reduce energy demand, consumption and CO2 emissions associated with office buildings in the future. Readers will gain an advanced understanding of energy use in buildings and how it can be reduced.

Zielgruppe

Research

Autoren/Hrsg.

Rubio-Bellido, Carlos

Pérez-Fargallo, Alexis

Pulido-Arcas, Jesús

Fachgebiete

• Geisteswissenschaften Architektur Ökologische Aspekte in der Architektur
• Mathematik | Informatik Mathematik Numerik und Wissenschaftliches Rechnen Angewandte Mathematik, Mathematische Modelle
• Technische Wissenschaften Energietechnik | Elektrotechnik Energieeffizienz
• Technische Wissenschaften Bauingenieurwesen Bauökologie, Baubiologie, Bauphysik, Bauchemie
• Geisteswissenschaften Architektur Gebäudetypen Öffentliche Gebäude, Gewerbliche Bauten
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Neuronale Netzwerke

Inhaltsverzeichnis

Introduction.- Research Method.- Energy Demand Analysis.- Multiple Linear Regressions.- Artificial Neural Networks.- Conclusions.

Über Autor(innen)

Carlos Rubio-Bellido is an assistant professor at the Department of Building Construction II at the University of Sevilla. His research focuses largely on energy efficiency, climate adaption and climate change in the building sector. 

Alexis Pérez-Fargallo is an assistant professor at the Department of Building Science at the University of Bío-Bío and is a specialist for energy demand, energy consumption and CO2 emissions in buildings that are in use. 

Jesús A. Pulido-Arcas is an assistant professor at the Department of Building Science at the University of Bío-Bío. He has published extensive research works concerning radiative transfer, statistical and environmental software in architecture.