Optimization of ventilation system operation in office environment using POD model reduction and genetic algorithm

Optimization of ventilation system operation in office environment using POD model reduction and... 1 Introduction</h5> Various optimization strategies have grown in popularity in air conditioning systems due to increasing concerns about the indoor comfort and building energy consumption simultaneously. Most of these methods generally assume that the indoor air is “perfectly mixed” and all spatial parameters, including air temperature, air contaminant, predicted mean vote (PMV), etc., are lumped at uniform values [1–4] . For many kinds of air conditioning systems, especially for thermal displacement ventilation systems (TDVS), spatial influence of the indoor environment is important to take into consideration because of the fully stratified air distribution. Nevertheless, limited works has been done to integrate the indoor spatial parameters into the optimization procedure. One reason is that the high-resolution indoor environment is complex and usually obtained by CFD simulations, which are software-based and difficult to integrate into optimization procedure directly. Some researchers combine artificial neural network (ANN) technique with CFD to acquire surrogate models of indoor environment, which are further used for environmental optimizations [5,6] . After plenty of CFD-data training, the obtained ANN model is integrated into optimization loops for fast and high-resolution fitness evaluations. The average error of the network is reported about ±6% and the optimization procedure takes 5–10 http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Energy and Buildings Elsevier

Optimization of ventilation system operation in office environment using POD model reduction and genetic algorithm

Loading next page...
 
/lp/elsevier/optimization-of-ventilation-system-operation-in-office-environment-iVJP4SYzu3
Publisher
Elsevier
Copyright
Copyright © 2013 Elsevier B.V.
ISSN
0378-7788
eISSN
1872-6178
D.O.I.
10.1016/j.enbuild.2013.07.075
Publisher site
See Article on Publisher Site

Abstract

1 Introduction</h5> Various optimization strategies have grown in popularity in air conditioning systems due to increasing concerns about the indoor comfort and building energy consumption simultaneously. Most of these methods generally assume that the indoor air is “perfectly mixed” and all spatial parameters, including air temperature, air contaminant, predicted mean vote (PMV), etc., are lumped at uniform values [1–4] . For many kinds of air conditioning systems, especially for thermal displacement ventilation systems (TDVS), spatial influence of the indoor environment is important to take into consideration because of the fully stratified air distribution. Nevertheless, limited works has been done to integrate the indoor spatial parameters into the optimization procedure. One reason is that the high-resolution indoor environment is complex and usually obtained by CFD simulations, which are software-based and difficult to integrate into optimization procedure directly. Some researchers combine artificial neural network (ANN) technique with CFD to acquire surrogate models of indoor environment, which are further used for environmental optimizations [5,6] . After plenty of CFD-data training, the obtained ANN model is integrated into optimization loops for fast and high-resolution fitness evaluations. The average error of the network is reported about ±6% and the optimization procedure takes 5–10

Journal

Energy and BuildingsElsevier

Published: Dec 1, 2013

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off