Neural network metamodelling in multi-objective optimization of a high latitude solar community

Janne Hirvonen; Hassam Rehman; Kalyanmoy Deb; Kai Sirén

doi:10.1016/j.solener.2017.06.040

Neural network metamodelling in multi-objective optimization of a high latitude solar community

Janne Hirvonen^*, Hassam Rehman, Kalyanmoy Deb, Kai Sirén

^*Corresponding author for this work

Department of Energy and Mechanical Engineering

Michigan State University

Research output: Contribution to journal › Article › Scientific › peer-review

15 Citations (Scopus)

Abstract

A solar community of 100 residential houses was optimized for Finnish conditions with the aim of achieving a 90% solar fraction for both space heating and domestic hot water. Optimization was done using a novel method based on neural network metamodelling and compared to the standard NSGA-II genetic algorithm. Compared to NSGA-II, the new method obtained a larger hypervolume by finding better solutions both in the center and edge of the non-dominated front. The combined non-dominated front of both methods was better than either one separately. The performance target was achieved as the optimal solar community designs had heating solar fractions ranging from 64% to 95%.

Original language	English
Pages (from-to)	323-335
Number of pages	13
Journal	Solar Energy
Volume	155
DOIs	https://doi.org/10.1016/j.solener.2017.06.040
Publication status	Published - 1 Oct 2017
MoE publication type	A1 Journal article-refereed

Keywords

Neural network
Seasonal storage
Simulation-based optimization
Solar assisted heat pump
Solar community
Solar district heating

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.solener.2017.06.040

Cite this

@article{52d8dae4a8484f8e8cc84aa540b65dcd,

title = "Neural network metamodelling in multi-objective optimization of a high latitude solar community",

abstract = "A solar community of 100 residential houses was optimized for Finnish conditions with the aim of achieving a 90% solar fraction for both space heating and domestic hot water. Optimization was done using a novel method based on neural network metamodelling and compared to the standard NSGA-II genetic algorithm. Compared to NSGA-II, the new method obtained a larger hypervolume by finding better solutions both in the center and edge of the non-dominated front. The combined non-dominated front of both methods was better than either one separately. The performance target was achieved as the optimal solar community designs had heating solar fractions ranging from 64% to 95%.",

keywords = "Neural network, Seasonal storage, Simulation-based optimization, Solar assisted heat pump, Solar community, Solar district heating",

author = "Janne Hirvonen and Hassam Rehman and Kalyanmoy Deb and Kai Sir{\'e}n",

year = "2017",

month = oct,

day = "1",

doi = "10.1016/j.solener.2017.06.040",

language = "English",

volume = "155",

pages = "323--335",

journal = "Solar Energy ",

issn = "0038-092X",

publisher = "Elsevier",

}

TY - JOUR

T1 - Neural network metamodelling in multi-objective optimization of a high latitude solar community

AU - Hirvonen, Janne

AU - Rehman, Hassam

AU - Deb, Kalyanmoy

AU - Sirén, Kai

PY - 2017/10/1

Y1 - 2017/10/1

N2 - A solar community of 100 residential houses was optimized for Finnish conditions with the aim of achieving a 90% solar fraction for both space heating and domestic hot water. Optimization was done using a novel method based on neural network metamodelling and compared to the standard NSGA-II genetic algorithm. Compared to NSGA-II, the new method obtained a larger hypervolume by finding better solutions both in the center and edge of the non-dominated front. The combined non-dominated front of both methods was better than either one separately. The performance target was achieved as the optimal solar community designs had heating solar fractions ranging from 64% to 95%.

AB - A solar community of 100 residential houses was optimized for Finnish conditions with the aim of achieving a 90% solar fraction for both space heating and domestic hot water. Optimization was done using a novel method based on neural network metamodelling and compared to the standard NSGA-II genetic algorithm. Compared to NSGA-II, the new method obtained a larger hypervolume by finding better solutions both in the center and edge of the non-dominated front. The combined non-dominated front of both methods was better than either one separately. The performance target was achieved as the optimal solar community designs had heating solar fractions ranging from 64% to 95%.

KW - Neural network

KW - Seasonal storage

KW - Simulation-based optimization

KW - Solar assisted heat pump

KW - Solar community

KW - Solar district heating

UR - http://www.scopus.com/inward/record.url?scp=85021196828&partnerID=8YFLogxK

U2 - 10.1016/j.solener.2017.06.040

DO - 10.1016/j.solener.2017.06.040

M3 - Article

AN - SCOPUS:85021196828

SN - 0038-092X

VL - 155

SP - 323

EP - 335

JO - Solar Energy

JF - Solar Energy

ER -

Neural network metamodelling in multi-objective optimization of a high latitude solar community

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this