A novel estimation approach for the solar radiation potential with its complex spatial pattern via machine-learning techniques

Choongwan Koo, Wenzhuo Li, Seung Hyun Cha, Shaojie Zhang

Research output: Contribution to journalArticleResearchpeer-review

Abstract

As a clean and sustainable energy resource with lower environmental impact, the Chinese government encourages the application of solar energy system. The global solar radiation on the horizontal surface in the specific site should be investigated in advance so that the solar energy system could be implemented properly and efficiently. However, the monthly average daily solar radiation (MADSR) in China has complex spatial patterns, and its observation stations are still lacking due to the high cost of equipment. To address these challenges, this study aimed to develop a novel estimation approach for the MADSR with its complex spatial pattern over a vast area in China via machine-learning techniques (i.e. a clustering method (k-means) and an advanced case-based reasoning (A-CBR) model). The MADSR and the relevant information were collected from 97 cities in China for 10 years (from 2006 to 2015). The average prediction accuracy of the proposed approach was determined at 93.23%, showing a promising way. The proposed novel approach is expected to be generalized via the interpolation methods (e.g. kriging method in a geographical information system) so that decision-makers (e.g. construction manager or facility manager) can determine the appropriate location, size and form in implementing the solar energy system.

Original languageEnglish
Pages (from-to)575-592
Number of pages18
JournalRenewable Energy
Volume133
DOIs
StatePublished - 2019 Apr 1

Fingerprint

Solar radiation
Learning systems
Solar energy
Managers
Case based reasoning
Energy resources
Environmental impact
Interpolation
Information systems
Costs

Keywords

  • Advanced case-based reasoning
  • Decision-making
  • Monthly average daily solar radiation
  • Prediction accuracy
  • Solar radiation zone
  • k-means clustering

Cite this

@article{f3446c46c4fc47b5938dc2bf513ce0c1,
title = "A novel estimation approach for the solar radiation potential with its complex spatial pattern via machine-learning techniques",
abstract = "As a clean and sustainable energy resource with lower environmental impact, the Chinese government encourages the application of solar energy system. The global solar radiation on the horizontal surface in the specific site should be investigated in advance so that the solar energy system could be implemented properly and efficiently. However, the monthly average daily solar radiation (MADSR) in China has complex spatial patterns, and its observation stations are still lacking due to the high cost of equipment. To address these challenges, this study aimed to develop a novel estimation approach for the MADSR with its complex spatial pattern over a vast area in China via machine-learning techniques (i.e. a clustering method (k-means) and an advanced case-based reasoning (A-CBR) model). The MADSR and the relevant information were collected from 97 cities in China for 10 years (from 2006 to 2015). The average prediction accuracy of the proposed approach was determined at 93.23{\%}, showing a promising way. The proposed novel approach is expected to be generalized via the interpolation methods (e.g. kriging method in a geographical information system) so that decision-makers (e.g. construction manager or facility manager) can determine the appropriate location, size and form in implementing the solar energy system.",
keywords = "Advanced case-based reasoning, Decision-making, Monthly average daily solar radiation, Prediction accuracy, Solar radiation zone, k-means clustering",
author = "Choongwan Koo and Wenzhuo Li and Cha, {Seung Hyun} and Shaojie Zhang",
year = "2019",
month = "4",
day = "1",
doi = "10.1016/j.renene.2018.10.066",
language = "English",
volume = "133",
pages = "575--592",
journal = "Renewable Energy",
issn = "0960-1481",

}

A novel estimation approach for the solar radiation potential with its complex spatial pattern via machine-learning techniques. / Koo, Choongwan; Li, Wenzhuo; Cha, Seung Hyun; Zhang, Shaojie.

In: Renewable Energy, Vol. 133, 01.04.2019, p. 575-592.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A novel estimation approach for the solar radiation potential with its complex spatial pattern via machine-learning techniques

AU - Koo, Choongwan

AU - Li, Wenzhuo

AU - Cha, Seung Hyun

AU - Zhang, Shaojie

PY - 2019/4/1

Y1 - 2019/4/1

N2 - As a clean and sustainable energy resource with lower environmental impact, the Chinese government encourages the application of solar energy system. The global solar radiation on the horizontal surface in the specific site should be investigated in advance so that the solar energy system could be implemented properly and efficiently. However, the monthly average daily solar radiation (MADSR) in China has complex spatial patterns, and its observation stations are still lacking due to the high cost of equipment. To address these challenges, this study aimed to develop a novel estimation approach for the MADSR with its complex spatial pattern over a vast area in China via machine-learning techniques (i.e. a clustering method (k-means) and an advanced case-based reasoning (A-CBR) model). The MADSR and the relevant information were collected from 97 cities in China for 10 years (from 2006 to 2015). The average prediction accuracy of the proposed approach was determined at 93.23%, showing a promising way. The proposed novel approach is expected to be generalized via the interpolation methods (e.g. kriging method in a geographical information system) so that decision-makers (e.g. construction manager or facility manager) can determine the appropriate location, size and form in implementing the solar energy system.

AB - As a clean and sustainable energy resource with lower environmental impact, the Chinese government encourages the application of solar energy system. The global solar radiation on the horizontal surface in the specific site should be investigated in advance so that the solar energy system could be implemented properly and efficiently. However, the monthly average daily solar radiation (MADSR) in China has complex spatial patterns, and its observation stations are still lacking due to the high cost of equipment. To address these challenges, this study aimed to develop a novel estimation approach for the MADSR with its complex spatial pattern over a vast area in China via machine-learning techniques (i.e. a clustering method (k-means) and an advanced case-based reasoning (A-CBR) model). The MADSR and the relevant information were collected from 97 cities in China for 10 years (from 2006 to 2015). The average prediction accuracy of the proposed approach was determined at 93.23%, showing a promising way. The proposed novel approach is expected to be generalized via the interpolation methods (e.g. kriging method in a geographical information system) so that decision-makers (e.g. construction manager or facility manager) can determine the appropriate location, size and form in implementing the solar energy system.

KW - Advanced case-based reasoning

KW - Decision-making

KW - Monthly average daily solar radiation

KW - Prediction accuracy

KW - Solar radiation zone

KW - k-means clustering

UR - http://www.scopus.com/inward/record.url?scp=85056208205&partnerID=8YFLogxK

U2 - 10.1016/j.renene.2018.10.066

DO - 10.1016/j.renene.2018.10.066

M3 - Article

VL - 133

SP - 575

EP - 592

JO - Renewable Energy

JF - Renewable Energy

SN - 0960-1481

ER -