Designing localized MPPT for PV systems using fuzzy-weighted extreme learning machine

Yang Du; Ke Yan; Zixiao Ren; Weidong Xiao

doi:10.3390/en11102615

Designing localized MPPT for PV systems using fuzzy-weighted extreme learning machine

Yang Du, Ke Yan^*, Zixiao Ren, Weidong Xiao

^*Corresponding author for this work

Department of Electrical and Electronic Engineering

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

48 Citations (Scopus)

Abstract

A maximum power point tracker (MPPT) should be designed to deal with various weather conditions, which are different from region to region. Customization is an important step for achieving the highest solar energy harvest. The latest development of modern machine learning provides the possibility to classify the weather types automatically and, consequently, assist localized MPPT design. In this study, a localized MPPT algorithm is developed, which is supported by a supervised weather-type classification system. Two classical machine learning technologies are employed and compared, namely, the support vector machine (SVM) and extreme learning machine (ELM). The simulation results show the outperformance of the proposed method in comparison with the traditional MPPT design.

Original language	English
Article number	2615
Journal	Energies
Volume	11
Issue number	10
DOIs	https://doi.org/10.3390/en11102615
Publication status	Published - Oct 2018

Keywords

Extreme learning machine
Maximum power point tracker
Solar irradiance classification system
Support vector machine

Access to Document

10.3390/en11102615

Cite this

@article{74a6bc331f1f4ff6a9fea5702ad5a1b8,

title = "Designing localized MPPT for PV systems using fuzzy-weighted extreme learning machine",

abstract = "A maximum power point tracker (MPPT) should be designed to deal with various weather conditions, which are different from region to region. Customization is an important step for achieving the highest solar energy harvest. The latest development of modern machine learning provides the possibility to classify the weather types automatically and, consequently, assist localized MPPT design. In this study, a localized MPPT algorithm is developed, which is supported by a supervised weather-type classification system. Two classical machine learning technologies are employed and compared, namely, the support vector machine (SVM) and extreme learning machine (ELM). The simulation results show the outperformance of the proposed method in comparison with the traditional MPPT design.",

keywords = "Extreme learning machine, Maximum power point tracker, Solar irradiance classification system, Support vector machine",

author = "Yang Du and Ke Yan and Zixiao Ren and Weidong Xiao",

note = "Publisher Copyright: {\textcopyright} 2018 by the authors.",

year = "2018",

month = oct,

doi = "10.3390/en11102615",

language = "English",

volume = "11",

journal = "Energies",

number = "10",

}

TY - JOUR

T1 - Designing localized MPPT for PV systems using fuzzy-weighted extreme learning machine

AU - Du, Yang

AU - Yan, Ke

AU - Ren, Zixiao

AU - Xiao, Weidong

PY - 2018/10

Y1 - 2018/10

N2 - A maximum power point tracker (MPPT) should be designed to deal with various weather conditions, which are different from region to region. Customization is an important step for achieving the highest solar energy harvest. The latest development of modern machine learning provides the possibility to classify the weather types automatically and, consequently, assist localized MPPT design. In this study, a localized MPPT algorithm is developed, which is supported by a supervised weather-type classification system. Two classical machine learning technologies are employed and compared, namely, the support vector machine (SVM) and extreme learning machine (ELM). The simulation results show the outperformance of the proposed method in comparison with the traditional MPPT design.

AB - A maximum power point tracker (MPPT) should be designed to deal with various weather conditions, which are different from region to region. Customization is an important step for achieving the highest solar energy harvest. The latest development of modern machine learning provides the possibility to classify the weather types automatically and, consequently, assist localized MPPT design. In this study, a localized MPPT algorithm is developed, which is supported by a supervised weather-type classification system. Two classical machine learning technologies are employed and compared, namely, the support vector machine (SVM) and extreme learning machine (ELM). The simulation results show the outperformance of the proposed method in comparison with the traditional MPPT design.

KW - Extreme learning machine

KW - Maximum power point tracker

KW - Solar irradiance classification system

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85056078534&partnerID=8YFLogxK

U2 - 10.3390/en11102615

DO - 10.3390/en11102615

M3 - Article

AN - SCOPUS:85056078534

VL - 11

JO - Energies

JF - Energies

IS - 10

M1 - 2615

ER -

Designing localized MPPT for PV systems using fuzzy-weighted extreme learning machine

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this