Random Forest-Based Approach for Maximum Power Point Tracking of Photovoltaic Systems Operating under Actual Environmental Conditions

Hussain Shareef, Ammar Hussein Mutlag, Azah Mohamed

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Many maximum power point tracking (MPPT) algorithms have been developed in recent years to maximize the produced PV energy. These algorithms are not sufficiently robust because of fast-changing environmental conditions, efficiency, accuracy at steady-state value, and dynamics of the tracking algorithm. Thus, this paper proposes a new random forest (RF) model to improve MPPT performance. The RF model has the ability to capture the nonlinear association of patterns between predictors, such as irradiance and temperature, to determine accurate maximum power point. A RF-based tracker is designed for 25 SolarTIFSTF-120P6 PV modules, with the capacity of 3 kW peak using two high-speed sensors. For this purpose, a complete PV system is modeled using 300,000 data samples and simulated using the MATLAB/SIMULINK package. The proposed RF-based MPPT is then tested under actual environmental conditions for 24 days to validate the accuracy and dynamic response. The response of the RF-based MPPT model is also compared with that of the artificial neural network and adaptive neurofuzzy inference system algorithms for further validation. The results show that the proposed MPPT technique gives significant improvement compared with that of other techniques. In addition, the RF model passes the Bland-Altman test, with more than 95 percent acceptability.

Original languageEnglish
Article number1673864
JournalComputational Intelligence and Neuroscience
Volume2017
DOIs
Publication statusPublished - 2017

Fingerprint

Photovoltaic System
Random Forest
MATLAB
Dynamic response
Adaptive Neuro-fuzzy Inference System
Irradiance
Matlab/Simulink
Neural networks
Dynamic Response
Model
Percent
Temperature
Artificial Neural Network
Predictors
Sensors
High Speed
Maximise
Forests
Module
Sensor

ASJC Scopus subject areas

  • Neuroscience(all)
  • Computer Science(all)
  • Mathematics(all)

Cite this

Random Forest-Based Approach for Maximum Power Point Tracking of Photovoltaic Systems Operating under Actual Environmental Conditions. / Shareef, Hussain; Mutlag, Ammar Hussein; Mohamed, Azah.

In: Computational Intelligence and Neuroscience, Vol. 2017, 1673864, 2017.

Research output: Contribution to journalArticle

@article{d9bbd7deefcc4e6596b2bd938ca74da8,
title = "Random Forest-Based Approach for Maximum Power Point Tracking of Photovoltaic Systems Operating under Actual Environmental Conditions",
abstract = "Many maximum power point tracking (MPPT) algorithms have been developed in recent years to maximize the produced PV energy. These algorithms are not sufficiently robust because of fast-changing environmental conditions, efficiency, accuracy at steady-state value, and dynamics of the tracking algorithm. Thus, this paper proposes a new random forest (RF) model to improve MPPT performance. The RF model has the ability to capture the nonlinear association of patterns between predictors, such as irradiance and temperature, to determine accurate maximum power point. A RF-based tracker is designed for 25 SolarTIFSTF-120P6 PV modules, with the capacity of 3 kW peak using two high-speed sensors. For this purpose, a complete PV system is modeled using 300,000 data samples and simulated using the MATLAB/SIMULINK package. The proposed RF-based MPPT is then tested under actual environmental conditions for 24 days to validate the accuracy and dynamic response. The response of the RF-based MPPT model is also compared with that of the artificial neural network and adaptive neurofuzzy inference system algorithms for further validation. The results show that the proposed MPPT technique gives significant improvement compared with that of other techniques. In addition, the RF model passes the Bland-Altman test, with more than 95 percent acceptability.",
author = "Hussain Shareef and Mutlag, {Ammar Hussein} and Azah Mohamed",
year = "2017",
doi = "10.1155/2017/1673864",
language = "English",
volume = "2017",
journal = "Computational Intelligence and Neuroscience",
issn = "1687-5265",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Random Forest-Based Approach for Maximum Power Point Tracking of Photovoltaic Systems Operating under Actual Environmental Conditions

AU - Shareef, Hussain

AU - Mutlag, Ammar Hussein

AU - Mohamed, Azah

PY - 2017

Y1 - 2017

N2 - Many maximum power point tracking (MPPT) algorithms have been developed in recent years to maximize the produced PV energy. These algorithms are not sufficiently robust because of fast-changing environmental conditions, efficiency, accuracy at steady-state value, and dynamics of the tracking algorithm. Thus, this paper proposes a new random forest (RF) model to improve MPPT performance. The RF model has the ability to capture the nonlinear association of patterns between predictors, such as irradiance and temperature, to determine accurate maximum power point. A RF-based tracker is designed for 25 SolarTIFSTF-120P6 PV modules, with the capacity of 3 kW peak using two high-speed sensors. For this purpose, a complete PV system is modeled using 300,000 data samples and simulated using the MATLAB/SIMULINK package. The proposed RF-based MPPT is then tested under actual environmental conditions for 24 days to validate the accuracy and dynamic response. The response of the RF-based MPPT model is also compared with that of the artificial neural network and adaptive neurofuzzy inference system algorithms for further validation. The results show that the proposed MPPT technique gives significant improvement compared with that of other techniques. In addition, the RF model passes the Bland-Altman test, with more than 95 percent acceptability.

AB - Many maximum power point tracking (MPPT) algorithms have been developed in recent years to maximize the produced PV energy. These algorithms are not sufficiently robust because of fast-changing environmental conditions, efficiency, accuracy at steady-state value, and dynamics of the tracking algorithm. Thus, this paper proposes a new random forest (RF) model to improve MPPT performance. The RF model has the ability to capture the nonlinear association of patterns between predictors, such as irradiance and temperature, to determine accurate maximum power point. A RF-based tracker is designed for 25 SolarTIFSTF-120P6 PV modules, with the capacity of 3 kW peak using two high-speed sensors. For this purpose, a complete PV system is modeled using 300,000 data samples and simulated using the MATLAB/SIMULINK package. The proposed RF-based MPPT is then tested under actual environmental conditions for 24 days to validate the accuracy and dynamic response. The response of the RF-based MPPT model is also compared with that of the artificial neural network and adaptive neurofuzzy inference system algorithms for further validation. The results show that the proposed MPPT technique gives significant improvement compared with that of other techniques. In addition, the RF model passes the Bland-Altman test, with more than 95 percent acceptability.

UR - http://www.scopus.com/inward/record.url?scp=85021625440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021625440&partnerID=8YFLogxK

U2 - 10.1155/2017/1673864

DO - 10.1155/2017/1673864

M3 - Article

C2 - 28702051

AN - SCOPUS:85021625440

VL - 2017

JO - Computational Intelligence and Neuroscience

JF - Computational Intelligence and Neuroscience

SN - 1687-5265

M1 - 1673864

ER -