A Hybrid Clustering and Neural Network-based Ensemble Method for Day-Ahead PV Output Forecast

被引：1

作者：

Tseng, Y. C. ^{[1
]}

Chiu, C. L. ^{[1
]}

Huang, W. Y. ^{[1
]}

Chang, G. W. ^{[1
]}

机构：

[1] Natl Chung Cheng Univ, Dept Elect Engn, Chiayi, Taiwan

来源：

2024 IEEE TEXAS POWER AND ENERGY CONFERENCE, TPEC | 2024年

关键词：

Solar PV; deep learning; clustering technique; ensemble method;

D O I：

10.1109/TPEC60005.2024.10472241

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

With the increasing demand for green energy, solar photovoltaic (PV) has become as a major source of electricity production. However, the high penetration of solar PV in the power grid poses challenges due to variations in electric power generation, making accurate PV output forecasting crucial for effective system operation. This paper proposes a hybrid method for day-ahead PV output forecasting based on historical data from an actual PV power plant. The study employs different weather clustering techniques and deep learning models. The forecast results of these models are then combined using an ensemble method. Results show that the proposed model improves accuracy across various weather conditions, and the method is suitable for day-ahead PV output forecasting.

引用

页码：150 / 155

页数：6

共 13 条

[1]

Al-Hajj R, 2019, INT CONF RENEW ENERG, P428, DOI [10.1109/icrera47325.2019.8996629, 10.1109/ICRERA47325.2019.8996629]

[2] Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models [J].

Benmouiza, Khalil ;

Cheknane, Ali .

ENERGY CONVERSION AND MANAGEMENT, 2013, 75 :561-569

[3]

Cho KYHY, 2014, Arxiv, DOI arXiv:1406.1078

[4]

da Silva Fonseca J. G., 2011, 2011 37th IEEE Photovoltaic Specialists Conference (PVSC 2011), P002579, DOI 10.1109/PVSC.2011.6186475

[5] Unsupervised Clustering-Based Short-Term Solar Forecasting [J].

Feng, Cong ;

Cui, Mingjian ;

Hodge, Bri-Mathias ;

Lu, Siyuan ;

Hamann, Hendrik F. ;

Zhang, Jie .

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, 2019, 10 (04) :2174-2185

[6]

Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.8.1735, 10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]

[7]

Kushwaha V, 2017, 2017 7TH INTERNATIONAL CONFERENCE ON POWER SYSTEMS (ICPS), P430, DOI 10.1109/ICPES.2017.8387332

[8] A Review of Classification Problems and Algorithms in Renewable Energy Applications [J].

Perez-Ortiz, Maria ;

Jimenez-Fernandez, Silvia ;

Gutierrez, Pedro A. ;

Alexandre, Enrique ;

Hervas-Martinez, Cesar ;

Salcedo-Sanz, Sancho .

ENERGIES, 2016, 9 (08)

[9]

Raza MQ, 2017, IEEE POW ENER SOC GE

[10] Data Analysis to Generate Models Based on Neural Network and Regression for Solar Power Generation Forecasting [J].

Verma, Tushar ;

Tiwana, A. P. S. ;

Reddy, C. C. ;

Arora, Vikas ;

Devanand, P. .

2016 7TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS, MODELLING AND SIMULATION (ISMS), 2016, :97-100

← 1 2 →