Forecasting I-V characteristic of PV modules considering real operating conditions using numerical method and deep learning

Nguyen Duc Tuyen, Le Viet Thinh, Vu Xuan Son Huu, Goro Fujita

研究成果: Conference contribution

抄録

The current-voltage (I-V) characteristic plays a dominant role in operating a photovoltaic (PV) system as it provides information about the performance of the system. Since the output quality of PV depends mainly on the solar irradiation and cell temperature, modeling the I-V relationship regarding solar irradiation and cell temperature need to be addressed. In this paper, the long short-term memory (LSTM) model is adopted to forecast the solar irradiation and temperature of a PV module. After that, a PV module model called one-diode model is introduced to identify the I-V characteristic of the PV module, which only employs the data forecasted by the LSTM-based model and the manufactured data. Since this method combines the strengths of two techniques, it solves the uncertainty of meteorological data as well as provides an effective method to model the I-V output quality of the PV module.

本文言語English
ホスト出版物のタイトルProceedings - 2020 International Conference on Smart Grids and Energy Systems, SGES 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ544-549
ページ数6
ISBN(電子版)9781728185507
DOI
出版ステータスPublished - 2020 11
イベント2020 International Conference on Smart Grids and Energy Systems, SGES 2020 - Virtual, Perth, Australia
継続期間: 2020 11 232020 11 26

出版物シリーズ

名前Proceedings - 2020 International Conference on Smart Grids and Energy Systems, SGES 2020

Conference

Conference2020 International Conference on Smart Grids and Energy Systems, SGES 2020
CountryAustralia
CityVirtual, Perth
Period20/11/2320/11/26

ASJC Scopus subject areas

  • Artificial Intelligence
  • Energy Engineering and Power Technology
  • Automotive Engineering
  • Electrical and Electronic Engineering
  • Control and Optimization
  • Transportation

フィンガープリント 「Forecasting I-V characteristic of PV modules considering real operating conditions using numerical method and deep learning」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル