Please use this identifier to cite or link to this item: http://hdl.handle.net/10995/101382
Title: Industry experience of developing day-ahead photovoltaic plant forecasting system based on machine learning
Authors: Khalyasmaa, A. I.
Eroshenko, S. A.
Tashchilin, V. A.
Ramachandran, H.
Chakravarthi, T. P.
Butusov, D. N.
Issue Date: 2020
Publisher: MDPI AG
Citation: Industry experience of developing day-ahead photovoltaic plant forecasting system based on machine learning / A. I. Khalyasmaa, S. A. Eroshenko, V. A. Tashchilin, et al. — DOI 10.3390/rs12203420 // Remote Sensing. — 2020. — Vol. 12. — Iss. 20. — P. 1-21. — 3420.
Abstract: This article highlights the industry experience of the development and practical implementation of a short-term photovoltaic forecasting system based on machine learning methods for a real industry-scale photovoltaic power plant implemented in a Russian power system using remote data acquisition. One of the goals of the study is to improve photovoltaic power plants generation forecasting accuracy based on open-source meteorological data, which is provided in regular weather forecasts. In order to improve the robustness of the system in terms of the forecasting accuracy, we apply newly derived feature introduction, a factor obtained as a result of feature engineering procedure, characterizing the relationship between photovoltaic power plant energy production and solar irradiation on a horizontal surface, thus taking into account the impacts of atmospheric and electrical nature. The article scrutinizes the application of different machine learning algorithms, including Random Forest regressor, Gradient Boosting Regressor, Linear Regression and Decision Trees regression, to the remotely obtained data. As a result of the application of the aforementioned approaches together with hyperparameters, tuning and pipelining of the algorithms, the optimal structure, parameters and the application sphere of different regressors were identified for various testing samples. The mathematical model developed within the framework of the study gave us the opportunity to provide robust photovoltaic energy forecasting results with mean accuracy over 92% for mostly-sunny sample days and over 83% for mostly cloudy days with different types of precipitation. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.
Keywords: FEATURE ENGINEERING
FORECASTING
GRAPHICAL USER INTERFACE SOFTWARE
MACHINE LEARNING
PHOTOVOLTAIC POWER PLANT
ADAPTIVE BOOSTING
DATA ACQUISITION
DECISION TREES
ELECTRIC POWER PLANTS
MACHINE LEARNING
METEOROLOGY
PHOTOVOLTAIC CELLS
PROFESSIONAL ASPECTS
SOLAR POWER GENERATION
SOLAR POWER PLANTS
STRUCTURAL OPTIMIZATION
FEATURE ENGINEERINGS
FORECASTING ACCURACY
HORIZONTAL SURFACES
INDUSTRY EXPERIENCE
METEOROLOGICAL DATA
PHOTOVOLTAIC ENERGY
PHOTOVOLTAIC POWER PLANT
REMOTE DATA ACQUISITION
WEATHER FORECASTING
URI: http://hdl.handle.net/10995/101382
Access: info:eu-repo/semantics/openAccess
SCOPUS ID: 85092891728
PURE ID: 14159013
7005acea-fac9-4ab2-8095-1d329798c649
ISSN: 20724292
DOI: 10.3390/rs12203420
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
2-s2.0-85092891728.pdf4,62 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.