Open AccessDETERMINATION OF RESS GENERATION USING ARTIFICIAL NEURAL NETWORKS
Author(s) -
Olena Rubanenko,
Dmytro Danylchenko,
V. Teptya
Publication year - 2020
Publication title -
vestnik nacionalʹnogo tehničeskogo universiteta "hpi". ènergetika: nadežnostʹ i ènergoèffektivnostʹ
Language(s) - English
Resource type - Journals
ISSN - 2224-0349
DOI - 10.20998/2224-0349.2020.01.11
Subject(s) - photovoltaic system , renewable energy , artificial neural network , electricity generation , computer science , meteorology , environmental economics , wind power , environmental science , electricity , electrical engineering , power (physics) , engineering , artificial intelligence , geography , economics , physics , quantum mechanics
Paper considers the perspectives and potential of using renewable energy sources to decide the global warming problem. The World trend of increasing electricity generation by photovoltaic power stations according to the International Renewable Energy Agency and the trend of increasing the installed capacity of photovoltaic power stations in Ukraine, which supply the generated capacity at a "green" tariff according to the National Commission for State Regulation of Energy utilities of Ukraine. Opportunities and conditions of using artificial neural networks to defined the power generation of photovoltaic power stations on the example of the power plant "Tsekinivska-2" 4–5 turns are investigated. A platform developed by the European Commission – Photovoltaic Geographical Information System – was used to create a database for the creation and training of artificial neural networks. Regularities of change of meteorological satellite data and their influence on electricity generation of photovoltaic power stations are established. For this purpose, the software complex MATLAB was used, namely the module for the creation of artificial neural networks – Neural Networks Toolbox. The height of the sun is conditionally considered constant and its value is repeated from year to year or has a slight deviation, so it can be used as an indicator of the hour and can be considered known in advance, so determined by empirical formulas and changes only under certain astrophysical laws. Regarding the temperature at 2 m and the wind at 10 m, these meteorological data are known, as they are needed not only for forecasting the operation of renewable energy sources but also in agriculture. Therefore, data related to solar radiation are considered to be the most problematic, as this value is the most difficult to determine. Satellite data may have an error, the installation of weather stations, namely quality pyranometers is a costly procedure, but will help provide a training sample of quality data. To forecast with satisfactory accuracy, it is necessary to collect data for 1 year of operation of the weather station. The nntool and Anfis MATLAB modules were used to predict generation. But the obtained results can be used to assess the effectiveness of the photovoltaic power stations, but they are unsatisfactory for the operational balancing of the system.