20.500.12556/RUL-115985 Advanced PV performance modelling based on different levels of irradiance data accuracy In photovoltaic (PV) systems, energy yield is one of the essential pieces of information to the stakeholders (grid operators, maintenance operators, financial units, etc.). The amount of energy produced by a photovoltaic system in a specific time period depends on the weather conditions, including snow and dust, the actual PV modules’ and inverters’ efficiency and balance-of-system losses. The energy yield can be estimated by using empirical models with accurate input data. However, most of the PV systems do not include on-site high-class measurement devices for irradiance and other weather conditions. For this reason, the use of reanalysis-based or satellite-based data is currently of significant interest in the PV community and combining the data with decomposition and transposition irradiance models, the actual Plane-of-Array operating conditions can be determined. In this paper, we are proposing an efficient and accurate approach for PV output energy modelling by combining a new data filtering procedure and fast machine learning algorithm Light Gradient Boosting Machine (LightGBM). The applicability of the procedure is presented on three levels of irradiance data accuracy (low, medium, and high) depending on the source or modelling used. A new filtering algorithm is proposed to exclude erroneous data due to system failures or unreal weather conditions (i.e., shading, partial snow coverage, reflections, soiling deposition, etc.). The cleaned data is then used to train three empirical models and three machine learning approaches, where we emphasize the advantages of the LightGBM. The experiments are carried out on a 17 kW roof-top PV system installed in Ljubljana, Slovenia, in a temperate climate zone. PV performance modelling data filtering PV systems machine learning lightGBM modeliranje učinkovitosti PV filtriranje podatkov PV sistemi strojno učenje lightGMB true false true Angleški jezik Slovenski jezik Članek v reviji 2020-05-05 10:49:01 2020-05-05 10:49:02 2022-08-28 03:46:39 0000-00-00 00:00:00 2020 0 0 12 str. iss. 9, art. 2166 Vol. 13 May 2020 0000-00-00 Zaloznikova Objavljeno apc 0000-00-00 0000-00-00 0000-00-00 621.383.51 1996-1073 10.3390/en13092166 13529091 518046745 RAZ_Ascencio-Vasquez_Julian_2020.pdf RAZ_Ascencio-Vasquez_Julian_2020.pdf 1 7CDDD952F09441E31D2E6A95483D5F67 189b66374efc9a7e9080b0de3c41760cf1df105b49c661492cf18d344ce286c4 830ceae0-4d34-11ec-abdb-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=151401 https://www.mdpi.com/1996-1073/13/9/2166/ 1 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=129371 Fakulteta za elektrotehniko Fakulteta za računalništvo in informatiko 0 0 0