izpis_h1_title_alt

Advanced PV performance modelling based on different levels of irradiance data accuracy
ID Ascencio Vásquez, Julián Andrés (Avtor), ID Bevc, Jakob (Avtor), ID Reba, Kristjan (Avtor), ID Brecl, Kristijan (Avtor), ID Jankovec, Marko (Avtor), ID Topič, Marko (Avtor)

.pdfPDF - Predstavitvena datoteka, prenos (5,05 MB)
MD5: 7CDDD952F09441E31D2E6A95483D5F67
URLURL - Izvorni URL, za dostop obiščite https://www.mdpi.com/1996-1073/13/9/2166/ Povezava se odpre v novem oknu

Izvleček
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.

Jezik:Angleški jezik
Ključne besede:PV performance modelling, data filtering, PV systems, machine learning, lightGBM
Vrsta gradiva:Članek v reviji (dk_c)
Tipologija:1.01 - Izvirni znanstveni članek
Organizacija:FE - Fakulteta za elektrotehniko
FRI - Fakulteta za računalništvo in informatiko
Leto izida:2020
Status objave pri reviji:Objavljeno
Verzija članka:Založnikova različica članka
Št. strani:12 str.
Številčenje:Vol. 13, iss. 9, art. 2166
PID:20.500.12556/RUL-115985 Povezava se odpre v novem oknu
UDK:621.383.51
ISSN pri članku:1996-1073
DOI:10.3390/en13092166 Povezava se odpre v novem oknu
COBISS.SI-ID:13529091 Povezava se odpre v novem oknu
Datum objave v RUL:05.05.2020
Število ogledov:620
Število prenosov:376
Metapodatki:XML RDF-CHPDL DC-XML DC-RDF
:
Kopiraj citat
Objavi na:AddThis
AddThis uporablja piškotke, za katere potrebujemo vaše privoljenje.
Uredi privoljenje...

Gradivo je del revije

Naslov:Energies
Skrajšan naslov:Energies
Založnik:Molecular Diversity Preservation International
ISSN:1996-1073
COBISS.SI-ID:518046745 Povezava se odpre v novem oknu

Licence

Licenca:CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
Povezava:http://creativecommons.org/licenses/by/4.0/deed.sl
Opis:To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.
Začetek licenciranja:01.05.2020

Sekundarni jezik

Jezik:Slovenski jezik
Ključne besede:modeliranje učinkovitosti PV, filtriranje podatkov, PV sistemi, strojno učenje, lightGMB

Projekti

Financer:EC - European Commission
Program financ.:H2020
Številka projekta:721452
Naslov:Photovoltaic module life time forecast and evaluation
Akronim:SOLAR-TRAIN

Financer:ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
Številka projekta:P2-0197
Naslov:Fotovoltaika in elektronika

Podobna dela

Podobna dela v RUL:
Podobna dela v drugih slovenskih zbirkah:

Nazaj