Forecasting of Power Quality Parameters Based on Meteorological Data in Small-Scale Household Off-Grid Systems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F22%3A10250123" target="_blank" >RIV/61989100:27240/22:10250123 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27730/22:10250123

Výsledek na webu

<a href="https://doi.org/10.3390/en15145251" target="_blank" >https://doi.org/10.3390/en15145251</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/en15145251" target="_blank" >10.3390/en15145251</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Forecasting of Power Quality Parameters Based on Meteorological Data in Small-Scale Household Off-Grid Systems

Popis výsledku v původním jazyce

Off-grid power systems are often used to supply electricity to remote households, cottages, or small industries, comprising small renewable energy systems, typically a photovoltaic plant whose energy supply is stochastic in nature, without electricity distributions. This approach is economically viable and conforms to the requirements of the European Green Deal and the Fit for 55 package. Furthermore, these systems are associated with a lower short circuit power as compared with distribution grid traditional power plants. The power quality parameters (PQPs) of such small-scale off-grid systems are largely determined by the inverter&apos;s ability to handle the impact of a device; however, this makes it difficult to accurately forecast the PQPs. To address this issue, this work compared prediction models for the PQPs as a function of the meteorological conditions regarding the off-grid systems for small-scale households in Central Europe. To this end, seven models-the artificial neural network (ANN), linear regression (LR), interaction linear regression (ILR), quadratic linear regression (QLR), pure quadratic linear regression (PQLR), the bagging decision tree (DT), and the boosting DT-were considered for forecasting four PQPs: frequency, the amplitude of the voltage, total harmonic distortion of the voltage (THDu), and current (THDi). The computation times of these forecasting models and their accuracies were also compared. Each forecasting model was used to forecast the PQPs for three sunny days in August. As a result of the study, the most accurate methods for forecasting are DTs. The ANN requires the longest computational time, and conversely, the LR takes the shortest computational time. Notably, this work aimed to predict poor PQPs that could cause all the equipment in off-grid systems to respond in advance to disturbances. This study is expected to be beneficial for the off-grid systems of small households and the substations included in existing smart grids.

Název v anglickém jazyce

Forecasting of Power Quality Parameters Based on Meteorological Data in Small-Scale Household Off-Grid Systems

Popis výsledku anglicky

Off-grid power systems are often used to supply electricity to remote households, cottages, or small industries, comprising small renewable energy systems, typically a photovoltaic plant whose energy supply is stochastic in nature, without electricity distributions. This approach is economically viable and conforms to the requirements of the European Green Deal and the Fit for 55 package. Furthermore, these systems are associated with a lower short circuit power as compared with distribution grid traditional power plants. The power quality parameters (PQPs) of such small-scale off-grid systems are largely determined by the inverter&apos;s ability to handle the impact of a device; however, this makes it difficult to accurately forecast the PQPs. To address this issue, this work compared prediction models for the PQPs as a function of the meteorological conditions regarding the off-grid systems for small-scale households in Central Europe. To this end, seven models-the artificial neural network (ANN), linear regression (LR), interaction linear regression (ILR), quadratic linear regression (QLR), pure quadratic linear regression (PQLR), the bagging decision tree (DT), and the boosting DT-were considered for forecasting four PQPs: frequency, the amplitude of the voltage, total harmonic distortion of the voltage (THDu), and current (THDi). The computation times of these forecasting models and their accuracies were also compared. Each forecasting model was used to forecast the PQPs for three sunny days in August. As a result of the study, the most accurate methods for forecasting are DTs. The ANN requires the longest computational time, and conversely, the LR takes the shortest computational time. Notably, this work aimed to predict poor PQPs that could cause all the equipment in off-grid systems to respond in advance to disturbances. This study is expected to be beneficial for the off-grid systems of small households and the substations included in existing smart grids.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20200 - Electrical engineering, Electronic engineering, Information engineering

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Energies

ISSN

1996-1073

e-ISSN

1996-1073

Svazek periodika

15

Číslo periodika v rámci svazku

14

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

20

Strana od-do

nestrankovano

Kód UT WoS článku

000833243800001

EID výsledku v databázi Scopus

2-s2.0-85136266668