Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System
In the context of smart grids, the need for forecasts of the power output of small-scale photovoltaic (PV) arrays increases as control processes such as the management of flexibilities in the distribution grid gain importance. However, there is often only very little knowledge about the PV systems i...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-05-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2021.639346/full |
| _version_ | 1818729339594735616 |
|---|---|
| author | Moritz Stüber Felix Scherhag Matthieu Deru Alassane Ndiaye Muhammad Moiz Sakha Boris Brandherm Jörg Baus Georg Frey |
| author_facet | Moritz Stüber Felix Scherhag Matthieu Deru Alassane Ndiaye Muhammad Moiz Sakha Boris Brandherm Jörg Baus Georg Frey |
| author_sort | Moritz Stüber |
| collection | DOAJ |
| description | In the context of smart grids, the need for forecasts of the power output of small-scale photovoltaic (PV) arrays increases as control processes such as the management of flexibilities in the distribution grid gain importance. However, there is often only very little knowledge about the PV systems installed: even fundamental system parameters such as panel orientation, the number of panels and their type, or time series data of past PV system performance are usually unknown to the grid operator. In the past, only forecasting models that attempted to account for cause-and-effect chains existed; nowadays, also data-driven methods that attempt to recognize patterns in past behavior are available. Choosing between physics-based or data-driven forecast methods requires knowledge about the typical forecast quality as well as the requirements that each approach entails. In this contribution, the achieved forecast quality for a typical scenario (day-ahead, based on numerical weather predictions [NWP]) is evaluated for one physics-based as well as five different data-driven forecast methods for a year at the same site in south-western Germany. Namely, feed-forward neural networks (FFNN), long short-term memory (LSTM) networks, random forest, bagging and boosting are investigated. Additionally, the forecast quality of the weather forecast is analyzed for key quantities. All evaluated PV forecast methods showed comparable performance; based on concise descriptions of the forecast approaches, advantages and disadvantages of each are discussed. The approaches are viable even though the forecasts regularly differ significantly from the observed behavior; the residual analysis performed offers a qualitative insight into the achievable forecast quality in a typical real-world scenario. |
| first_indexed | 2024-12-17T22:44:19Z |
| format | Article |
| id | doaj.art-8d11761fa07c44b6a3ee05d43e023338 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-12-17T22:44:19Z |
| publishDate | 2021-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-8d11761fa07c44b6a3ee05d43e0233382022-12-21T21:29:49ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2021-05-01910.3389/fenrg.2021.639346639346Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV SystemMoritz Stüber0Felix Scherhag1Matthieu Deru2Alassane Ndiaye3Muhammad Moiz Sakha4Boris Brandherm5Jörg Baus6Georg Frey7Chair of Automation and Energy Systems, Saarland University, Saarbrücken, GermanyChair of Automation and Energy Systems, Saarland University, Saarbrücken, GermanyGerman Research Center for Artificial Intelligence (DFKI), Saarbrücken, GermanyGerman Research Center for Artificial Intelligence (DFKI), Saarbrücken, GermanyGerman Research Center for Artificial Intelligence (DFKI), Saarbrücken, GermanyGerman Research Center for Artificial Intelligence (DFKI), Saarbrücken, GermanyGerman Research Center for Artificial Intelligence (DFKI), Saarbrücken, GermanyChair of Automation and Energy Systems, Saarland University, Saarbrücken, GermanyIn the context of smart grids, the need for forecasts of the power output of small-scale photovoltaic (PV) arrays increases as control processes such as the management of flexibilities in the distribution grid gain importance. However, there is often only very little knowledge about the PV systems installed: even fundamental system parameters such as panel orientation, the number of panels and their type, or time series data of past PV system performance are usually unknown to the grid operator. In the past, only forecasting models that attempted to account for cause-and-effect chains existed; nowadays, also data-driven methods that attempt to recognize patterns in past behavior are available. Choosing between physics-based or data-driven forecast methods requires knowledge about the typical forecast quality as well as the requirements that each approach entails. In this contribution, the achieved forecast quality for a typical scenario (day-ahead, based on numerical weather predictions [NWP]) is evaluated for one physics-based as well as five different data-driven forecast methods for a year at the same site in south-western Germany. Namely, feed-forward neural networks (FFNN), long short-term memory (LSTM) networks, random forest, bagging and boosting are investigated. Additionally, the forecast quality of the weather forecast is analyzed for key quantities. All evaluated PV forecast methods showed comparable performance; based on concise descriptions of the forecast approaches, advantages and disadvantages of each are discussed. The approaches are viable even though the forecasts regularly differ significantly from the observed behavior; the residual analysis performed offers a qualitative insight into the achievable forecast quality in a typical real-world scenario.https://www.frontiersin.org/articles/10.3389/fenrg.2021.639346/fullPV forecastingforecast qualitynumerical weather predictionsmart gridPV modelingmachine learning |
| spellingShingle | Moritz Stüber Felix Scherhag Matthieu Deru Alassane Ndiaye Muhammad Moiz Sakha Boris Brandherm Jörg Baus Georg Frey Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System Frontiers in Energy Research PV forecasting forecast quality numerical weather prediction smart grid PV modeling machine learning |
| title | Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System |
| title_full | Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System |
| title_fullStr | Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System |
| title_full_unstemmed | Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System |
| title_short | Forecast Quality of Physics-Based and Data-Driven PV Performance Models for a Small-Scale PV System |
| title_sort | forecast quality of physics based and data driven pv performance models for a small scale pv system |
| topic | PV forecasting forecast quality numerical weather prediction smart grid PV modeling machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2021.639346/full |
| work_keys_str_mv | AT moritzstuber forecastqualityofphysicsbasedanddatadrivenpvperformancemodelsforasmallscalepvsystem AT felixscherhag forecastqualityofphysicsbasedanddatadrivenpvperformancemodelsforasmallscalepvsystem AT matthieuderu forecastqualityofphysicsbasedanddatadrivenpvperformancemodelsforasmallscalepvsystem AT alassanendiaye forecastqualityofphysicsbasedanddatadrivenpvperformancemodelsforasmallscalepvsystem AT muhammadmoizsakha forecastqualityofphysicsbasedanddatadrivenpvperformancemodelsforasmallscalepvsystem AT borisbrandherm forecastqualityofphysicsbasedanddatadrivenpvperformancemodelsforasmallscalepvsystem AT jorgbaus forecastqualityofphysicsbasedanddatadrivenpvperformancemodelsforasmallscalepvsystem AT georgfrey forecastqualityofphysicsbasedanddatadrivenpvperformancemodelsforasmallscalepvsystem |