Eliminating Meteorological Dependencies in Solar Power Forecasting: A Deep Learning Solution With NeuralProphet and Real-World Data

Forecasting solar power generation is essential for efficient energy management and grid stability. However, existing predictive models often rely on external datasets, such as meteorological and sensor data, to make accurate predictions. This dependency introduces complexities and limits their appl...

Full description

Saved in:
Bibliographic Details
Main Authors: Necati Aksoy, Alper Yilmaz, Gokay Bayrak, Mehmet Koc
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11015433/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850175141784322048
author Necati Aksoy
Alper Yilmaz
Gokay Bayrak
Mehmet Koc
author_facet Necati Aksoy
Alper Yilmaz
Gokay Bayrak
Mehmet Koc
author_sort Necati Aksoy
collection DOAJ
description Forecasting solar power generation is essential for efficient energy management and grid stability. However, existing predictive models often rely on external datasets, such as meteorological and sensor data, to make accurate predictions. This dependency introduces complexities and limits their application in data-sparse scenarios. In this study, we propose a novel forecasting approach based on the NeuralProphet algorithm, a deep learning model that predicts solar power generation solely from its historical data, eliminating reliance on additional input data. To evaluate the proposed approach, we conducted two case studies. The first utilized a 10-month dataset from a 1.2 kW small-scale solar power unit at Bursa Technical University’s Smart Grids laboratory, recorded at 15-minute intervals. Despite the limited dataset, the model achieved an R-squared value exceeding 0.74, demonstrating promising predictive capability. The second case study applied the NeuralProphet-based model to a large-scale dataset of nationwide solar power generation in Germany, spanning five years and collected at 15-minute intervals. Models trained on this dataset achieved R-squared values exceeding 0.99, highlighting the algorithm’s capacity to effectively capture seasonal and temporal patterns at a national scale. Our results indicate that the NeuralProphet-based forecasting approach offers a viable and efficient alternative for solar power prediction, achieving high accuracy without external data dependencies.
format Article
id doaj-art-5e3f941db6c5431598cc00fbc9552ea8
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5e3f941db6c5431598cc00fbc9552ea82025-08-20T02:19:31ZengIEEEIEEE Access2169-35362025-01-0113932879330110.1109/ACCESS.2025.357344311015433Eliminating Meteorological Dependencies in Solar Power Forecasting: A Deep Learning Solution With NeuralProphet and Real-World DataNecati Aksoy0https://orcid.org/0000-0003-1496-2916Alper Yilmaz1https://orcid.org/0000-0003-3736-3668Gokay Bayrak2https://orcid.org/0000-0002-5136-0829Mehmet Koc3https://orcid.org/0000-0001-9665-6650Department of Electrical and Electronics Engineering, Renewable Energy Systems and Smart Grids Laboratory, Bursa Technical University, Bursa, TürkiyeDepartment of Electrical and Electronics Engineering, Renewable Energy Systems and Smart Grids Laboratory, Bursa Technical University, Bursa, TürkiyeDepartment of Electrical and Electronics Engineering, Renewable Energy Systems and Smart Grids Laboratory, Bursa Technical University, Bursa, TürkiyeUludağ Elektrik Dağıtım A.Ş. (UEDAŞ), Bursa, TürkiyeForecasting solar power generation is essential for efficient energy management and grid stability. However, existing predictive models often rely on external datasets, such as meteorological and sensor data, to make accurate predictions. This dependency introduces complexities and limits their application in data-sparse scenarios. In this study, we propose a novel forecasting approach based on the NeuralProphet algorithm, a deep learning model that predicts solar power generation solely from its historical data, eliminating reliance on additional input data. To evaluate the proposed approach, we conducted two case studies. The first utilized a 10-month dataset from a 1.2 kW small-scale solar power unit at Bursa Technical University’s Smart Grids laboratory, recorded at 15-minute intervals. Despite the limited dataset, the model achieved an R-squared value exceeding 0.74, demonstrating promising predictive capability. The second case study applied the NeuralProphet-based model to a large-scale dataset of nationwide solar power generation in Germany, spanning five years and collected at 15-minute intervals. Models trained on this dataset achieved R-squared values exceeding 0.99, highlighting the algorithm’s capacity to effectively capture seasonal and temporal patterns at a national scale. Our results indicate that the NeuralProphet-based forecasting approach offers a viable and efficient alternative for solar power prediction, achieving high accuracy without external data dependencies.https://ieeexplore.ieee.org/document/11015433/Deep learningNeuralProphetpredictive modelsrenewable energysolar power forecasting
spellingShingle Necati Aksoy
Alper Yilmaz
Gokay Bayrak
Mehmet Koc
Eliminating Meteorological Dependencies in Solar Power Forecasting: A Deep Learning Solution With NeuralProphet and Real-World Data
IEEE Access
Deep learning
NeuralProphet
predictive models
renewable energy
solar power forecasting
title Eliminating Meteorological Dependencies in Solar Power Forecasting: A Deep Learning Solution With NeuralProphet and Real-World Data
title_full Eliminating Meteorological Dependencies in Solar Power Forecasting: A Deep Learning Solution With NeuralProphet and Real-World Data
title_fullStr Eliminating Meteorological Dependencies in Solar Power Forecasting: A Deep Learning Solution With NeuralProphet and Real-World Data
title_full_unstemmed Eliminating Meteorological Dependencies in Solar Power Forecasting: A Deep Learning Solution With NeuralProphet and Real-World Data
title_short Eliminating Meteorological Dependencies in Solar Power Forecasting: A Deep Learning Solution With NeuralProphet and Real-World Data
title_sort eliminating meteorological dependencies in solar power forecasting a deep learning solution with neuralprophet and real world data
topic Deep learning
NeuralProphet
predictive models
renewable energy
solar power forecasting
url https://ieeexplore.ieee.org/document/11015433/
work_keys_str_mv AT necatiaksoy eliminatingmeteorologicaldependenciesinsolarpowerforecastingadeeplearningsolutionwithneuralprophetandrealworlddata
AT alperyilmaz eliminatingmeteorologicaldependenciesinsolarpowerforecastingadeeplearningsolutionwithneuralprophetandrealworlddata
AT gokaybayrak eliminatingmeteorologicaldependenciesinsolarpowerforecastingadeeplearningsolutionwithneuralprophetandrealworlddata
AT mehmetkoc eliminatingmeteorologicaldependenciesinsolarpowerforecastingadeeplearningsolutionwithneuralprophetandrealworlddata