Photovoltaics (PV) System Energy Forecast on the Basis of the Local Weather Forecast: Problems, Uncertainties and Solutions

Brecl, Kristijan; Topič, Marko

doi:10.3390/en11051143

Cited by 25 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Brecl and Topic () proposed an approach that uses only common weather forecasts, without solar irradiance information, obtaining satisfactory results.…”

Section: Related Workmentioning

confidence: 99%

Big data solar power forecasting based on deep learning and multiple data sources

et al. 2019

View full text Add to dashboard Cite

In this paper, we consider the task of predicting the electricity power generated by photovoltaic solar systems for the next day at half‐hourly intervals. We introduce DL, a deep learning approach based on feed‐forward neural networks for big data time series, which decomposes the forecasting problem into several sub‐problems. We conduct a comprehensive evaluation using 2 years of Australian solar data, evaluating accuracy and training time, and comparing the performance of DL with two other advanced methods based on neural networks and pattern sequence similarity. We investigate the use of multiple data sources (solar power and weather data for the previous days, and weather forecast for the next day) and also study the effect of different historical window sizes. The results show that DL produces competitive accuracy results and scales well, and is thus a highly suitable method for big data environments.

show abstract

“…Brecl and Topic () proposed an approach that uses only common weather forecasts, without solar irradiance information, obtaining satisfactory results.…”

Section: Related Workmentioning

confidence: 99%

Big data solar power forecasting based on deep learning and multiple data sources

et al. 2019

View full text Add to dashboard Cite

show abstract

“…[19]) assume perfectly forecasted demands and do not capture stochastic properties of their parameters [10,11,45]. Examples for varying parameters include solar power [60] and wind power [61] that both depend on weather conditions. In contrast, the TEMOA model can address these uncertainties due to its design for using stochastic programming and having the possibility to generate near-optimal solutions.…”

Section: Limitations Of a Deterministic Uncertainty Analysismentioning

confidence: 99%

OSeMOSYS-PuLP: A Stochastic Modeling Framework for Long-Term Energy Systems Modeling

Dreier¹,

Howells²

2019

Energies

View full text Add to dashboard Cite

Recent open-data movements give access to large datasets derived from real-world observations. This data can be utilized to enhance energy systems modeling in terms of heterogeneity, confidence, and transparency. Furthermore, it allows to shift away from the common practice of considering average values towards probability distributions. In turn, heterogeneity and randomness of the real-world can be captured that are usually found in large samples of real-world data. This paper presents a methodological framework for an empirical deterministic–stochastic modeling approach to utilize large real-world datasets in long-term energy systems modeling. A new software system—OSeMOSYS-PuLP—was developed and is available now.It adds the feature of Monte Carlo simulations to the existing open-source energy modeling system (the OSeMOSYS modeling framework). An application example is given, in which the initial application example of OSeMOSYS is used and modified to include real-world operation data from a public bus transport system.

show abstract

“…Accurate forecasting requires information about expected solar irradiance, which is not readily available. Therefore, Brecl and Topič [17] developed a method based on only weather forecast data, and solar irradiance was simulated based on discrete weather class values. The simple approach led to a root-mean-square error of measured and forecasted power data of 65%, while the correlation in terms of R 2 was high at 0.85.…”

Section: Design and Integration Issuesmentioning

confidence: 99%

Photovoltaic System Design and Performance

Sark

2019

Energies

View full text Add to dashboard Cite

This editorial summarizes the collection of papers in the Special Issue entitled Photovoltaic System Design and Performance, which was published in MDPI’s Energies journal. Papers on this topic were submitted in 2017 and 2018, and a total of 21 papers were published. Main topics included data analysis for optimal performance and fault analysis, causes for energy loss, and design and integration issues. The papers in this Special Issue demonstrate the importance of designing and properly monitoring photovoltaic systems in the field in order to ensure maintaining good performance.

show abstract

Photovoltaics (PV) System Energy Forecast on the Basis of the Local Weather Forecast: Problems, Uncertainties and Solutions

Cited by 25 publications

References 23 publications

Big data solar power forecasting based on deep learning and multiple data sources

Big data solar power forecasting based on deep learning and multiple data sources

OSeMOSYS-PuLP: A Stochastic Modeling Framework for Long-Term Energy Systems Modeling

Photovoltaic System Design and Performance

Contact Info

Product

Resources

About