Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing

Theocharides, Spyros; Makrides, George; Livera, Andreas; Theristis, Marios; Kaimakis, Paris; Georghiou, George E.

doi:10.1016/j.apenergy.2020.115023

Cited by 137 publications

(59 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More advanced methods, the so-called machine learning (ML) methods, can provide better results [29,30], however, in most cases they require more computational efforts. Some examples of machine learning methods used in PV power forecasting include [2,[29][30][31]: k-nearest neighbors (k-NN), artificial neural networks (ANN), support vector machine (SVM), random forests (RF) and light gradient boost machines (LightGBM). The basic description of these methods is presented below with the references for a detailed description.…”

Section: Statistical and Machine Learning Methodsmentioning

confidence: 99%

“…Using gradient-based optimization techniques, the ANNs learn a specific task (e.g., prediction) by the optimization of the "weights". This method is widely used in PV power forecasting [2] described in [29,34,35] • Support Vector Machine (SVM): The method separates the data linearly and transforms it into a higher dimensional feature space through a specific kernel function. The linear separation is performed with the so-called "hyperplanes".…”

Section: Statistical and Machine Learning Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Photovoltaic Power Forecasting Methods

Kaaya¹,

Ascencio‐Vásquez²

2022

Solar Radiation - Measurement, Modeling and Forecasting Techniques for Photovoltaic Solar Energy Applications

View full text Add to dashboard Cite

The rapid growth in grid penetration of photovoltaic (PV) calls for more accurate methods to forecast the performance and reliability of PV. Several methods have been proposed to forecast the PV power generation at different temporal horizons. In this chapter the different methods used in PV power forecasting are described with an example on their applications and related uncertainty. The methods discussed include physical, heuristic, statistical and machine learning methods. When benchmarked, it is shown that physical method showed the highest uncertainties compared to other methods. In the chapter, the effect of degradation on lifetime PV power and energy forecast is also assessed using linear and non-linear degradation scenarios. It is shown that the relative difference in lifetime yield prediction is over 5% between linear and non-linear scenarios.

show abstract

Section: Statistical and Machine Learning Methodsmentioning

confidence: 99%

Section: Statistical and Machine Learning Methodsmentioning

confidence: 99%

Photovoltaic Power Forecasting Methods

Kaaya¹,

Ascencio‐Vásquez²

2022

Solar Radiation - Measurement, Modeling and Forecasting Techniques for Photovoltaic Solar Energy Applications

View full text Add to dashboard Cite

show abstract

“…Moreover, following the discussion of other key factors that are essential for adequacy of forecast models, the authors concluded that hybridizing artificial neural networks and evolutionary algorithms is optimum. In addition, Theocharides et al [112] sought to improve the accuracy of day-ahead solar forecast, which led to proposition of a comprehensive model that combined machine learning (ANN) and post-processing linear regression correction methods that could enhance performance. The authors applied the proposed models to PV systems in hot as well as cold semi-arid regions, and results showed high forecasting accuracy and stability.…”

Section: Solar Energymentioning

confidence: 99%

Impacts of Renewable Energy Resources on Effectiveness of Grid-Integrated Systems: Succinct Review of Current Challenges and Potential Solution Strategies

et al. 2020

View full text Add to dashboard Cite

This study is aimed at a succinct review of practical impacts of grid integration of renewable energy systems on effectiveness of power networks, as well as often employed state-of-the-art solution strategies. The renewable energy resources focused on include solar energy, wind energy, biomass energy and geothermal energy, as well as renewable hydrogen/fuel cells, which, although not classified purely as renewable resources, are a famous energy carrier vital for future energy sustainability. Although several world energy outlooks have suggested that the renewable resources available worldwide are sufficient to satisfy global energy needs in multiples of thousands, the different challenges often associated with practical exploitation have made this assertion an illusion to date. Thus, more research efforts are required to synthesize the nature of these challenges as well as viable solution strategies, hence, the need for this review study. First, brief overviews are provided for each of the studied renewable energy sources. Next, challenges and solution strategies associated with each of them at generation phase are discussed, with reference to power grid integration. Thereafter, challenges and common solution strategies at the grid/electrical interface are discussed for each of the renewable resources. Finally, expert opinions are provided, comprising a number of aphorisms deducible from the review study, which reveal knowledge gaps in the field and potential roadmap for future research. In particular, these opinions include the essential roles that renewable hydrogen will play in future energy systems; the need for multi-sectoral coupling, specifically by promoting electric vehicle usage and integration with renewable-based power grids; the need for cheaper energy storage devices, attainable possibly by using abandoned electric vehicle batteries for electrical storage, and by further development of advanced thermal energy storage systems (overviews of state-of-the-art thermal and electrochemical energy storage are also provided); amongst others.

show abstract

“…With the rapid development of the global new energy power generation industry, solar energy has been widely used because of its some advantages of safety, efficiency, and wide distribution [1]- [3]. The process of PV power generation is random and unstable, which brings great challenges to the safe operation of power system [4]- [6]. So, the stability of power system operation relies on accurate short-term PV power prediction.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Photovoltaic Power Forecasting Based on VMD and ISSA-GRU

et al. 2021

View full text Add to dashboard Cite

Photovoltaic (PV) power generation is affected by many meteorological factors and environmental factors, which has obvious intermittent, random, and volatile characteristics. To improve the accuracy of short-term PV power prediction, a hybrid model (VMD-ISSA-GRU) based on variational mode decomposition (VMD), improved sparrow search algorithm (ISSA) and gated recurrent unit (GRU) is proposed. First of all, the PV time series is decomposed into a series of different subsequences by VMD to reduce the non-stationarity of the original data. Then, the main factors affecting PV power generation are obtained by using the correlation coefficients of Spearman and Pearson, which reduces the computational complexity of the model. Finally, the GRU network optimized by ISSA is used to predict all the subsequences and residual error of VMD, and the prediction results are reconstructed. The results show that the hybrid VMD-ISSA-GRU model has stronger adaptability and higher accuracy than other traditional models. The mean absolute error (MAE) in the whole test set is 1.0128 KW, the root mean square error (RMSE) is 1.5511 KW.INDEX TERMS short-term PV power forecast, variational mode decomposition, improved sparrow search algorithm, GRU neural network.

show abstract

Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing

Cited by 137 publications

References 44 publications

Photovoltaic Power Forecasting Methods

Photovoltaic Power Forecasting Methods

Impacts of Renewable Energy Resources on Effectiveness of Grid-Integrated Systems: Succinct Review of Current Challenges and Potential Solution Strategies

Short-Term Photovoltaic Power Forecasting Based on VMD and ISSA-GRU

Contact Info

Product

Resources

About