Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction

Markovics, Dávid; Mayer, Martin János

doi:10.1016/j.rser.2022.112364

Cited by 202 publications

(55 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, ML is used to regress renewable energy output and load demand, depending on the day and time. The utilization of ML is preferred over regular fitting techniques due to the low accuracy results of fitting techniques, in the presence of uncertainties and highly fluctuating data [26]. After that, using the energy output and load data, ML coordinates the use of backup sources, such as diesel and auxiliary loads, and finds the most appropriate power of each component to optimize the performance of the HPPs.…”

Section: ML Modelmentioning

confidence: 99%

An Intelligent Two-Stage Energy Dispatch Management System for Hybrid Power Plants: Impact of Machine Learning Deployment

2023

View full text Add to dashboard Cite

Section: ML Modelmentioning

confidence: 99%

An Intelligent Two-Stage Energy Dispatch Management System for Hybrid Power Plants: Impact of Machine Learning Deployment

2023

View full text Add to dashboard Cite

“…• Occurrences of global minima and stagnation issues [3][4][5][6][7] • Scalability problems on the normalization procedures adopted [2,8,[12][13][14][15][16][17] • Over-fitting and under-fitting issues [5, 6, 9-11, 23, 48, 51] • Dimensionality constraints of the solar farm data and data handling issues [18][19][20][21][22][23][24] • Elapsed training time [29,31,37] • Data extraction problems in regression based ML models [10][11][12][13][14][15] • Higher number of trainable parameters in DL models [1, 14, 19-20, 26, 27, 43, 47] • Repetitive training of deep neural networks [19,20,26,27] • High computational overhead due to repetitive process [29][30][31][32][33][34][35][36] • Few predictor models with high complexity and data redundancy [45][46][47]…”

Section: Challengesmentioning

confidence: 99%

“…Table 1 details the installed megawatt capacity of solar farms and their percentage contribution of solar power across the globe. The need and importance of power generation from solar source is well lucid considering the abundance sun natural source and difficulty in handling of other forms of energy production [1][2][3]. Due to which, each and every country takes immense steps in building high potential solar farms and thereby to increase the rate of renewable source of power production from their country.…”

Section: Introductionmentioning

confidence: 99%

Variational mode decomposition combined fuzzy—Twin support vector machine model with deep learning for solar photovoltaic power forecasting

et al. 2022

View full text Add to dashboard Cite

A novel Variational Mode Decomposition (VMD) combined Fuzzy-Twin Support Vector Machine Model with deep learning mechanism is devised in this research study to forecast the solar Photovoltaic (PV) output power in day ahead basis. The raw data from the solar PV farms are highly fluctuating and to extract the useful stable components VMD is employed. A novel Fuzzy–Twin Support Vector Machine (FTSVM) model developed acts as the forecasting model for predicting the solar PV output power for the considered solar farms. The twin support vector machine (SVM) model formulates two separating hyperplanes for predicting the output power and in this research study a fuzzy based membership function identifies most suitable two SVM prediction hyperplanes handling the uncertainties of solar farm data. For the developed, new VMD-FTSVM prediction technique, their optimal parameters for the training process are evaluated with the classic Ant Lion Optimizer (ALO) algorithm. The solar PV output power is predicted using the novel VMD-FTSVM model and during the process multi-kernel functions are utilized to devise the two fuzzy based hyperplanes that accurately performs the prediction operation. Deep learning (DL) based training of the FTSVM model is adopted so that the deep auto-encoder and decoder module enhances the accuracy rate. The proposed combined forecasting model, VMD-ALO-DLFTSVM is validated for superiority based on a two 250MW PV solar farm in India. Results prove that the proposed model outperforms the existing model in terms of the performance metrics evaluated and the forecasted PV Power.

show abstract

“…Because of that, this approach was extensively evaluated during the past decade [14,15,19]. Nevertheless, the reliability is far from optimal and machine-learning methods play an important role in providing enhanced solar forecasts derived from NWPs models [20,21]. In this context, the inputs for machine learning techniques are forecasts of several meteorological variables provided by numerical weather prediction (NWP) physical models such as the European Center for Medium Weather Forecasts (ECMWF) and the Global Ensemble Forecast System (GEFS).…”

Section: Introductionmentioning

confidence: 99%

A combination of supervised dimensionality reduction and learning methods to forecast solar radiation

et al. 2022

View full text Add to dashboard Cite

Machine learning is routinely used to forecast solar radiation from inputs, which are forecasts of meteorological variables provided by numerical weather prediction (NWP) models, on a spatially distributed grid. However, the number of features resulting from these grids is usually large, especially if several vertical levels are included. Principal Components Analysis (PCA) is one of the simplest and most widely-used methods to extract features and reduce dimensionality in renewable energy forecasting, although this method has some limitations. First, it performs a global linear analysis, and second it is an unsupervised method. Locality Preserving Projection (LPP) overcomes the locality problem, and recently the Linear Optimal Low-Rank (LOL) method has extended Linear Discriminant Analysis (LDA) to be applicable when the number of features is larger than the number of samples. Supervised Nonnegative Matrix Factorization (SNMF) also achieves this goal extending the Nonnegative Matrix Factorization (NMF) framework to integrate the logistic regression loss function. In this article we try to overcome all these issues together by proposing a Supervised Local Maximum Variance Preserving (SLMVP) method, a supervised non-linear method for feature extraction and dimensionality reduction. PCA, LPP, LOL, SNMF and SLMVP have been compared on Global Horizontal Irradiance (GHI) and Direct Normal Irradiance (DNI) radiation data at two different Iberian locations: Seville and Lisbon. Results show that for both kinds of radiation (GHI and DNI) and the two locations, SLMVP produces smaller MAE errors than PCA, LPP, LOL, and SNMF, around 4.92% better for Seville and 3.12% for Lisbon. It has also been shown that, although SLMVP, PCA, and LPP benefit from using a non-linear regression method (Gradient Boosting in this work), this benefit is larger for PCA and LPP because SMLVP is able to perform non-linear transformations of inputs.

show abstract

Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction

Cited by 202 publications

References 55 publications

An Intelligent Two-Stage Energy Dispatch Management System for Hybrid Power Plants: Impact of Machine Learning Deployment

An Intelligent Two-Stage Energy Dispatch Management System for Hybrid Power Plants: Impact of Machine Learning Deployment

Variational mode decomposition combined fuzzy—Twin support vector machine model with deep learning for solar photovoltaic power forecasting

A combination of supervised dimensionality reduction and learning methods to forecast solar radiation

Contact Info

Product

Resources

About