Search

[Display omitted] • Easy-to-use machine learning model for hourly renewable production and load profile modeling. • Novel variance-correction method to improve the reliability of the modeled profiles. • Probabilistic energy supply simulation based on 42 years of meteorological data. • Detailed evaluation and novel categorization of Dunkelflaute events. • Uncertainty analysis of the share of photovoltaic, wind and nuclear electricity. The increasing penetration of weather-dependent renewable energy generation calls for high-resolution modeling of the possible future energy mixes to support the energy strategy and policy decisions. Simulations relying on the data of only a few years, however, are not only unreliable but also unable to quantify the uncertainty resulting from the year-to-year variability of the weather conditions. This paper presents a new method based on artificial neural networks that map the relationship between the weather data from atmospheric reanalysis and the photovoltaic and wind power generation and the electric load. The regression models are trained based on the data of the last 3 to 6 years, and then they are used to generate synthetic hourly renewable power production and load profiles for 42 years as an ensemble representation of possible outcomes in the future. The modeled profiles are post-processed by a novel variance-correction method that ensures the statistical similarity of the modeled and real data and thus the reliability of the simulation based on these profiles. The probabilistic modeling enabled by the proposed approach is demonstrated in two practical applications for the Hungarian electricity system. First, the so-called Dunkelflaute (dark doldrum) events, are analyzed and categorized. The results reveal that Dunkelflaute events most frequently happen on summer nights, and their typical duration is less than 12 h, even though events ranging through multiple days are also possible. Second, the renewable energy supply is modeled for different photovoltaic and wind turbine installed capacities. Based on our calculations, the share of the annual power consumption that weather-dependent renewable generation can directly cover is up to 60% in Hungary, even with very high installed capacities and overproduction, and higher carbon-free electricity share targets can only be achieved with an energy mix containing nuclear power and renewable sources. The proposed method can easily be extended to other countries and used in more detailed electricity market simulations in the future. [ABSTRACT FROM AUTHOR]

Irradiance-to-power conversion is an essential step of state-of-the-art photovoltaic (PV) power forecasting, regardless of the source and post-processing of irradiance forecasts. The two distinct approaches for mapping the irradiance forecasts to PV power are physical and data-driven, which can also be hybridized. The contribution of this paper is twofold; first, it proposes a concept and identifies the best implementation of a hybrid physical and machine learning irradiance-to-power conversion method. Second, a head-to-head comparison of the physical, data-driven, and hybrid methods is performed for the operational day-ahead power forecasting of 14 PV plants in Hungary based on numerical weather prediction (NWP). To respect the rule of consistency but still obtain as complete picture as possible, two directives are set, namely minimizing the mean absolute error (MAE) and minimizing the root mean square error (RMSE), and separate sets of forecasts are optimized for both directives. The results reveal that for two years of training data, the hybrid method that involves the most physically-calculated predictors can reduce the MAE by 5.2% and 10.4% compared, respectively, to the optimized physical model chains and the machine learning without any physical considerations. The two most important physical modeling steps are separation and transposition modeling, and the rest of the physical PV simulation can be left to machine learning in hybrid models without a significant increase in the errors. The optimization of the physical model chains is found to be important even in the case of hybrid modeling; therefore, it should become a standard procedure in practical applications. Finally, the hybrid method is only beneficial for at least one year of training data, while in the initial period of the operation of a PV plant, it is advised to stay with optimized physical modeling. The guidelines and recommendations of this paper can help both researchers and practitioners design and optimize their power conversion model to increase the accuracy of the PV power forecasts. • New concept for hybrid physical and machine learning irradiance-to-power conversion. • Comparison of physical, data-driven, and hybrid approaches for two directives. • Physical global tilted irradiance calculation is sufficient in hybrid modeling. • Optimization of physical model chains is important even in hybrid models. • The recommended method depends on the length of the available training data. [ABSTRACT FROM AUTHOR]

The increase of the worldwide installed photovoltaic (PV) capacity and the intermittent nature of the solar resource highlights the importance of power forecasting for the grid integration of the technology. This study compares 24 machine learning models for deterministic day-ahead power forecasting based on numerical weather predictions (NWP), tested for two-year-long 15-min resolution datasets of 16 PV plants in Hungary. The effects of the predictor selection and the benefits of the hyperparameter tuning are also evaluated. The results show that the two most accurate models are kernel ridge regression and multilayer perceptron with an up to 44.6% forecast skill score over persistence. Supplementing the basic NWP data with Sun position angles and statistically processed irradiance values as the inputs of the learning models results in a 13.1% decrease of the root mean square error (RMSE), which underlines the importance of the predictor selection. The hyperparameter tuning is essential to exploit the full potential of the models, especially for the less robust models, which are prone to under or overfitting without proper tuning. The overall best forecasts have a 13.9% lower RMSE compared to the baseline scenario of using linear regression. Moreover, the power forecasts based on only daily average irradiance forecasts and the Sun position angles have only a 1.5% higher RMSE than the best scenario, which demonstrates the effectiveness of machine learning even for limited data availability. The results of this paper can support both researchers and practitioners in constructing the best data-driven techniques for NWP-based PV power forecasting. • 24 machine learning models tested for day-ahead photovoltaic power forecasting. • Kernel ridge and multilayer perceptron are the overall most accurate models. • Predictor selection is even more important than model selection. • Hyperparameter optimization is essential for the highest accuracy. • Up to 13.9% RMSE improvement over a baseline linear regression model. [ABSTRACT FROM AUTHOR]