<p>In this study, we present a deep learning-based method to provide short-range point-forecasts (1-2 days ahead) of the 10-meter wind speed for complex terrain. Gridded data with different horizontal resolutions from numeric weather prediction (NWP) models, gridded observations, and point data are used. An artificial neural network (ANN), able to process several differently structured inputs simultaneously, is developed.<br>The heterogeneous structure of inputs is targeted by the ANN by combining convolutional, long-short-term-memory (LSTM), fully connected (FC) layers, and others within a common network. Convolutional layers efficiently solve image processing tasks, however, they are applicable to any gridded data source. An LSTM layer models recurrent steps in the ANN and is, thus, useful for time-series, such as meteorological observations. Further key objectives of this research are to consider different spatial and temporal resolutions and different topographic characteristics of the selected sites.</p><p>Data from the Austrian TAWES system (Teilautomatische Wetterstationen, meteorological observations in 10-minute intervals), INCA's (Integrated Nowcasting through Comprehensive Analysis) gridded observation fields, and NWP data from the ECMWF IFS (European Center for Medium-Range Weather Forecast&#8217;s Integrated Forecasting System) model are used in this study. Hourly runs for 12 test locations (selected TAWES sites representing different topographic &#160;characteristics in Austria) and different seasons are conducted.<br>&#160;<br>The ANN&#8217;s results yield, in general, high forecast-skills (MAE=1.13 m/s, RMSE=1.72 m/s), indicating a successful learning based on the used training data. Different combinations of the number of input field grid points were investigated centering around the target sites. It is shown that a small number of ECMWF IFS grid Points (e.g.: 5x5 grid points) and a higher number of INCA grid points (e.g.: 15x15) resulted in the best performing forecasts. The different number of grid points is directly related to the models' resolution. However, keeping the nowcasting-range in mind, it is shown that adding NWP data does not increase the model performance. Thus, for nowcasting a stronger weighting towards the observations is important. Beyond the nowcasting range, the deep learning-based ANN model outperforms the more basic machine learning algorithms as well as other alternative models.</p>
<p>In this study, we address point-forecasting using a deep learning LSTM-approach for renewable energy systems with focus on the short- to medium-range. Hourly resolution (medium-range) as well as 10-minute resolution (nowcasting) are the anticipated forecasting frequency. The forecasting approach is applied to: (i) wind speed at 10 meters height (observation sites), (ii) wind speed at hub-height of wind turbines, and (iii) solar power forecasts for selected solar power plants.</p><p>As input to the proposed method numerical weather prediction (NWP) data, gridded observations (analysis and/or reanalysis), and point data are used. The data of studied test-cases is extracted from the Austrian TAWES system (Teilautomatische Wetterstationen, meteorological observations in 10-minute intervals), &#160;SCADA data of wind farms, solar power output of a solar power plant, INCA's (Integrated Nowcasting through Comprehensive Analysis) gridded observation fields, reanalysis fields from Merra2 and Era5-land, as well as, NWP data from the ECMWF IFS (European Center for Medium-Range Weather Forecast&#8217;s Integrated Forecasting System). These data-sources embrace very different temporal and spatial semantics, thus, careful pre-processing was carried out. Four daily runs over the course of one year for 12 synoptic sites + 38 wind turbines + 1 solar power plant test locations are conducted.</p><p>The advantage of an LSTM architecture is that it includes recurrent steps in the ANN and, thus, is useful especially for time-series, such as meteorological observations or NWP forecasts. So far, comparatively few attempts have been made to integrate time-series with different semantics of a sensor network and physical models in one LSTM. We tackle this issue by conserving the time-steps of the delayed NWP along with their difference to recently observed time-series and, additionally, separate them into forecasting-intervals (e.g., of 3 to 12 subsequent forecasting hours being shortest in nowcasting). This enables us to employ a sequence-to-sequence LSTM based artificial neural network (ANN). The benefit of a sequence-to-sequence setup is to match an input- and output time-series in each sample, thereby, learning complex temporal relationships. To fully use the advantage of the diverse data a tailored pre- and post-processing of these heterogenous data sources in the renewable energy applications is needed.</p><p>The ANN&#8217;s results yield, in general, high forecast-skills, indicating a successful learning based on the used training data. Different combinations of inputs and processing-steps were investigated. It is shown that combining various data sources and implement an adequate pre- and post-processing yields the most promising results in the case studies (e.g.: a heuristic to estimate produced power based on the meteorological parameters and prediction of the offset to NWPs tailored to the studied location). Results are compared to traditional forecast methods and statistical methods such as a random forest and multiple-linear-regression.</p>
<p>Fostering solar power as a sustainable, as fossil fuel free as possible, energy source demands accurate, location-optimized, and highly resolved forecasts of power production. For this study, we consider the issue of production offsets due to Sahara dust events in large areas of Central Europe as well as data coverage and inconsistency issues with evolving solar power sites. In the presented case study we investigate subhourly nowcasts using machine learning for (i) specific solar power plants in Central Europe (ii) the suitability of synthetically generated production using NWP grid points in the studied areas. &#160;<br>Deep learning enables us to consider complex timeseries from historic data to model highly variable (spatial, temporal) diurnal and seasonal changes in the expected power production. In particular, we investigate how to exploit the spatio-temporal relationships in highly resolved forecasts by a sequence-to-sequence encoder-decoder inspired LSTM (long short-term memory) artificial neural network. We optimize the performance of our deep learning approach by tuning hyper-parameters, network weighting, and loss as well as addressing the input feature selection accordingly. Our preprocessing steps transform available data into a suitable representation for learning efficiently from a combination of multiple, very heterogeneous data sources with varying temporal availability and spatial resolution. For instance, we utilize 3D-fields from other weather prediction models, satellite data and remote sensing products, and observation time-series as well as their generated climatologies. A key objective is to properly process the differing temporal and spatial resolution while still generating nowcasts efficiently. To extend the historic training data set of complex models, we generate synthetic solar production data using machine learning and consider climatological driven data transformation. We investigate transfer learning as a further option in our deep learning setup.<br>Results obtained by the developed method generally yield high forecast-skills, where the best model setups are shown in our analysis. We compare the forecast results of up to 6 hours ahead obtained through this machine learning approach to available forecast methods, e.g., forecasts generated with python pvlib driven with AROME.</p>
<p>With the transition towards an increased use of renewable energy system, especially in solar energy, accurate predictions are essential to maintain and secure grid stability; grid feed-in scheduling of PV production as well as in intra-day and day-ahead trading. To provide forecasts in the nowcasting and intra-day range a combination of different heterogeneous data sources such as satellite data, observations, power productions, and numerical weather prediction data is needed.</p><p>In this study, a graph neural network model (GNN) with adapted loss function is evaluated against more &#8220;classical&#8221; deep learning and statistical approaches such as a ConvLSTM architecture for nowcasting and intra-day prediction of PV production. Besides the GNN and the ConvLSTM a baseline forecast using an observation-based analog method is implemented. The analog method includes a Euclidean distance measure and dimensionality reduction to include not only temporal analogs but also spatial analogs surrounding the target site. For selected sites, which are included in the NWP domain, a simple NWP to PV forecast is used as baesline using the Python library PVLIB. The target region for the models is a belt in Central Europe stretching from Luxembourg to Austria with PV sites in different altitude and climatic regions. Heterogeneous data sources with varying temporal availability and spatial resolution are used as inputData pre-processing and careful feature selection are needed to not overfit the different methods.</p><p>Results show that the graph neural network is able to outperform the standard and baseline methods as well as the other two methods for most of the selected cases.</p>
<p>Wind gusts and high wind speeds need to be considered in wind power industry and power grid management as they affect construction, material, siting and maintenance of turbines and power lines. Furthermore, gusts are an important information source on turbulence conditions in the atmosphere at the respective sites.<br />Often, the wind farm operators only provide basic data of the turbines such as average wind speed, direction, power and temperature. However, they require forecasts of gusts, too. Thus, a simple gust estimation algorithm based on the average wind speed was developed. The algorithm is tested at different mast measurement sites and WFIP2 data and applied to selected wind turbines. Results show that the algorithm is skillful enough to be used as a first guess gust estimation for single turbines and is, thus, used for nowcasting.<br />For nowcasting for the first two hours with a temporal fequency of ten minutes solely observations are used. A high-frequency wind speed and gust nowcasting ensemble based on different machine learning methodologies, including an ensemble for every method, was developd. Used are boosting, random forest, linear regression, a simple monte carlo method and a feed forward neural network. Results show that perturbing the observations provides a good forecasting spread for at least some of the methods. However, for other methods the spread is reduced significantly. Most of the used methods are able to provide good forecastst. However, hyperparameter tuning for the lightGBM boosting algorithm and the neural network is still needed.</p>
<p>The amount of wind farms and wind power production in Europe, both on- and off-shore, increased rapidly in the past years. To ensure grid stability, on-time (re)scheduling of maintenance tasks and mitigate fees in energy trading, accurate predictions of wind speed and wind power are needed. It has become particularly important to improve wind speed predictions in the short range of one to six hours as wind speed variability in this range has been found to pose the largest operational challenges. Furthermore, accurate predictions of extreme wind events are of high importance to wind farm operators as timely knowledge of these can both prevent damages and offer economic preparedness. We propose in this work a deep convolutional recurrent neural network (RNN) based regression model for the spatio-temporal prediction of extreme wind speed events over Europe in the short-to-medium range (12 hour lead-time in 1 hour intervals). This is achieved by training a multi-layered convolutional long short-term memory (ConvLSTM) network with imbalanced regression loss, to which end we investigate three different loss functions: the inversely weighted mean absolute error (W-MAE) loss, the inversely weighted mean squared error (W-MSE) loss and the squared error-relevance area (SERA) loss.&#160;</p><p>The results indicate superior performance of the SERA loss, showing significant improvements on high intensity extreme events. The W-MAE and W-MSE shows no improvements over the standard MSE loss and we thus discourage the usage of the inverse weighting method. We conclude that the SERA loss provides an effective way to adapt deep learning to the task of imbalanced spatio-temporal regression and&#160;its application to the forecasting of extreme wind events in the short-to-medium range.&#160;</p><p>&#160;This work was performed as a part of the MEDEA project, which is funded by the Austrian Climate Research Program to further research on renewable energy and meteorologically induced extreme events.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.