The demand for minute-scale forecasts of wind power is continuously increasing with the growing penetration of renewable energy into the power grid, as grid operators need to ensure grid stability in the presence of variable power generation. For this reason, IEA Wind Tasks 32 and 36 together organized a workshop on “Very Short-Term Forecasting of Wind Power” in 2018 to discuss different approaches for the implementation of minute-scale forecasts into the power industry. IEA Wind is an international platform for the research community and industry. Task 32 tries to identify and mitigate barriers to the use of lidars in wind energy applications, while IEA Wind Task 36 focuses on improving the value of wind energy forecasts to the wind energy industry. The workshop identified three applications that need minute-scale forecasts: (1) wind turbine and wind farm control, (2) power grid balancing, (3) energy trading and ancillary services. The forecasting horizons for these applications range from around 1 s for turbine control to 60 min for energy market and grid control applications. The methods that can be applied to generate minute-scale forecasts rely on upstream data from remote sensing devices such as scanning lidars or radars, or are based on point measurements from met masts, turbines or profiling remote sensing devices. Upstream data needs to be propagated with advection models and point measurements can either be used in statistical time series models or assimilated into physical models. All methods have advantages but also shortcomings. The workshop’s main conclusions were that there is a need for further investigations into the minute-scale forecasting methods for different use cases, and a cross-disciplinary exchange of different method experts should be established. Additionally, more efforts should be directed towards enhancing quality and reliability of the input measurement data.

The inverse radiative transfer equation to retrieve atmospheric ozone distribution from the UV‐visible satellite spectrometer Global Ozone Monitoring Experiment (GOME) has been modeled by means of a feed forward neural network. This Neural Network Ozone Retrieval System (NNORSY) was trained exclusively on a data set of GOME radiances collocated with ozone measurements from ozonesondes, Halogen Occultation Experiment, Stratospheric Aerosol and Gas Experiment II, and Polar Ozone and Aerosol Measurement III. Network input consists of a combination of spectral, geolocation, and climatological information (time and latitude). In the stratosphere the method globally reduces standard deviation with respect to an ozone climatology by around 40%. Tropospheric ozone can also be retrieved in many cases with corresponding reduction of 10–30%. All GOME data from January 1996 to July 2001 were processed. In a number of case studies involving comparisons with ozonesondes from Hohenpeissenberg, Syowa, and results from the classical Full Retrieval Method, we found good agreement with our results. The neural network was found capable of implicitly correcting for instrument degradation, pixel cloudiness, and scan angle effects. Integrated profiles generally agree to within ±5% with the monthly Total Ozone Mapping Spectrometer version 7 total ozone field. However, some problems remain at high solar zenith angles and very low ozone values, where local deviations of 10–20% have been observed in some cases. In order to better characterize individual ozone profiles, two local error estimation methods are presented. Vertical resolution of the profiles was assessed empirically and seems to be of the order of 4–6 km. Since neural network retrieval is a mathematically simple, one‐step procedure, NNORSY is about 103–105 times faster than classical retrieval techniques based upon optimal estimation.

[1] An evaluation is made of ozone profiles retrieved from measurements of the nadir-viewing Global Ozone Monitoring Experiment (GOME) instrument. Currently, four different approaches are used to retrieve ozone profile information from GOME measurements, which differ in the use of external information and a priori constraints. In total nine different algorithms will be evaluated exploiting the optimal estimation (Royal Netherlands Meteorological Institute, Rutherford Appleton Laboratory, University of Bremen, National Oceanic and Atmospheric Administration, Smithsonian Astrophysical Observatory), Phillips-Tikhonov regularization (Space Research Organization Netherlands), neural network (Center for Solar Energy and Hydrogen Research, Tor Vergata University), and data assimilation (German Aerospace Center) approaches. Analysis tools are used to interpret data sets that provide averaging kernels. In the interpretation of these data, the focus is on the vertical resolution, the indicative altitude of the retrieved value, and the fraction of a priori information. The evaluation is completed with a comparison of the results to lidar data from the Network for Detection of Stratospheric Change stations in Andoya (Norway), Observatoire Haute Provence (France), Mauna Loa (Hawaii), Lauder (New Zealand), and Dumont d'Urville (Antarctic) for the years 1997-1999. In total, the comparison involves nearly 1000 ozone profiles and allows the analysis of GOME data measured in different global regions and hence observational circumstances. The main conclusion of this paper is that unambiguous information on the ozone profile can at best be retrieved in the altitude range 15-48 km with a vertical resolution of 10 to 15 km, precision of 5-10%, and a bias up to 5% or 20% depending on the success of recalibration of the input spectra. The sensitivity of retrievals to ozone at lower altitudes varies from scheme to scheme and includes significant influence from a priori assumptions.

A new approach based on a neural-network technique for reduction in the computation time of radiative-transfer models is presented. This approach gives high spectral resolution without significant loss of accuracy. A rigorous radiative-transfer model is used to calculate radiation values at a few selected wavelengths, and a neural-network algorithm replenishes them to a complete spectrum with radiation values at a high spectral resolution. This method is used for the UV and visible spectral ranges. The results document the ability of a neural network to learn this specific task. More than 20,000 UV-index values for all kinds of atmosphere are calculated by both the rigorous radiative-transfer model alone and the model in combination with the neural-network algorithm. The agreement between both approaches is generally of the order of ?1%; the computation time is reduced by a factor of more than 20. The new algorithm can be used for all kinds of high-quality radiative-transfer model to speed up computation time.

Abstract. Usually, neural networks trained on historical feed-in time series of wind turbines deterministically predict power output over the next hours to days. Here, the training goal is to minimise a scalar cost function, often the root mean square error (RMSE) between network output and target values. Yet similar to the analog ensemble (AnEn) method, the training algorithm can also be adapted to analyse the uncertainty of the power output from the spread of possible targets found in the historical data for a certain meteorological situation. In this study, the uncertainty estimate is achieved by discretising the continuous time series of power targets into several bins (classes). For each forecast horizon, a neural network then predicts the probability of power output falling into each of the bins, resulting in an empirical probability distribution. Similiar to the AnEn method, the proposed method avoids the use of costly numerical weather prediction (NWP) ensemble runs, although a selection of several deterministic NWP forecasts as input is helpful. Using state-of-the-art deep learning technology, we applied our method to a large region and a single wind farm. MAE scores of the 50-percentile were on par with or better than comparable deterministic forecasts. The corresponding Continuous Ranked Probability Score (CRPS) was even lower. Future work will investigate the overdispersiveness sometimes observed, and extend the method to solar power forecasts.