Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “FORECASTING”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Relating CMIP5 Model Biases to Seasonal Forecast Skill in the Tropical Pacific

Abstract We examine links between tropical Pacific mean state biases and El Niño/Southern Oscillation forecast skill, using model‐analog hindcasts of sea surface temperature (SST; 1961–2015) and precipitation (1979–2015) at leads of 0–12 months, generated by 28 different models from the fifth phase of the Coupled Model Intercomparison Project (CMIP5). Model‐analog forecast skill has been demonstrated to match or even exceed traditional assimilation‐initialized forecast skill in a given model. Models with the most realistic mean states and interannual variability for SST, precipitation, and 10‐m zonal winds in the equatorial Pacific also generate the most skillful precipitation forecasts in the central equatorial Pacific and the best SST forecasts at 6‐month or longer leads. These results show direct links between model climatological biases and seasonal forecast errors, demonstrating that model‐analog hindcast skill—that is, how well a model can capture the observed evolution of tropical Pacific anomalies—is an informative El Niño/Southern Oscillation metric for climate simulations.

Ding, Hui↗
DOE OSTI2023

Short-lead seasonal precipitation forecast in northeastern Brazil using an ensemble of artificial neural networks

This study assesses the deterministic and probabilistic forecasting skill of a 1-month-lead ensemble of Artificial Neural Networks (EANN) based on low-frequency climate oscillation indices. The predictand is the February-April (FMA) rainfall in the Brazilian state of Ceará, which is a prominent subject in climate forecasting studies due to its high seasonal predictability. Additionally, the study proposes combining the EANN with dynamical models into a hybrid multi-model ensemble (MME). The forecast verification is carried out through a leave-one-out cross-validation based on 40 years of data. The EANN forecasting skill is compared with traditional statistical models and the dynamical models that compose Ceará’s operational seasonal forecasting system. A spatial comparison showed that the EANN was among the models with the smallest Root Mean Squared Error (RMSE) and Ranked Probability Score (RPS) in most regions. Moreover, the analysis of the area-aggregated reliability showed that the EANN is better calibrated than the individual dynamical models and has better resolution than Multinomial Logistic Regression for above-normal (AN) and below-normal (BN) categories. It is also shown that combining the EANN and dynamical models into a hybrid MME reduces the overconfidence of the extreme categories observed in a dynamically-based MME, improving the reliability of the forecasting system.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Evaluating Recursive Blind Forecast Against API and Baseline: A Puerto Rican Case Study on Solar Irradiance for Normal and Extreme Weather

This paper leverages ongoing work in a community microgrid in Adjuntas, Puerto Rico to forecast global horizontal irradiance (GHI) and compare performance in normal and extreme weather. Given a positive correlation of 0.98 between GHI and PV power, forecasting GHI can be an effective, indirect forecast of photovoltaic (PV) power, especially in microgrids where the end-users, owners, operators, or other stakeholders are reluctant to share data for training or validation due to privacy and security concerns. A recursive one-shot (termed as "blind") forecast is, hence, formulated, wherein a gradient-boosted regression tree (GBR) is built to forecast GHI for a 7-day horizon in normal weather, and a 2-day horizon in extreme weather. To demonstrate its resilience, the architecture is trained on normal and hurricane weather GHI from 2002-2022. It is generalized on February 9-16, 2023, and on the landfall of Hurricane Nicole (Nov 4-5, 2022), respectively. Forecasts from GBR are compared against that from a satellite-based API resource and three baselines: persistence, averaging, and exponential smoothing. Results show GBR and persistence outperform sophisticated API in both types of weather for this case study.

Sundararajan, Aditya↗
DOE OSTI2023

Impacts of Dispatch Strategies and Forecast Errors on the Economics of Behind-the-Meter PV-Battery Systems

To assess the economic value of batteries in hybrid PV-battery systems, one must create a dispatch profile for the battery. Many analyses of battery value assume perfect forecasts of PV generation and load, determining an upper limit on the value of the battery. Prior work that accounts for forecast uncer- tainty often does so in the context of a single dispatch algorithm, which does not provide a baseline for comparison. Furthermore, when multiple dispatch algorithms are assessed with uncertainty, the benefits considered are for diesel generation in a microgrid, not retail rate savings. This work addresses the gaps in the literature by comparing the performance of both heuristic and optimal dispatch algorithms for retail rate savings under forecast uncertainty, and provides comparisons of the robustness of these algorithms and their associated estimates of economic value. We find that using a perfect forecast can overestimate the value of hybrid PV-battery systems between 1% and 8% compared to the reality of using a day-ahead forecast, depending on the dispatch algorithm used. Thus, accounting for forecast uncertainty in system design and analysis will significantly improve the accuracy of modeled system values.

batteries↗
DOE OSTI2024

Multi-year assessment of the impact of ship-borne radiosonde observations on polar WRF forecasts in the Arctic

Abstract To compensate for the lack of conventional observations over the Arctic Ocean, ship-borne radiosonde observations have been regularly carried out during summer Arctic expeditions and the observed data have been broadcast via the global telecommunication system since 2017. With these data obtained over the data-sparse Arctic Ocean, observing system experiments were carried out using a polar-optimized version of the Weather Research and Forecasting (WRF) model and the WRF Data Assimilation (WRFDA) system to investigate their effects on analyses and forecasts over the Arctic. The results of verification against reanalysis data reveal: (1) DA effects on analyses and forecasts; (2) the reason for the year-to-year variability of DA effects; and (3) the possible role of upper-level potential vorticity in delayed DA effects. The overall assimilation effects of the extra data on the analyses and forecasts over the Arctic are positive. Initially, the DA effects are the most apparent in the temperature variables in the middle/lower troposphere, which spread to the wind variables in the upper troposphere. The effects decrease with time but reappear after approximately 120 h, even in the 240-h forecasts. The effects on forecasts vary depending on the proximity of the radiosonde observation locations to the high synoptic variability. The upper-level potential vorticity is known to play an important role in the development of Arctic cyclones, and it is suggested as a possible explanation for the delayed DA effects after about 120 h.

Geology↗
DOE OSTI2025

Synthetic method of analogues for emerging infectious disease forecasting

The Method of Analogues (MOA) has gained popularity in the past decade for infectious disease forecasting due to its non-parametric nature. In MOA, the local behavior observed in a time series is matched to the local behaviors of several historical time series. The known values that directly follow the historical time series that best match the observed time series are used to calculate a forecast. This non-parametric approach leverages historical trends to produce forecasts without extensive parameterization, making it highly adaptable. However, MOA is limited in scenarios where historical data is sparse. This limitation was particularly evident during the early stages of the COVID-19 pandemic, where the emerging global epidemic had little-to-no historical data. In this work, we propose a new method inspired by MOA, called the Synthetic Method of Analogues (sMOA). sMOA replaces historical disease data with a library of synthetic data that describe a broad range of possible disease trends. This model circumvents the need to estimate explicit parameter values by instead matching segments of ongoing time series data to a comprehensive library of synthetically generated segments of time series data. We demonstrate that sMOA has competitive performance with state-of-the-art infectious disease forecasting models, out-performing 78% of models from the COVID-19 Forecasting Hub in terms of averaged Mean Absolute Error and 76% of models from the COVID-19 Forecasting Hub in terms of averaged Weighted Interval Score. Additionally, we introduce a novel uncertainty quantification methodology designed for the onset of emerging epidemics. Developing versatile approaches that do not rely on historical data and can maintain high accuracy in the face of novel pandemics is critical for enhancing public health decision-making and strengthening preparedness for future outbreaks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Solar and Wind Forecast Error Reserve Sharing in a Multi-Utility Region

As electricity systems transition to higher levels of solar and wind generation, electric system operators will likely need to hold additional reserves to manage solar and wind forecast error. Because solar and wind forecast errors tend to be weakly correlated across space, system operators can reduce their reserve requirements by sharing reserves. This paper examines the benefits of forecast error reserve sharing among balancing areas in the Southeastern United States, in scenarios in which solar and wind generation ranges from 34% to 65% of total generation. It finds that day-ahead forecast error reserve requirements increase linearly with growth in solar and wind generation capacity (6%-10% of total capacity), but that reserve sharing can significantly reduce these requirements (by 6%-29%). It finds that, in economic terms, the value of forecast error reserve sharing ($\$$0.09-$\$$1.24 billion per year, $\$$0.12-$\$$1.68/MWh of load across scenarios) tends to decline with higher levels of solar and wind generation, due to lower reserve and energy prices. Even with declines in reserve prices, forecast error reserve sharing can still provide substantial value, though with higher levels of solar, wind, and electricity storage this value is increasingly tied to avoiding scarcity prices.

14 SOLAR ENERGY↗
DOE OSTI2020

Evaluation of the Four-Dimensional Ensemble-Variational Hybrid Data Assimilation with Self-Consistent Regional Background Error Covariance for Improved Hurricane Intensity Forecasts

The feasibility of a hurricane initialization framework based on the Gridpoint Statistical Interpolation (GSI)-based four-dimensional ensemble-variational (GSI-4DEnVar) hybrid data assimilation system for the Hurricane Weather Research and Forecasting model (HWRF) model is evaluated in this study. The system considers the temporal evolution of error covariances via the use of four-dimensional ensemble perturbations that are provided by high-resolution, self-consistent HWRF ensemble forecasts. It is different from the configuration of the GSI-based three-dimensional ensemble-variational (GSI-3DEnVar) hybrid data assimilation system, similar to that used in the operational HWRF, which employs background error covariances provided by coarser-resolution global ensembles from the National Centers for Environmental Prediction (NCEP) Global Forecast System (GFS) ensemble Kalman filtering data assimilation system. In addition, our proposed initialization framework discards the empirical intensity correction in the vortex initialization package that is employed by the GSI-3DEnVar initialization framework in operational HWRF. Data assimilation and numerical simulation experiments for Hurricanes Joaquin (2015), Patricia (2015), and Matthew (2016) are conducted during their intensity changes. The impacts of two initialization frameworks on the HWRF analyses and forecasts are compared. It is found that GSI-4DEnVar leads to a reduction in track, minimum sea level pressure (MSLP), and maximum surface wind (MSW) forecast errors in all of the HWRF simulations, compared with the GSI-3DEnVar initialization framework. With assimilating high-resolution observations within the hurricane inner-core region, GSI-4DEnVar can produce the initial hurricane intensity reasonably well without the empirical vortex intensity correction. Further diagnoses with Hurricane Joaquin indicate that GSI-4DEnVar can significantly alleviate the imbalances in the initial conditions and enhance the performance of the data assimilation and subsequent hurricane intensity and precipitation forecasts

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

An Assessment of the Influence of Uncertainty in Temporally Evolving Streamflow Forecasts on Riverine Inundation Modeling

Continental-scale river forecasting platforms forecast streamflow at reaches that can be used as boundary conditions to drive a local-scale flood inundation model. Uncertainty accumulated during this process stems not only from any part of the forecasting chain but can also be caused by the daily variations in weather forcing that keeps evolving as the event advances. This work aims to examine the influence of the evolving forecast streamflow on predicting the maximum inundation for extreme floods. A diagnostic case study was made on the basis of a hindcast of Hurricane Matthew striking the eastern U.S. in 2016. The U.S. National Water Model was one-way coupled to a hydrodynamic inundation model through a developed automated workflow. Although the river forcing has significantly mismatched hydrographs versus observations, the simulated peak water surface elevations and maximum extents were validated to be comparable with the observations, which indicates that the inundation model may not be sensitive to the inherited uncertainty from the weather forcing. Moreover, the uncertainty of the forecast streamflow time series caused only one order of magnitude fewer variations in inundation prediction; this dampening effect may become clearer for extreme events with large areas inundated. In addition, the forecast total volume of stream discharge appears to be an important metric for assessing the performance of river forcing for inundation mapping, as a linear correlation between the total volume and the accuracy of the predicted peak water surface elevation and maximum extent was found, with the coefficients of determination all above 0.8. Extra best-practice experience of running similar operational tasks demonstrated the tradeoff between the cost and accuracy gain.

flood, national water model, RIFT↗
DOE OSTI2022

Local-thermal-gradient and large-scale-circulation impacts on turbine-height wind speed forecasting over the Columbia River Basin

Abstract. We investigate the sensitivity of turbine-height wind speed forecast to initial condition (IC) uncertainties over the Columbia River Gorge (CRG) and Columbia River Basin (CRB) for two typical weather phenomena, i.e., local-thermal-gradient-induced marine air intrusion and a cold frontal passage. Four types of turbine-height wind forecast anomalies and their associated IC uncertainties related to local thermal gradients and large-scale circulations are identified using the self-organizing map (SOM) technique. The four SOM types are categorized into two patterns, each accounting for half of the ensemble members. The first pattern corresponds to IC uncertainties that alter the wind forecast through a modulating weather system, which produces the strongest wind anomalies in the CRG and CRB. In the second pattern, the moderate uncertainties in local thermal gradient and large-scale circulation jointly contribute to wind forecast anomaly. We analyze the cross section of wind and temperature anomalies through the gorge to explore the evolution of vertical features of each SOM type. The turbine-height wind anomalies induced by large-scale IC uncertainties are more concentrated near the front. In contrast, turbine-height wind anomalies induced by the local IC thermal uncertainties are found above the surface thermal anomalies. Moreover, the wind forecast accuracy in the CRG and CRB is limited by IC uncertainties in a few specific regions, e.g., the 2 m temperature within the basin and large-scale circulation over the northeast Pacific around 140∘ W.

17 WIND ENERGY↗
DOE OSTI2023

Using High-Resolution NSRDB Data to Evaluate Cloud Mask Forecast from WRF-Solar EPS

Validating spatiotemporal distributions of cloud forecasts using numerical weather prediction (NWP) models is difficult as this requires high-quality cloud-property at significantly high spatial and temporal resolution over extended periods of time. Observations of cloud properties, such as cloud mask, cloud optical thickness, and cloud type, are vital for assessing the capability of NWP models to forecast various types of clouds. Using the National Solar Radiation Database (NSRDB), this research evaluates ensemble cloud-mask predictions from the WRF-Solar ensemble prediction system (WRF-Solar EPS). From the WRF-Solar EPS, day-ahead solar forecasts for the contiguous United States (CONUS) for 2018 are simulated. Given the NSRDB data is accessible at a resolution of 2 km, we can calculate the cloud fraction across the 9-km grid of WRF-Solar EPS. This allows us to spatially assess the cloud-mask forecasts using two methods against the high-resolution NSRDB: (a) considering all 2-km NSRDB clouds in the forecast domain (EMAll), and (b) using a minimum cloud fraction threshold of 50% to designate a pixel as cloudy (EMP50). The low-resolution cloud masks from WRF-Solar EPS are evaluated directly against the cloud-resolving scale gridded observations from NSRDB using EMAll. With EMP50, we presume that scenes with less than 50% cloud cover from the 2-km NSRDB are clear. Thus, this assessment approach allows for a fair comparison with WRF-Solar EPS resolved to a 9-km grid. A method of point-by-point verification is used to evaluate dichotomous (yes/no) cloud mask predictions against the NSRDB. For each pixel of model extent, cloud frequency and traditional metrics (e.g., probability of detection, false alarm rate, and hit rate, etc.) are computed and compared with satellite-derived data sets. Mismatched cloud frequency (MCF) is computed to measure the present capability of WRF-Solar EPS in representing various types of clouds, which are categorized using three levels of cloud top height (CTH) and cloud optical depth (COD) across entire CONUS. Preliminary results show that the WRF-Solar EPS provides MCF values ranging from 9% to 46%, 16% to 33%, and 8% to 27% for low-level, middle-level, and high-level clouds, respectively, for three CTHs. The model produces MCFs ranging from 27% to 46%, 13% to 34%, and 8% to 19% for thin, medium-thickness, and thick clouds, respectively, for three CODs. The presentation will include a detailed description of the current outcomes as well as potential future extensions. The evaluation approach established in this study is readily extensible to the evaluation of cloud predictions from different ensemble NWP models. In addition, the findings of the suggested evaluation technique aid in identifying model weaknesses and will ultimately lead to advances in WRF-Solar EPS's skill in predicting clouds and solar irradiance.

cloud mask forecast↗
DOE OSTI2021

Review of Onsite Temperature and Solar Forecasting Models to Enable Better Building Design and Operations

Advanced building controls and energy optimization for new constructions and retrofits rely on accurate weather data. Traditionally, most studies utilize airport weather information as the decision inputs. However, most buildings are in environments that are quite different than those at the airport miles away. Tree cover, adjacent buildings, and micro-climate effects caused by the larger surrounding area can all yield deviations in air temperature, humidity, solar irradiance, and wind that are large enough to influence design and operation decisions. In order to overcome this challenge, there are many prior studies on developing weather forecasting algorithms from micro-to meso-scales. Additionally, this paper reviews and complies knowledge on common weather data resources, data processing methodologies and forecasting techniques of weather information. Commonly used statistical, machine learning and physical-based models are discussed and presented as two major categories: deterministic forecasting and probabilistic forecasting. Finally, evaluation metrics for forecasting errors are listed and discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Active learning strategy for high fidelity short-term data-driven building energy forecasting

The quality of a data-driven model is heavily dependent on the quality of data. Data from building operation often have data bias problems, which means that the data sample is collected in a way that some members of the intended data population are less likely to be included than others. Data-driven energy forecasting models built on such data hence are biased and could lead to large forecasting errors. Active learning—an effective method to defying data bias—is rarely studied or applied in the area of data-driven building energy forecasting modeling. This paper attempts to fill this gap and explores the application of active learning in data-driven building energy forecasting. The developed strategy in this paper efficiently generate informative training data within a time budget and uses block design to passively consider weather disturbances. The developed active learning strategy is applied and evaluated in both virtual and real-building testbeds against traditional data-driven methods. Via these virtual and real-building evaluation cases, we have demonstrated that the data bias problem typically exists in building operation data is resolved by applying the developed active learning strategy. Furthermore, building energy forecasting models trained from data generated from the active learning strategy have shown improved performances in both model accuracy and model extendibility perspectives. The effectiveness of the block design module is also validated to effectively consider the impact of weather conditions on active learning design.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Explainable machine learning model for multi-step forecasting of reservoir inflow with uncertainty quantification

We propose an explainable machine learning (ML) model with uncertainty quantification (UQ) to improve multi-step reservoir inflow forecasting. Traditional ML methods have challenges in forecasting inflows multiple days ahead, and lack explainability and UQ. To address these limitations, we introduce an encoder–decoder long short-term memory (ED-LSTM) network for multi-step forecasting, employ the SHapley Additive exPlanation (SHAP) technique for understanding the influence of hydrometeorological factors on inflow prediction, and develop a novel UQ method for prediction trustworthiness. We apply these methods to forecast 7-day inflow in snow-dominant and rain-driven reservoirs. The results demonstrate the effectiveness of the ED-LSTM model, with high forecasting accuracy for short lead times. Our UQ method provides reliable uncertainty estimates, covering 90% of data with a 90% confidence level. The SHAP analysis reveals the importance of historical inflow and precipitation as influential factors. These findings and methods may support reservoir operators in optimizing water resources management decisions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

AGFormer: Adaptive Spatiotemporal graph informed transformer for multi-reservoir inflow forecasting

Accurate reservoir inflow forecasting is crucial for effective water resource management, yet most machine learning models focus on single-reservoir prediction and overlook spatial dependencies among hydrologically connected reservoirs. Here, we propose AGFormer (Adaptive Graph-Informed Transformer), an end-to-end framework that integrates adaptive graph learning with temporal sequence modeling for multi-reservoir inflow forecasting. A shared encoder and graph attention mechanism generate reservoir-specific embeddings, which are then processed by the Transformer-based encoder–decoder for multi-step inflow forecasting. We also introduce a pretraining paradigm to learn robust temporal embeddings from misaligned historical records. Evaluated on 30 reservoirs in the Upper Colorado River Basin, AGFormer achieves superior seven-day-ahead forecasts, with NSE > 0.75 for 20 reservoirs—outperforming Encoder–Decoder LSTM, GCN+LSTM, and Transformer baselines. Adaptive graph learning captures dynamic inter-reservoir dependencies, and feature attribution aligns with snowmelt-driven hydrology. Incorporating forecasted meteorological inputs further enhances accuracy, demonstrating AGFormer’s potential to support reservoir management under dynamic hydrological conditions.

Adaptive graph learning↗
DOE OSTI2020

Air compressor load forecasting using artificial neural network

Air compressor systems are responsible for approximately 10% of the electricity consumed in United States and European Union industry. As many researches have proven the effectiveness of using Artificial Neural Network inair compressor performance prediction, there is still a need to forecast the air compressor electrical load profile. The objective of this study is to predict compressed air systems’ electrical load profile, which is valuable to industry practitioners as well as software providers in developing better practice and tools for load managementand look-ahead scheduling programs. Two artificial neural networks, Two-Layer Feed-Forward Neural Networkand Long Short-Term Memory were used to predict an air compressors electrical load. Compressors with three different control mechanisms are evaluated with a total number of 11,874 observations. Here, the forecasts were validated using out-of-sample datasets with 5-fold cross-validation. Models produced average coefficient ofdetermination values from 0.24 to 0.94, average root-mean-square errors from 0.05 kW - 5.83 kW, and meanabsolute scaled errors from 0.20 to 1.33. The results indicate that both artificial neural networks yield goodresults for compressors using variable speed drive (average R 2 = 0.8 and no naïve forecasting), only the longshort-term memory model gives acceptable results for compressors using on/off control (average R 2 = 0.82 and no naïve forecasting), and no satisfactory results are obtained for load/unload type air compressors (models constituting active forecasting).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Forecasting Megaelectron-Volt Electrons Inside Earth's Outer Radiation Belt: PreMevE 2.0 Based on Supervised Machine Learning Algorithms

We present the recent progress in upgrading a predictive model for megaelectron-volt (MeV) electrons inside the Earth's outer Van Allen belt. This updated model, called PreMevE 2.0, provides improved forecasts, particularly at outer L-shells, by adding upstream solar wind speeds to the model's input parameter list that originally includes precipitating electrons observed at low Earth orbits and MeV electron fluxes in situ measured by a geosynchronous satellite. Furthermore, based on several kinds of linear and artificial neural networks algorithms, a list of models was constructed, trained, validated, and tested with 42-month MeV electron observations from Van Allen Probes. Out-of-sample test results from these models show that, with optimized model hyperparameters and input parameter combinations, the top performer from each category of models has the similar capability of making reliable 1-day (2-day) forecasts of 1-MeV electron flux distributions with performance efficiency values ~0.87 (~0.82) averaged over the L-shell range of 2.8–6.6, significantly outperforming the previous version of PreMevE particularly at L-shells > ~4.5. Interestingly, the linear regression model is often the most successful when compared to other models, which suggests the relationship between dynamics of trapped 1-MeV electrons and precipitating electrons is dominated by linear components. Results also show that PreMevE 2.0 can reasonably well predict the onsets of MeV electron events in 2-day forecasts. PreMevE 2.0 is designed to be driven by observations from longstanding space infrastructure to make high-fidelity forecasts for MeV electrons, thus can be an invaluable space weather forecasting tool for the future.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Entropy-Infused Deep Learning Loss Function for Capturing Extreme Values in Wind Power Forecasting

Extreme scenarios in wind power generation occur with higher frequency and larger magnitude in the recent years due to the ever-increasing extreme meteorological factors. Accurate forecasting of the occurrence of extreme values in wind power generation is of great concern to ensure reliable power system operation. Recently, deep learning models have surged in popularity for wind power forecasting, with the mean squared error (MSE) loss function being commonly used. However, the MSE loss function, being sensitive to extreme values, disproportionately penalizes larger errors, cannot adequately capture the extreme values present in wind energy data, and novel loss functions have seldom been tailored for wind power forecasting. To this end, in this paper, we introduce a novel loss function specifically crafted to capture extreme values in wind power forecasting. The experimental results with four fundamental deep learning methods on open source wind power dataset validate that the new loss function is efficient and superior in all cases compared to MSE in capturing extreme values while maintaining forecasting performance.

17 WIND ENERGY↗