Solar and wind power generation forecasts using elastic net in time-varying forecast combinations

Nikodinoska, Dragana; Käso, Mathias; Müsgens, Felix

doi:10.1016/j.apenergy.2021.117983

Cited by 40 publications

(8 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the total installed capacity of wind and solar power generation in the world in 2022 reached 2079 GW. [ 38 ] The annual production of Ir falls within the range of 5–10 tons each year. Assuming a maximum output of 10 tons, the cumulative electrolytic power of such TiO 2 ‐ordered MEAs could potentially reach an impressive 3444 GW.…”

Section: Resultsmentioning

confidence: 99%

Hybrid 3D‐Ordered Membrane Electrode Assembly (MEA) with Highly Stable Structure, Enlarged Interface, and Ultralow Ir Loading by Doping Nano TiO₂ Nanoparticles for Water Electrolyzer

Liu,

Tian,

Ning

et al. 2023

Advanced Energy Materials

View full text Add to dashboard Cite

Proton exchange membrane water electrolysis (PEMWE) is a very promising and sustainable hydrogen production technology. Currently, there is a growing interest in achieving ordered structures within membrane electrode assembly (MEA) for PEMWE. However, both ordered electron conductor and ordered proton conductor structures are single component structure, which still have many shortcomings. In this work, a hybrid ordered membrane electrodes assembly based on cone‐shaped is constructed Nafion array with rough surface by introducing TiO2 nanoparticles to Nafion emulsion. As a result, this hybrid ordered MEA achieves a high surface roughness of 3.39 nm that is 2.64 times higher than that of ordered MEA without TiO2 nanoparticles doped and current density up to 2.48 A cm−2 at 2 V with 14.4 µg cm−2 (Ir) catalyst loading. This work provides a new hybrid ordered structure for MEA and exhibits the great potential of enhancing the interfacial contact between the catalyst layer and Nafion membrane to improve PEMWE performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Hybrid 3D‐Ordered Membrane Electrode Assembly (MEA) with Highly Stable Structure, Enlarged Interface, and Ultralow Ir Loading by Doping Nano TiO₂ Nanoparticles for Water Electrolyzer

Liu,

Tian,

Ning

et al. 2023

Advanced Energy Materials

View full text Add to dashboard Cite

show abstract

“…So we developed code that iterates over various regression models to forecast a temperature series using the obtained coefficients B 1 and B 2 . These models include Decision Tree 52 , Bagging 53 , AdaBoost 54 , XGBoost 55 , SVR (Support Vector Regression) 56 , Gradient Boosting 57 , Linear Regression 58 , Random Forest 59 , Ridge 60 , LassoLars 61 , RANSAC 62 , SVR Poly 63 , Elastic Net CV 64 , OMP (Orthogonal Matching Pursuit) 65 , Tweedie 66 , Gaussian Process 67 , Passive Aggressive 68 , CatBoost 69 , LightGBM 70 (Light Gradient Boosting Machine), Hist Gradient Boosting 71 (Histogram-based Gradient Boosting), Bayesian Ridge 72 , PA Hinge 73 (Passive Aggressive with Hinge Loss), Extra Trees 74 , Theil-Sen 75 , Poisson 76 , GLM (Generalized Linear Model) 77 , Quantile Regression 78 , and Gamma 79 . For each model, it trains a polynomial regression with different degrees and evaluates its performance metrics such as mean squared error (MSE), R-squared (R 2 ), root mean squared error (RMSE), normalized MSE (NMSE), mean absolute error (MAE), and mean percentage error (MPE).…”

Section: Dataset Processing and Forecastingmentioning

confidence: 99%

Exploring Temperature-Dependent Photoluminescence Dynamics in Colloidal CdSe Nanoplatelets using Machine Learning Approach

Malashin,

Daibagya,

Tynchenko

et al. 2024

Preprint

View full text Add to dashboard Cite

The study explore machine learning techniques to predict temperature-dependent photoluminescence spectra in colloidal CdSe nanoplatelets, leveraging polynomial regression models trained on experimental data from 85 to 270 K spanning temperatures to forecast photoluminescence spectra backward to 0 K and forward to 300 K. 6th-degree polynomial models with Tweedie regression were optimal for band energy B1 predictions up to 300 K, while 9th-degree models with LassoLars and Linear Regression regressors were suitable for backward predictions to 0 K. For exciton energy B2, the Lasso model of degree 5 and the Ridge model of degree 4 performed well up to 300 K, while the Tweedie model of degree 2 and Theil-Sen model of degree 2 showed promise for predictions to 0 K. Furthermore, we utilize a GA-based approach to fit experimental data to theoretical model of Fan and Varshni equations, facilitating a comparative analysis with the ML-predicted curves.

show abstract

“…At present, wind farm data mainly rely on the SCADA system [15] to collect real-time data, and a large number of feature data are obtained with the help of sensors, which is helpful to analyze the running state of the wind turbine. How to use the collected multi-feature data to study the correlation in the deep aspect is a hot topic in wind power prediction research [16][17][18].…”

Section: Related Workmentioning

confidence: 99%

Interpretable Wind Power Short-Term Power Prediction Model Using Deep Graph Attention Network

Zhang,

Li,

Cheng

et al. 2024

Energies

View full text Add to dashboard Cite

High-precision spatial-temporal wind power prediction technology is of great significance for ensuring the safe and stable operation of power grids. The development of artificial intelligence technology provides a new scheme for modeling with strong spatial-temporal correlation. In addition, the existing prediction models are mostly ‘black box’ models, lacking interpretability, which may lead to a lack of trust in the model by power grid dispatchers. Therefore, improving the model to obtain interpretability has become an important challenge. In this paper, an interpretable short-term wind power prediction model based on ensemble deep graph neural network is designed. Firstly, the graph network model (GNN) with an attention mechanism is applied to the aggregate and the spatial-temporal features of wind power data are extracted, and the interpretable ability is obtained. Then, the long short-term memory (LSTM) method is used to process the extracted features and establish a wind power prediction model. Finally, the random sampling algorithm is used to optimize the hyperparameters to improve the learning rate and performance of the model. Through multiple comparative experiments and a case analysis, the results show that the proposed model has a higher prediction accuracy than other traditional models and obtains reasonable interpretability in time and space dimensions.

show abstract

Solar and wind power generation forecasts using elastic net in time-varying forecast combinations

Cited by 40 publications

References 80 publications

Hybrid 3D‐Ordered Membrane Electrode Assembly (MEA) with Highly Stable Structure, Enlarged Interface, and Ultralow Ir Loading by Doping Nano TiO₂ Nanoparticles for Water Electrolyzer

Hybrid 3D‐Ordered Membrane Electrode Assembly (MEA) with Highly Stable Structure, Enlarged Interface, and Ultralow Ir Loading by Doping Nano TiO₂ Nanoparticles for Water Electrolyzer

Exploring Temperature-Dependent Photoluminescence Dynamics in Colloidal CdSe Nanoplatelets using Machine Learning Approach

Interpretable Wind Power Short-Term Power Prediction Model Using Deep Graph Attention Network

Contact Info

Product

Resources

About

Solar and wind power generation forecasts using elastic net in time-varying forecast combinations

Cited by 40 publications

References 80 publications

Hybrid 3D‐Ordered Membrane Electrode Assembly (MEA) with Highly Stable Structure, Enlarged Interface, and Ultralow Ir Loading by Doping Nano TiO2 Nanoparticles for Water Electrolyzer

Hybrid 3D‐Ordered Membrane Electrode Assembly (MEA) with Highly Stable Structure, Enlarged Interface, and Ultralow Ir Loading by Doping Nano TiO2 Nanoparticles for Water Electrolyzer

Exploring Temperature-Dependent Photoluminescence Dynamics in Colloidal CdSe Nanoplatelets using Machine Learning Approach

Interpretable Wind Power Short-Term Power Prediction Model Using Deep Graph Attention Network

Contact Info

Product

Resources

About

Hybrid 3D‐Ordered Membrane Electrode Assembly (MEA) with Highly Stable Structure, Enlarged Interface, and Ultralow Ir Loading by Doping Nano TiO₂ Nanoparticles for Water Electrolyzer

Hybrid 3D‐Ordered Membrane Electrode Assembly (MEA) with Highly Stable Structure, Enlarged Interface, and Ultralow Ir Loading by Doping Nano TiO₂ Nanoparticles for Water Electrolyzer