The Impact of Weather Variability on Renewable Energy Consumption: Insights from Explainable Machine Learning Models DOI Open Access

Rong Qu,

Ruibing Kou, T. Zhang

и другие.

Sustainability, Год журнала: 2024, Номер 17(1), С. 87 - 87

Опубликована: Дек. 26, 2024

The pursuit of carbon neutrality is reshaping global energy systems, making the transition to renewable critical for mitigating climate change. However, unstable weather conditions continue challenge consumption stability and grid reliability. This study investigates effectiveness various machine learning (ML) models at predicting differences employs SHapley Additive Explanations (SHAP) interpretability tool quantify influence key variables, using five years data (2017–2022) 196,776 observations collected across Europe. dataset consists hourly records, variables such as Global Horizontal Irradiance (GHI), sunlight duration, day length, cloud cover, humidity are identified predictors. results demonstrate that Random Forest (RF) model achieves highest accuracy (R2 = 0.92, RMSE 360.17, MAE 208.84), outperforming other in differences. Through SHAP analysis, this demonstrates profound GHI, which exhibits a correlation coefficient 0.88 with variance. Incorporating advanced preprocessing predictor selection techniques remains RF but reduces by approximately 25% XGBoost model, underlining importance selecting appropriate input variables. Hyperparameter tuning further enhances performance, particularly less robust algorithms prone overfitting. reveals complex seasonal regional effects on demands. These findings underscore ML addressing challenges systems provide valuable insights policymakers practitioners optimize management strategies, integrate sources, achieve sustainable development objectives.

Язык: Английский

Hydrogen Fuel Cell Vehicles: Opportunities and Challenges DOI Open Access
Qusay Hassan, Itimad D. J. Azzawi, Aws Zuhair Sameen

и другие.

Sustainability, Год журнала: 2023, Номер 15(15), С. 11501 - 11501

Опубликована: Июль 25, 2023

This paper provides an in-depth review of the current state and future potential hydrogen fuel cell vehicles (HFCVs). The urgency for more eco-friendly efficient alternatives to fossil-fuel-powered underlines necessity HFCVs, which utilize gas power onboard electric motor, producing only water vapor heat. Despite their impressive energy efficiency ratio (EER), higher power-to-weight ratio, substantial emissions reduction potential, widespread implementation HFCVs is presently hindered by several technical infrastructural challenges. These include high manufacturing costs, relatively low density hydrogen, safety concerns, durability issues, insufficient refueling infrastructure, complexities storage transportation. Nevertheless, technological advancements policy interventions offer promising prospects suggesting they could become a vital component sustainable transportation in future.

Язык: Английский

Процитировано

97
Government Initiative and Policy for Agricultural Waste Utilization as Biofuel DOI
Prateek Srivastava

Clean Energy Production Technologies, Год журнала: 2024, Номер unknown, С. 273 - 304

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

2
A Roadmap with Strategic Policy toward Green Hydrogen Production: the Case of Iraq DOI Open Access
Qusay Hassan, Aws Zuhair Sameen, Hayder Mahmood Salman

и другие.

Опубликована: Март 13, 2023

The most potential renewable energy source for global emissions reductions is green hydrogen production. Iraq looking into several sources of alternative to lessen its dependency on fossil fuels and considerably cut carbon dioxide emissions. This research examined the conceptual framework production consumption in Iraq. On basis accessible official public data from government agencies, capabilities resources are assessed, certain fair assumptions also established a full study evaluation possible country. presented here demonstrate conclusively that contributions substantial, giving country prominence area A pathway economy by 2050 proposed this based analysis. It distributed three stages: as fuel industry; using cells; commercialization. other hand, found number challenges implementation can be used developing countries, including technological, economic, social problems addition related policy consequences.

Язык: Английский

Процитировано

4
The Impact of Weather Variability on Renewable Energy Consumption: Insights from Explainable Machine Learning Models DOI Open Access

Rong Qu,

Ruibing Kou, T. Zhang

и другие.

Sustainability, Год журнала: 2024, Номер 17(1), С. 87 - 87

Опубликована: Дек. 26, 2024

The pursuit of carbon neutrality is reshaping global energy systems, making the transition to renewable critical for mitigating climate change. However, unstable weather conditions continue challenge consumption stability and grid reliability. This study investigates effectiveness various machine learning (ML) models at predicting differences employs SHapley Additive Explanations (SHAP) interpretability tool quantify influence key variables, using five years data (2017–2022) 196,776 observations collected across Europe. dataset consists hourly records, variables such as Global Horizontal Irradiance (GHI), sunlight duration, day length, cloud cover, humidity are identified predictors. results demonstrate that Random Forest (RF) model achieves highest accuracy (R2 = 0.92, RMSE 360.17, MAE 208.84), outperforming other in differences. Through SHAP analysis, this demonstrates profound GHI, which exhibits a correlation coefficient 0.88 with variance. Incorporating advanced preprocessing predictor selection techniques remains RF but reduces by approximately 25% XGBoost model, underlining importance selecting appropriate input variables. Hyperparameter tuning further enhances performance, particularly less robust algorithms prone overfitting. reveals complex seasonal regional effects on demands. These findings underscore ML addressing challenges systems provide valuable insights policymakers practitioners optimize management strategies, integrate sources, achieve sustainable development objectives.

Язык: Английский

Процитировано

0