Using Artificial Intelligence to Predict Wind Speed for Energy Application in Saudi Arabia

Brahimi, Tayeb

doi:10.3390/en12244669

Cited by 46 publications

(20 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acceptance of a model heavily depends on its validation. Instead of relying only on the visual endorsement or a single statistical measurement, the current model was validated by exploiting a selected number of statistical parameters [22][23][24][25][26][27][28][29][30][31]. Only the test datasets were used for the present statistical analysis that allowed us to compare the performances of the WAF models objectively.…”

Section: Discussionmentioning

confidence: 99%

A Two-Parameter Model for Water-Lubricated Pipeline Transportation of Unconventional Crudes

et al. 2021

View full text Add to dashboard Cite

Water-lubricated flow technology is an environmentally friendly and economically beneficial means of transporting unconventional viscous crudes. The current research was initiated to investigate an engineering model suitable to estimate the frictional pressure losses in water-lubricated pipelines as a function of design/operating parameters such as flow rates, water content, pipe size, and liquid properties. The available models were reviewed and critically assessed for this purpose. As the reliability of the existing models was not found to be satisfactory, a new two-parameter model was developed based on a phenomenological analysis of the dataset available in the open literature. The experimental conditions for these data included pipe sizes and oil viscosities in the ranges of 25–260 mm and 1220–26,500 mPa·s, respectively. A similar range of water equivalent Reynolds numbers corresponding to the investigated flow conditions was 103–106. The predictions of the new model agreed well with the experimental results. The respective values of the coefficient of determination (R2) and the root mean square error (RMSE) were 0.90 and 0.46. The current model is more refined, easy-to-use, and adaptable compared to other existing models.

show abstract

Section: Discussionmentioning

confidence: 99%

A Two-Parameter Model for Water-Lubricated Pipeline Transportation of Unconventional Crudes

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A complete state-of-the-art review, including the appropriate references, is given by [17,[20][21][22][23][24][25]. The wind turbine loads analysis can be achieved using three effective methods: the momentum method through Blade Element Momentum (BEM), the vortex theory, and the Computational Fluid Dynamics (CFD) method, and more recently using artificial intelligence (AI) to predict wind speed and power performance [26]. With the increased development and installation of wind turbines as wind farms, more work has been investigated in the wake velocity deficits generated by the upfront wind turbines.…”

Section: Previous Workmentioning

confidence: 99%

“…It is important here to note that the wind turbine performance is affected by many parameters such as wind speed, tip-speed ratio (TSR), airfoil shape and size, turbine aspect ratio (H/R), the solidity of the rotor, the swept area, the rotational speed, and other parameters such as dynamic stall effects, the presence of spoilers. Wind turbine aerodynamic loads and performance predictions in the vortex methods use lifting lines or surface to represent rotor blade trailing and shed vorticity in the wake then; the induced velocity is then determined at any point using the Biot-Savard law [21,26]. Two types of vortex models have been used in this approach: the fixed-wake and the free-wake models.…”

Section: Previous Workmentioning

confidence: 99%

Aerodynamic Analysis and Performance Prediction of VAWT and HAWT Using CARDAAV and Qblade Computer Codes

Brahimi¹,

Paraschivoiu²

2022

Entropy and Exergy in Renewable Energy

Self Cite

View full text Add to dashboard Cite

Wind energy researchers have recently invited the scientific community to tackle three significant wind energy challenges to transform wind power into one of the more substantial, low-cost energy sources. The first challenge is to understand the physics behind wind energy resources better. The second challenge is to study and investigate the aerodynamics, structural, and dynamics of large-scale wind turbine machines. The third challenge is to enhance grid integration, network stability, and optimization. This chapter book attempts to tackle the second challenge by detailing the physics and mathematical modeling of wind turbine aerodynamic loads and the performance of horizontal and vertical axis wind turbines (HAWT & VAWT). This work underlines success in the development of the aerodynamic codes CARDAAV and Qbalde, with a focus on Blade Element Method (BEM) for studying the aerodynamic of wind turbines rotor blades, calculating the induced velocity fields, the aerodynamic normal and tangential forces, and the generated power as a function of a tip speed ration including dynamic stall and atmospheric turbulence. The codes have been successfully applied in HAWT and VAWT machines, and results show good agreement compared to experimental data. The strength of the BEM modeling lies in its simplicity and ability to include secondary effects and dynamic stall phenomena and require less computer time than vortex or CFD models. More work is now needed for the simulation of wind farms, the influence of the wake, the atmospheric wind flow, the structure and dynamics of large-scale machines, and the enhancement of energy capture, control, stability, optimization, and reliability.

show abstract

“…There have been many works on wind prediction reported in the past two decades, especially over the last few years. However, most of these works are on the refinement of statistical and AI approaches [13][14][15][16][17][18]; there have been very few studies examining and analyzing the errors of numerical weather models. As a matter of fact, for wind forecasts beyond ~1 h, numerical weather prediction models become essential and fundamental.…”

Section: Introductionmentioning

confidence: 99%

Wind Speed Forecasts of a Mesoscale Ensemble for Large-Scale Wind Farms in Northern China: Downscaling Effect of Global Model Forecasts

Shi

Liu

et al. 2022

Energies

View full text Add to dashboard Cite

To facilitate wind power integration for the electric power grid operated by the Inner Mongolia Electric Power Corporation—a major electric power grid in China—a high-resolution (of 2.7 km grid intervals) mesoscale ensemble prediction system was developed that forecasts winds for 130 wind farms in the Inner Mongolia Autonomous Region. The ensemble system contains 39 forecasting members that are divided into 3 groups; each group is composed of the NCAR (National Center for Atmospheric Research) real-time four-dimensional data assimilation and forecasting model (RTFDDA) with 13 physical perturbation members, but driven by the forecasts of the GFS (Global Forecast System), GEM (Global Environmental Multiscale Model), and GEOS (Goddard Earth Observing System), respectively. The hub-height wind predictions of these three sub-ensemble groups at selected wind turbines across the region were verified against the hub-height wind measurements. The forecast performance and variations with lead time, wind regimes, and diurnal and regional changes were analyzed. The results show that the GFS group outperformed the other two groups with respect to correlation coefficient and mean absolute error. The GFS group had the most accurate forecasts in ~59% of sites, while the GEOS and GEM groups only performed the best on 34% and 2% of occasions, respectively. The wind forecasts were most accurate for wind speeds ranging from 3 to 12 m/s, but with an overestimation for low speeds and an underestimation for high speeds. The GEOS-driven members obtained the least bias error among the three groups. All members performed rather accurately in daytime, but evidently overestimated the winds during nighttime. The GFS group possessed the fewest diurnal errors, and the bias of the GEM group grew significantly during nighttime. The wind speed forecast errors of all three ensemble members increased with the forecast lead time, with the average absolute error increasing by ~0.3 m/s per day during the first 72 h of forecasts.

show abstract

Using Artificial Intelligence to Predict Wind Speed for Energy Application in Saudi Arabia

Cited by 46 publications

References 43 publications

A Two-Parameter Model for Water-Lubricated Pipeline Transportation of Unconventional Crudes

A Two-Parameter Model for Water-Lubricated Pipeline Transportation of Unconventional Crudes

Aerodynamic Analysis and Performance Prediction of VAWT and HAWT Using CARDAAV and Qblade Computer Codes

Wind Speed Forecasts of a Mesoscale Ensemble for Large-Scale Wind Farms in Northern China: Downscaling Effect of Global Model Forecasts

Contact Info

Product

Resources

About