A simple gust estimation algorithm and machine learning based nowcasting for wind turbines

2020 ◽  
Author(s):  
Irene Schicker ◽  
Petrina Papazek
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Wind Speed ◽  
Wind Turbines ◽  
Wind Farm ◽  
Construction Material ◽  
Information Source ◽  
Estimation Algorithm ◽  
Average Wind Speed ◽  
Average Wind

<p>Wind gusts and high wind speeds need to be considered in wind power industry and power grid management as they affect construction, material, siting and maintenance of turbines and power lines. Furthermore, gusts are an important information source on turbulence conditions in the atmosphere at the respective sites.<br>Often, the wind farm operators only provide basic data of the turbines such as average wind speed, direction, power and temperature. However, they require forecasts of gusts, too. Thus, a simple gust estimation algorithm based on the average wind speed was developed. The algorithm is tested at different mast measurement sites and WFIP2 data and applied to selected wind turbines. Results show that the algorithm is skillful enough to be used as a first guess gust estimation for single turbines and is, thus, used for nowcasting.<br>For nowcasting for the first two hours with a temporal fequency of ten minutes solely observations are used. A high-frequency wind speed and gust nowcasting ensemble based on different machine learning methodologies, including an ensemble for every method, was developd. Used are boosting, random forest, linear regression, a simple monte carlo method and a feed forward neural network. Results show that perturbing the observations provides a good forecasting spread for at least some of the methods. However, for other methods the spread is reduced significantly. Most of the used methods are able to provide good forecastst. However, hyperparameter tuning for the lightGBM boosting algorithm and the neural network is still needed.</p>

SHAPING OF AN AUTONOMOUS POWER SYSTEM FOR GUARANTEED POWER SUPPLY WITH THE PREDOMINANCE WIND ENERGY

2018 ◽  
pp. 28-50
Author(s):  
S. G. Ignatiev ◽  
S. V. Kiseleva
Keyword(s):  
Energy Storage ◽  
Wind Speed ◽  
Wind Energy ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Energy Demand ◽  
Diesel Generator ◽  
Average Wind Speed ◽  
Wind Speeds ◽  
Average Wind

Optimization of the autonomous wind-diesel plants composition and of their power for guaranteed energy supply, despite the long history of research, the diversity of approaches and methods, is an urgent problem. In this paper, a detailed analysis of the wind energy characteristics is proposed to shape an autonomous power system for a guaranteed power supply with predominance wind energy. The analysis was carried out on the basis of wind speed measurements in the south of the European part of Russia during 8 months at different heights with a discreteness of 10 minutes. As a result, we have obtained a sequence of average daily wind speeds and the sequences constructed by arbitrary variations in the distribution of average daily wind speeds in this interval. These sequences have been used to calculate energy balances in systems (wind turbines + diesel generator + consumer with constant and limited daily energy demand) and (wind turbines + diesel generator + consumer with constant and limited daily energy demand + energy storage). In order to maximize the use of wind energy, the wind turbine integrally for the period in question is assumed to produce the required amount of energy. For the generality of consideration, we have introduced the relative values of the required energy, relative energy produced by the wind turbine and the diesel generator and relative storage capacity by normalizing them to the swept area of the wind wheel. The paper shows the effect of the average wind speed over the period on the energy characteristics of the system (wind turbine + diesel generator + consumer). It was found that the wind turbine energy produced, wind turbine energy used by the consumer, fuel consumption, and fuel economy depend (close to cubic dependence) upon the specified average wind speed. It was found that, for the same system with a limited amount of required energy and high average wind speed over the period, the wind turbines with lower generator power and smaller wind wheel radius use wind energy more efficiently than the wind turbines with higher generator power and larger wind wheel radius at less average wind speed. For the system (wind turbine + diesel generator + energy storage + consumer) with increasing average speed for a given amount of energy required, which in general is covered by the energy production of wind turbines for the period, the maximum size capacity of the storage device decreases. With decreasing the energy storage capacity, the influence of the random nature of the change in wind speed decreases, and at some values of the relative capacity, it can be neglected.

scholarly journals The super-turbine wind power conversion paradox: using machine learning to reduce errors caused by Jensen's inequality

2019 ◽  
Vol 4 (2) ◽  
pp. 343-353 ◽  
Author(s):  
Tyler C. McCandless ◽  
Sue Ellen Haupt
Keyword(s):  
Machine Learning ◽  
Standard Deviation ◽  
Wind Speed ◽  
Wind Power ◽  
Power Conversion ◽  
Jensen’S Inequality ◽  
Jensen's Inequality ◽  
Average Wind Speed ◽  
Wind Speeds ◽  
Average Wind

Abstract. Wind power is a variable generation resource and therefore requires accurate forecasts to enable integration into the electric grid. Generally, the wind speed is forecast for a wind plant and the forecasted wind speed is converted to power to provide an estimate of the expected generating capacity of the plant. The average wind speed forecast for the plant is a function of the underlying meteorological phenomena being predicted; however, the wind speed for each turbine at the farm is also a function of the local terrain and the array orientation. Conversion algorithms that assume an average wind speed for the plant, i.e., the super-turbine power conversion, assume that the effects of the local terrain and array orientation are insignificant in producing variability in the wind speeds across the turbines at the farm. Here, we quantify the differences in converting wind speed to power at the turbine level compared with a super-turbine power conversion for a hypothetical wind farm of 100 2 MW turbines as well as from empirical data. The simulations with simulated turbines show a maximum difference of approximately 3 % at 11 m s−1 with a 1 m s−1 standard deviation of wind speeds and 8 % at 11 m s−1 with a 2 m s−1 standard deviation of wind speeds as a consequence of Jensen's inequality. The empirical analysis shows similar results with mean differences between converted wind speed to power and measured power of approximately 68 kW per 2 MW turbine. However, using a random forest machine learning method to convert to power reduces the error in the wind speed to power conversion when given the predictors that quantify the differences due to Jensen's inequality. These significant differences can lead to wind power forecasters overestimating the wind generation when utilizing a super-turbine power conversion for high wind speeds, and indicate that power conversion is more accurately done at the turbine level if no other compensatory mechanism is used to account for Jensen's inequality.

Estimation of average wind speed in the city of Tianguá using Artificial Neural Network

2021 ◽  
Author(s):  
Arilson F. G. Ferreira ◽  
Anderson P. de Aragao ◽  
Necio de L. Veras ◽  
Ricardo A. L. Rabelo ◽  
Petar Solic
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Wind Speed ◽  
Average Wind Speed ◽  
Average Wind ◽  
Artificial Neural ◽  
The City

scholarly journals A Simplified Morphing Blade for Horizontal Axis Wind Turbines

2013 ◽  
Vol 136 (1) ◽  
Author(s):  
Weijun Wang ◽  
Stéphane Caro ◽  
Fouad Bennis ◽  
Oscar Roberto Salinas Mejia
Keyword(s):  
Wind Speed ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Energy Production ◽  
Turbine Blades ◽  
Wind Turbine Blades ◽  
Annual Average ◽  
Average Wind Speed ◽  
Pitch Control ◽  
Average Wind

The aim of designing wind turbine blades is to improve the power capture ability. Since rotor control technology is currently limited to controlling rotational speed and blade pitch, an increasing concern has been given to morphing blades. In this paper, a simplified morphing blade is introduced, which has a linear twist distribution along the span and a shape that can be controlled by adjusting the twist of the blade's root and tip. To evaluate the performance of wind turbine blades, a numerical code based on the blade element momentum theory is developed and validated. The blade of the NREL Phase VI wind turbine is taken as a reference blade and has a fixed pitch. The optimization problems associated with the control of the morphing blade and a blade with pitch control are formulated. The optimal results show that the morphing blade gives better results than the blade with pitch control in terms of produced power. Under the assumption that at a given site, the annual average wind speed is known and the wind speed follows a Rayleigh distribution, the annual energy production of wind turbines was evaluated for three types of blade, namely, morphing blade, blade with pitch control and fixed pitch blade. For an annual average wind speed varying between 5 m/s and 15 m/s, it turns out that the annual energy production of the wind turbine containing morphing blades is 24.5% to 69.7% higher than the annual energy production of the wind turbine containing pitch fixed blades. Likewise, the annual energy production of the wind turbine containing blades with pitch control is 22.7% to 66.9% higher than the annual energy production of the wind turbine containing pitch fixed blades.

Feasibility of Small Wind Turbine via Net Metering in Greek Islands

2021 ◽  
Vol 1 (1) ◽  
pp. 23-28
Author(s):  
D. Daskalaki ◽  
J. Fantidis ◽  
P. Kogias
Keyword(s):  
Wind Speed ◽  
Greenhouse Gases ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Average Wind Speed ◽  
Small Wind Turbine ◽  
Net Metering ◽  
Average Wind ◽  
Environmental Criteria ◽  
Small Wind Turbines

The evaluation of a small 3kW wind turbine through the net metering scheme is studied in this article. 14 near to sea locations in Greece examined with the help of the RetScreen expert software. The simulations based on electrical, financial and environmental criteria. Siros with average wind speed of 6.93 m/s is the most attractive area while Iraklion is the least attractive location. According to the results the simulated project is already economically sound and a small wind turbine in the Greek islands will become a progressively an even more financially source of electricity in Greece. Finally yet importantly is the fact that the use of small wind turbines has as a result that significant amount of Greenhouse gases do not reradiate into the topical atmosphere.

scholarly journals The Super-Turbine Wind Power Conversion Paradox: Using Machine Learning to Reduce Errors Caused by Jensen’s Inequality

2019 ◽  
Author(s):  
Tyler C. McCandless ◽  
Sue Ellen Haupt
Keyword(s):  
Machine Learning ◽  
Standard Deviation ◽  
Wind Speed ◽  
Wind Power ◽  
Power Conversion ◽  
Jensen’S Inequality ◽  
Jensen's Inequality ◽  
Average Wind Speed ◽  
Wind Speeds ◽  
Average Wind

Abstract. Wind power is a variable generation resource and therefore requires accurate forecasts to enable integration into the electric grid. Generally, the wind speed is forecast for a wind plant and the forecasted wind speed is converted to power to provide an estimate of the expected generating capacity of the plant. The average wind speed forecast for the plant is a function of the underlying meteorological phenomena being predicted; however, the wind speed for each turbine at the farm is also a function of the local terrain and the array orientation. Conversion algorithms that assume an average wind speed for the plant, i.e., the super-turbine power conversion, assume that the effects of the local terrain and array orientation are insignificant in producing variability in the wind speeds across the turbines at the farm. Here, we quantify the differences in converting wind speed to power at the turbine level compared to a super-turbine power conversion for a hypothetical wind farm of 100 2-MW turbines as well as from empirical data. The simulations with simulated turbines show a maximum difference of approximately 3 % at 11 m s−1 with 1 m s−1 standard deviation of wind speeds and 8 % at 11 m s−1 with 2 m s−1 standard deviation of wind speeds as a consequence of Jensen’s Inequality. The empirical analysis shows similar results with mean differences between converted wind speed to power and measured power of approximately 68 kW per 2 MW turbine. However, using a random forest machine learning method to convert to power reduces the error in the wind speed to power conversion when given the predictors that quantify the differences due to Jensen’s Inequality. These significant differences can lead to wind power forecasters over-estimating the wind generation when utilizing a super-turbine power conversion for high wind speeds, and indicates that power conversion is more accurately done at the turbine level if no other compensatory mechanism is used to account for Jensen’s Inequality.

Application of a Genetic Algorithm to Wind Turbine Design

1996 ◽  
Vol 118 (1) ◽  
pp. 22-28 ◽  
Author(s):  
M. S. Selig ◽  
V. L. Coverstone-Carroll
Keyword(s):  
Genetic Algorithm ◽  
Wind Speed ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Energy Production ◽  
Turbine Blades ◽  
Hybrid Approach ◽  
Optimization Method ◽  
Average Wind Speed ◽  
Average Wind

This paper presents an optimization method for stall-regulated horizontal-axis wind turbines. A hybrid approach is used that combines the advantages of a genetic algorithm with an inverse design method. This method is used to determine the optimum blade pitch and blade chord and twist distributions that maximize the annual energy production. To illustrate the method, a family of 25 wind turbines was designed to examine the sensitivity of annual energy production to changes in the rotor blade length and peak rotor power. Trends are revealed that should aid in the design of new rotors for existing turbines. In the second application, five wind turbines were designed to determine the benefits of specifically tailoring wind turbine blades for the average wind speed at a particular site. The results have important practical implications related to rotors designed for the Midwestern US versus those where the average wind speed may be greater.

ANALISA PERFORMA TURBIN ANGIN SUMBU HORISONTAL BERSUDU AIRFOIL MELALUI VARIASI JUMLAH SUDU

ROTOR ◽  
2018 ◽  
Vol 11 (2) ◽  
pp. 18
Author(s):  
Wabang A Jhon ◽  
Abanat D.J Jufra ◽  
Hattu Edwin
Keyword(s):  
Wind Speed ◽  
Kinetic Energy ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Mechanical Energy ◽  
Coefficient Of Performance ◽  
Research Activity ◽  
Average Wind Speed ◽  
Wind Speeds ◽  
Average Wind

Indonesia is an area that has the potential for sufficient wind resources to be utilized for kinetic energy into other energy such as mechanical energy and electrical energy through its generators (generators). The way to utilize wind kinetic energy into other energy is through a device called a wind turbine. Wind turbines have been around since ancient times, and are called airfoil angled wind turbines. This airfoil wind turbine is designed only for areas with average wind speeds above 6m / s. While in Indonesia not all regions have the same wind speed. In certain seasons, the average wind speed is below 6 m / s. This has become a major problem in regions that have average wind speeds below 6 m / s. Seeing this condition, there is a need for scientific research to obtain wind turbines that can be used in areas with average wind speeds below 5m / s. For this reason, the research I want to do is get a wind turbine that can be used as a power plant in areas that have wind speeds below 6m / s. This research was conducted on the basis of scientific theory in fluid mechanics regarding the sweeping area of wind turbines and the performance of variations in the number of blades in the wind. In addition, the research in several scientific journals was used as the basis of this research This research method is an experimental method, in the form of testing a wind turbine axis prototype horizontal and airfoil axis. The details of the research activity are the design and manufacture of laboratory scale horizontal airfoil axis turbines. Next, testing with a fan as a source of wind. The fan used has three variations of speed, all of which are used to determine the lowest average wind speed that can be applied. The results of the research are where wind turbines with the greatest torque and power and the Coefficient of Performance (CP) with the highest value will be used as a result to be applied to the community. Based on experimental data, it can be concluded that the greatest torque and power occur in turbines with 4 blades with details at speed 1, the largest torque and power are 0.201 Nm and 4.5 W; at speed 2, the biggest torque and power are 0.25 Nm and 7.21 W; at speed 3, the biggest torque and power are 0.28 Nm and 8.35 W Keywords: wind turbine, airfoil, nozzle, diffuser

scholarly journals Lake Michigan Wind Assessment Analysis, 2012 and 2013

2017 ◽  
Vol 6 (1) ◽  
pp. 19-27
Author(s):  
Charles R Standridge ◽  
Daivd Zeitler ◽  
Aaron Clark ◽  
Tyson Spoolma ◽  
Erik Nordman ◽  
...  
Keyword(s):  
Wind Speed ◽  
Wind Energy ◽  
Wind Farm ◽  
Lake Michigan ◽  
Floating Platform ◽  
Energy Potential ◽  
Average Wind Speed ◽  
Average Wind ◽  
Wind Energy Potential ◽  
Lower Height

A study was conducted to address the wind energy potential over Lake Michigan to support a commercial wind farm.  Lake Michigan is an inland sea in the upper mid-western United States.  A laser wind sensor mounted on a floating platform was located at the mid-lake plateau in 2012 and about 10.5 kilometers from the eastern shoreline near Muskegon Michigan in 2013.  Range gate heights for the laser wind sensor were centered at 75, 90, 105, 125, 150, and 175 meters.  Wind speed and direction were measured once each second and aggregated into 10 minute averages.  The two sample t-test and the paired-t method were used to perform the analysis.  Average wind speed stopped increasing between 105 m and 150 m depending on location.  Thus, the collected data is inconsistent with the idea that average wind speed increases with height. This result implies that measuring wind speed at wind turbine hub height is essential as opposed to using the wind energy power law to project the wind speed from lower heights.  Average speed at the mid-lake plateau is no more that 10% greater than at the location near Muskegon.  Thus, it may be possible to harvest much of the available wind energy at a lower height and closer to the shoreline than previously thought.  At both locations, the predominate wind direction is from the south-southwest.  The ability of the laser wind sensor to measure wind speed appears to be affected by a lack of particulate matter at greater heights.Article History: Received June 15th 2016; Received in revised form January 16th 2017; Accepted February 2nd 2017 Available onlineHow to Cite This Article: Standridge, C., Zeitler, D., Clark, A., Spoelma, T., Nordman, E., Boezaart, T.A., Edmonson, J.,  Howe, G., Meadows, G., Cotel, A. and Marsik, F. (2017) Lake Michigan Wind Assessment Analysis, 2012 and 2013. Int. Journal of Renewable Energy Development, 6(1), 19-27.http://dx.doi.org/10.14710/ijred.6.1.19-27

Sign in / Sign up

Export Citation Format

Share Document