scholarly journals Stochastic Extreme Wind Speed Modeling and Bayes Estimation under the Inverse Rayleigh Distribution

2020 ◽  
Vol 10 (16) ◽  
pp. 5643
Author(s):  
Elio Chiodo ◽  
Luigi Pio Di Noia
Keyword(s):  
Wind Speed ◽  
Prior Information ◽  
Extreme Values ◽  
Risk Index ◽  
Rayleigh Distribution ◽  
Bayes Estimation ◽  
Large Set ◽  
Extreme Wind ◽  
System Engineer ◽  
Extreme Wind Speed

Inverse Rayleigh probability distribution is shown in this paper to constitute a valid model for characterization and estimation of extreme values of wind speed, thus constituting a useful tool of wind power production evaluation and mechanical safety of installations. The first part of this paper illustrates such a model and its validity to interpret real wind speed field data. The inverse Rayleigh model is then adopted as the parent distribution for assessment of a dynamical “risk index” defined in terms of a stochastic Poisson process, based upon crossing a given value with part of the maximum value of wind speed on a certain time horizon. Then, a novel Bayes approach for the estimation of such an index under the above model is proposed. The method is based upon assessment of prior information in a novel way which should be easily feasible for a system engineer, being based upon a model quantile (e.g., the median value) or, alternatively, on the probability that the wind speed is greater than a given value. The results of a large set of numerical simulation—based upon typical values of wind-speed parameters—are reported to illustrate the efficiency and the precision of the proposed method, also with hints to its robustness. The validity of the approach is also verified with respect to the two different methods of assessing the prior information.

scholarly journals The Compound Inverse Rayleigh as an Extreme Wind Speed Distribution and its Bayes Estimation

2021 ◽  
Author(s):  
Elio Chiodo ◽  
Maurizio Fantauzzi ◽  
Giovanni Mazzanti
Keyword(s):  
Wind Speed ◽  
Prior Information ◽  
Extreme Values ◽  
Rayleigh Distribution ◽  
Bayes Estimation ◽  
Large Set ◽  
Wind Speeds ◽  
Extreme Wind ◽  
Extreme Wind Speed ◽  
Extreme Wind Speeds

The paper deals with the Compound Inverse Rayleigh distribution, shown to constitute a proper model for the characterization of the probability distribution of extreme values of wind-speed, a topic which is gaining growing interest in the field of renewable generation assessment, both in view of wind power production evaluation and the wind-tower mechanical reliability and safety. The first part of the paper illustrates such model starting from its origin as a generalization of the Inverse Rayleigh model - already proven to be a valid model for extreme wind-speeds - by means of a continuous mixture generated by a Gamma distribution on the scale parameter, which gives rise to its name. Moreover, its validity to interpret different field data is illustrated, also by means of numerous numerical examples based upon real wind speed measurements. Then, a novel Bayes approach for the estimation of such extreme wind-speed model is proposed. The method relies upon the assessment of prior information in a practical way, that should be easily available to system engineers. In practice, the method allows to express one’s prior beliefs both in terms of parameters, as customary, and/or in terms of probabilities. The results of a large set of numerical simulations – using typical values of wind-speed parameters - are reported to illustrate the efficiency and the accuracy of the proposed method. The validity of the approach is also verified in terms of its robustness with respect to significant differences compared to the assumed prior information.

scholarly journals Global Estimates of Extreme Wind Speed and Wave Height

2011 ◽  
Vol 24 (6) ◽  
pp. 1647-1665 ◽  
Author(s):  
J. Vinoth ◽  
I. R. Young
Keyword(s):  
Wind Speed ◽  
Wave Height ◽  
Return Period ◽  
Significant Wave Height ◽  
Extreme Values ◽  
Significant Wave ◽  
Extreme Wind ◽  
Extreme Wind Speed ◽  
Global Estimates ◽  
Buoy Measurements

Abstract A long-term dataset of satellite altimeter measurements of significant wave height and wind speed, spanning 23 years, is analyzed to determine extreme values corresponding to a 100-yr return period. The analysis considers the suitability of both the initial distribution method (IDM) and peaks-over-threshold (POT) approaches and concludes that for wave height both IDM and POT methods can yield reliable results. For the first time, the global POT results for wave height show spatial consistency, a feature afforded by the larger dataset. The analyses also show that the POT approach is sensitive to spatial resolution. Since wind speed has greater spatial and temporal variability than wave height, the POT approach yields unreliable results for wind speed as a result of undersampling of peak events. The IDM approach does, however, generate extreme wind speed values in reasonable agreement with buoy estimates. The results show that the altimeter database can estimate 100-yr return period significant wave height to within 5% of buoy measurements and the 100-yr wind speed to within 10% of buoy measurements when using the IDM approach. Owing to the long dataset and global coverage, global estimates of extreme values can be developed on a 1° × 1° grid when using the IDM and a coarser 2° × 2° for the POT approach. The high-resolution 1° × 1° grid together with the long duration of the dataset means that finescale features not previously identified using altimeter data are clearly apparent in the IDM results. Goodness-of-fit tests show that the observed data conform to a Fisher–Tippett Type 1 (FT-1) distribution. Even in regions such as the Gulf of Mexico where extreme forcing is produced by small-scale hurricanes, the altimeter results are consistent with buoy data.

scholarly journals Inverse Log-logistic distribution for Extreme Wind Speed modeling: Genesis, identification and Bayes estimation

AIMS Energy ◽  
2018 ◽  
Vol 6 (6) ◽  
pp. 926-948 ◽  
Author(s):  
Elio Chiodo ◽  
◽  
Pasquale De Falco ◽  
Luigi Pio Di Noia ◽  
Fabio Mottola ◽  
...  
Keyword(s):  
Wind Speed ◽  
Bayes Estimation ◽  
Logistic Distribution ◽  
Extreme Wind ◽  
Extreme Wind Speed

scholarly journals Time Series Analysis on Incidence of Pulmonary Tuberculosis With Weather Factors During 2004-2017 in Guangdong Province, China

2021 ◽  
Author(s):  
Tianyu Qin ◽  
Yu Hao ◽  
Juan He
Keyword(s):  
Wind Speed ◽  
Atmospheric Pressure ◽  
Guangdong Province ◽  
Maximum Temperature ◽  
Maximum Pressure ◽  
Weather Factors ◽  
Sarima Model ◽  
Extreme Wind ◽  
Wind Speed Maximum ◽  
Extreme Wind Speed

Abstract Background: Although the occurrence of some infectious diseases including TB was found to be associated with specific weather factors, few studies have incorporated weather factors into the model to predict the incidence of tuberculosis (TB). We aimed to establish an accurate forecasting model using TB data in Guangdong Province, incorporating local weather factors.Methods: Data of sixteen meteorological variables (2003-2016) and the TB incidence data (2004-2016) of Guangdong were collected. Seasonal autoregressive integrated moving average (SARIMA) model was constructed based on the data. SARIMA model with weather factors as explanatory variables (SARIMAX) was performed to fit and predict TB incidence in 2017. Results: Maximum temperature, maximum daily rainfall, minimum relative humidity, mean vapor pressure, extreme wind speed, maximum atmospheric pressure, mean atmospheric pressure and illumination duration were significantly associated with log(TB incidence). After fitting the SARIMAX model, maximum pressure at lag 6 (β= -0.007, P < 0.05, 95% confidence interval (CI): -0.011, -0.002, mean square error (MSE): 0.279) was negatively associated with log(TB incidence), while extreme wind speed at lag 5 (β=0.009, P < 0.05, 95% CI: 0.005, 0.013, MSE: 0.143) was positively associated. SARIMAX (1, 1, 1) (0, 1, 1)12 with extreme wind speed at lag 5 was the best predictive model with lower Akaike information criterion (AIC) and MSE. The predicted monthly TB incidence all fall within the confidence intervals using this model. Conclusions: Weather factors have different effects on TB incidence in Guangdong. Incorporating meteorological factors into the model increased the accuracy of prediction.

Sign in / Sign up

Export Citation Format

Share Document