The objective of this work is to present a comprehensive exploration of deep learning based wind forecasting model. The forecasting of speed of wind is called as the wind speed forecasting/prediction. It is basically done to achieve the better sustainability for power generation and production. The availability of wind energy in ample amount makes it quite comfortable to be utilized for various functionalities. In this research work the main aim is to forecast speed using LSTM including certain parameters and then comparative analysis is done using SVM. Both are machine learning approaches but have different functionalities in comparison to each other. This comparison is done to obtain the better technique which can be further applied on larger datasets to design a better, accurate, efficient forecasting model for speed of wind. The survey and implementation of both the techniques gave a clear idea about the utilisation of long short term memory for the better and enhanced wind speed forecasting. The forecasting is based on various atmospheric variables, and the data set is taken from the kaggle datsets which have numerous attributes but we have considered few of them only for the prediction purpose.

No abstract

No abstract

In modern years, wind energy has a significant development in the world. However, one of the major issues of power generated from wind is its uncertainty and resultant power. To solve the above-said problem, few approaches have been presented. In recent times, the Artificial Neural Networks (ANN) as a heuristic method has more applications for this propose. The Back-propagation (BP) neural network is then provided with the data to establish the relationship between the inputs and the output. Measured wind speeds, temperature, pressure and wind speed predicted outputs with each 10-min resolution for 15 th January 2015(24 hours) an existing wind power station, located at VSB-TUO, Ostrava, are integrated to form three types of input neuron numbers. In this, paper presents a short -term power prediction for a wind power plant located at VSB-TUO, Ostrava using multilayer ANN approach. Simulation results are reported, showing that the estimated wind speed values (predicted by the proposed network) are in good agreement with the experimental measured values.

Stereo Cartosat-1 satellite data was processed to generate high spatial resolution digital elevation model (DEM) using ground control points (GCPs) collected through geodetic single frequency GPS in differential GPS mode. DEM was processed to generate bare earth DEM by removing heights of natural and man made features from DEM. The bare earth DEM was further analysed in GIS environment to generate terrain-topographic indices viz. wetness index (WI), stream power index (SPI) and sediment transport index (STI) to characterize topographic potential of soil erosion. Hillslopes in the studied watershed (part of Shiwalik hills of Dehradun district, Uttarakhand state) were characterized as low wetness index values indicating dry areas whereas high wetness index values at lower reaches of the watershed indicating as possible source areas for generation of saturated overland fl ow. Higher STI values were observed in hilly as well as upper part of the piedmont plain and at along sides of the streams in upper piedmont indicating areas susceptible to severe soil erosion. GIS based these topographic indices provided an easy and quick appraisal and scientifi c basis to identify spatial variability of soil erosion risk in a hilly watershed.