International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-9 Issue-12, October 2020 369 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Retrieval Number: 100.1/ijitee.K78530991120 DOI: 10.35940/ijitee.K7853.1091220 Neuron Network Prediction Feed- Forwad Wind Speed Network on Mauritania's North Coast: Ballawack Case Soukeyna Mohamed, Diene Ndiaye, Sidi Mohamed Mustapha, Abdel Kader Mahmoud Abstract: The assessment of the suitability of a wind system depends largely on the prediction of the wind potential. Indeed, the variability and uncertainty inherent in renewable energy sources can have a significant impact on accurate and reliable prediction of the power produced. Wind sources are needed at different time stages and at different altitudes. Thus, putting in place tools for predicting these wind resources is essential for their effective integration in the frame of electricity generation. In this context, the paper of this study is to propose a short-term wind energy prediction method through the formation of historical wind velocity data based on neural networks. This assessment involves modelling wind speed using ANN through the feed-forwad network. So, ANN are at the basis of adaptive identification methods and intelligent command laws. In this sense, first, the process of forecasting wind energy involves the creation of a raw data base, which is then filtered by probabilistic neural network. More concretely, the contribution of the work can be given in the form of technical results. These results start with a proposal of the theoretical models, then it is given the approach method that is used, then it is proposed the design of the system and the whole is closed by a performance evaluation. As far as performance evaluation is concerned, it is presented in the form of the results of analysed simulations of the forecast model. In practical terms, it should be noted that the proposed model also provides a high degree of accuracy for the measured data. In the end, normalized average absolute errors were recorded between 4.7% and 4.9%. As, it was found a regression factor R (measures the correlation between output-Target) between 91% and 96% for the site of the northern Mauritanian coast. This is largely acceptable for similar calculations. Keywords: Artificial Neural Networks (ANN), MATLAB, Mathematical model, Mauritanian north coast, Wind speed prediction, Wind power prediction Abbreviations: ANN, Artificial Neural Networks; GA, Genetic Algorithm I. INTRODUCTION It is important to note that in the bibliography [1, 2, 3, 4], a multitude of prediction methods of varying utility are discussed. Revised Manuscript Received on October 10, 2020. Soukeyna Mohamed, Assistant Professor, Department of physic Nouakchott, (Applied Research Laboratory for Renewable Energies (LRAER), Université de Nouakchott, Al-Aasriya (UNA), Mauritanie E- mail: soukwewe@gmail.com Diene Ndiaye, Associate Professor, Department of physic, saint-louis, (Laboratory of Electronic, Computing, Telecommunication and Renewable Energies (LEITER), UGB, Saint-Louis, Senegal.), Senegal E-mail: Ndiaye- diene@yahoo.fr Sidi Mohamed Mustapha, Assistant Professor, Department of physic Nouakchott, (Applied Research Laboratory for Renewable Energies (LRAER), Université de Nouakchott, Al-Aasriya (UNA), Mauritanie E- mail: sidi-mustapha@yahoo.fr Abdel Kader Mahmoud, Assistant Professor, Department of physic Nouakchott, (Applied Research Laboratory for Renewable Energies (LRAER), Université de Nouakchott, Al-Aasriya (UNA), Mauritanie E- mail: nakader@yahoo.fr If, the first gives the predictions of natural disasters that fall within the framework of the security of people and their property (example earthquakes in the Indonesian region), on the other hand the second article talks about machine learning algorithms and validates the results using Mean Absolute Error (MAE) and Mean Square Error (RMSE). It is also possible to cite the example in [3] for the improvement of technical systems on the basis of the genetic algorithm (GA).Without forgetting, the article [4] whose author proposes an innovative approach to finding response keywords from a given corpus of news or data titles, realized with the use of Gated Recurrent Unit (GRU). Thus, in the present paper, the problem posed is that a large part of the sites of the Mauritanian coast are isolated from the national electricity grid and their majority are inhabited by sinners, without drinking water for their food needs, without means of conservation for their fishery products. These problems can find the solution through the wind application which has environmental protection benefits of these sites. In fact, wind speed forecasts can help to determine and optimize the location of weather observation station networks that are able to detect sites with the best wind potential [5] estimate the electricity production associated with daily operations as in [6]. With regard to the accuracy of forecast models, to be predicted, an example is proposed in [7] which is the high-quality model by NWP (Numerical Wearther Prediction), but has not been used for wind power.On the other hand, the model proposed in [8] is available every hour within the forecast horizon up to 12 hours or more, to take into account the influence of local speed and wind direction. It uses a data exploration approach with a model neighbouring k-plus. In the end, the approach chosen for this paper which v& guide our work will be summarized as follows: in part (2) it will be presented the site, as, it will be proposed in (3) the structures of neuron networks of type feed- forwad. Then, the results will be proposed in part (3) as a theoretical development of the neural networks feed-forwad. In addition, it will be given in these results the approach of the algorithm. Then, it will be proposed the system design by data preparation which is followed by an evaluation of the performance of the prediction method and in the end, a conclusion will be made to close this work. A. Brief description of study area The locality of BALLAWACK is located in the northern zone of the Mauritanian coast. It is located on the edge of the Atlantic Ocean between the town of Nouakchott to the south and the town of Nouadhibou to the north (latitude 18.52° and longitude 16.07°).