Speakers
Description
This workshop will focus on the integration of geospatial datasets, and deep
learning algorithms for real-time monitoring and forecasting of offshore wind
energy. The session will cover the framework for data retrieval, pre-processing,
integration of remotely sensed datasets and the development of predictive models
to optimize wind turbine performance. After developing the predictive models, we
will integrate climate scenarios to forecast the state of wind in real-time
monitoring and near-future prediction. Participants will learn how to integrate
cutting-edge geospatial, and meteorological datasets with deep learning
algorithms to predict energy production. The workshop will provide valuable
insights for renewable energy-related professionals and stakeholders on how
geospatia
The global demand for renewable energy, particularly wind energy, is escalating due to the urgent need to combat climate change and decrease reliance on fossil fuels. The study aims to develop a system using geospatial data and deep learning techniques for monitoring and forecasting wind energy. The study seeks to answer three key questions: (i) to develop a framework for integrating and processing geospatial big data for wind energy monitoring. (ii) implement a near-real-time data acquisition pipeline for continuous monitoring, and (iii) develop a predictive model using deep learning algorithms and statistical methods. The use of geospatial and meteorological datasets, turbine performance data (wind speed and direction, theoretical power and active power) and Recurring Neural Network -Long Short-Term Memory will enable near-real-time monitoring and prediction of wind energy. The model performance will be evaluated using statistical indicators like stability tests and forecast accuracy metrics like MAE and RMSE, to measure its stability under different conditions. The proposed model will be used to provide accurate wind patterns and energy potential insights, thereby optimizing wind turbine performance and energy production through the integration of various datasets. The study’s results will enhance wind energy predictions, aid in better grid planning, decrease fossil fuel reliance, and enhance grid stability.
Keywords: Deep Learning, geospatial Big data, remote Sensing, wind energy
