Application of stacked and bidirectional long short-term memory deep learning models for wind speed forecasting at an offshore site

ABSTRACT

Very short-term offshore wind speed forecasting by application of Stacked long short-term memory (LSTM) and Bidirectional LSTM deep learning models is done in this work. Wind speed data of two different offshore sites located in two different continents are used for testing the models. Performance is measured on the basis of accuracy of forecasting and computational time. The effectiveness of Stacked LSTM and Bidirectional LSTM models is also validated by comparing their performance with convolutional neural network, convolutional neural network-long short-term memory network, multi-layer perceptron, and rolling forecasting auto regressive integrated moving average models. Results of forecasting error confirm that Stacked LSTM model is better than other compared models in forecasting very short-term offshore wind speed. Mean absolute percentage error (MAPE) of wind speed forecasting by Stacked LSTM model is 4.59% at Anholt (Denmark) and 3.62% at Dhanushkodi (India) sites. From comparison of MAPE of Stacked LSTM model with that of eight other latest existing models in literature, it can be concluded that Stacked LSTM model is superior to many other existing models.

KEYWORDS:

• Deep learning
• long short-term memory
• offshore wind
• wind speed forecasting
• wind energy

Data availability statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Competing interests

The authors declare that they have no potential competing interest.

Additional information

Notes on contributors

Bharat Kumar Saxena

Bharat Kumar Saxena is presently PhD research scholar at Department of Renewable Energy, Rajasthan Technical University (RTU), Kota, Rajasthan, India. He obtained Master of Technology (Hons.) degree in Renewable Energy Technology from University College of Engineering, RTU, Kota in 2014 and Bachelor of Engineering (Hons.) degree in Electrical Engineering from Engineering College, Kota affiliated to University of Rajasthan, Jaipur, India in 2000. His current research interests include renewable energy, solar photovoltaic, wind energy, and application of artificial intelligence and machine learning in renewable energy. Earlier, he was Chief Executive and Principal Investigator at a not-for-profit organization and has served the rural community in the fields of sustainable technologies, environment, and energy.

Sanjeev Mishra

Sanjeev Mishra is Professor in Department of Mechanical Engineering and is former Head of Department of Renewable Energy, Rajasthan Technical University (RTU), Kota, India. He is also currently Chairman of Departmental Research Committee & Convener of Board of Studies of Renewable Energy at RTU, Kota. He obtained PhD degree from Indian Institute of Technology, Kanpur in year 2004. His research interests include renewable energy, nanotechnology, operations research, and quality management.

Komaragiri Venkata Subba Rao

Komaragiri Venkata Subba Rao is Professor in mechanical engineering and obtained PhD degree from Indian Institute of Technology, Delhi in 1996 and Master of Technology degree from Indian Institute of Technology, Kanpur in year 1984. He has a vast administrative, teaching, and research experience of working at Department of Mechanical Engineering and Department of Renewable Energy at Rajasthan Technical University, Kota, India. Presently, he is Principal of Gayatri Vidya Parishad College of Engineering for Women at Visakhapatnam, Andhra Pradesh, India. His research interest includes harnessing solar energy and wind energy.