Enhanced recurrent neural network for short-term wind farm power output prediction

Eze, Ethelbert Chinedu and Chatwin, Chris R (2019) Enhanced recurrent neural network for short-term wind farm power output prediction. IJRDO - Journal of Applied Science, 5 (2). pp. 28-35. ISSN 2455-6653

[img] PDF - Published Version
Available under License Creative Commons Attribution-NonCommercial No Derivatives.

Download (1MB)

Abstract

Scientists, investors and policy makers have become aware of the importance of providing near accurate spatial estimates of renewable energies. This is why current studies show improvements in methodologies to provide more precise energy predictions. Wind energy is tied to weather patterns, which are irregular, especially in climates with erratic weather patterns. This can lead to errors in the predicted potentials. Therefore, recurrent neural networks (RNN) are exploited for enhanced wind-farm power output prediction. A model involving a combination of RNN regularization methods using dropout and long short-term memory (LSTM) is presented. In this model, the regularization scheme modifies and adapts to the stochastic nature of wind and is optimised for the wind farm power output (WFPO) prediction. This algorithm implements a dropout method to suit non-deterministic wind speed by applying LSTM to prevent RNN from overfitting. A demonstration for accuracy using the proposed method is performed on a 14-turbines wind farm. The model out performs the ARIMA model with up to 80% accuracy.

Item Type: Article
Keywords: Wind Power Output Prediction, Recurrent Neural Network, Deep learning, oLSTM, ARIMA, RMSE, MSE.
Schools and Departments: School of Engineering and Informatics > Informatics
School of Engineering and Informatics > Engineering and Design
Research Centres and Groups: Industrial Informatics and Signal Processing Research Group
Subjects: Q Science > QA Mathematics > QA0273 Probabilities. Mathematical statistics
Q Science > QA Mathematics > QA0299 Analysis. Including analytical methods connected with physical problems
T Technology > TJ Mechanical engineering and machinery
T Technology > TJ Mechanical engineering and machinery > TJ0163.13 Power resources
T Technology > TJ Mechanical engineering and machinery > TJ0163.26 Energy conservation
T Technology > TJ Mechanical engineering and machinery > TJ0212 Control engineering systems. Automatic machinery (General)
T Technology > TJ Mechanical engineering and machinery > TJ0266 Turbines. Turbomachines (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1001 Production of electric energy or power. Powerplants. Central stations
Depositing User: Chris Chatwin
Date Deposited: 07 Mar 2019 11:19
Last Modified: 01 Jul 2019 19:16
URI: http://sro.sussex.ac.uk/id/eprint/82364

View download statistics for this item

📧 Request an update