2026-09-22T03:15:33Zhttps://repository.rice.edu/server/oai/request

oai:repository.rice.edu:1911/1057682024-01-11T20:59:03Zcom_1911_8299col_1911_13110

Meade, Andrew J Qormemeti, Arti 2019-05-17T15:20:04Z 2019-05-17T15:20:04Z 2018-05 2018-04-19 May 2018 2019-05-17T15:20:04Z Qormemeti, Arti. "Wind Speed Forecasting for Power Generation Using a Self-Assembling Closed-Loop Recurrent Neural Network." (2018) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/105768">https://hdl.handle.net/1911/105768</a>. https://hdl.handle.net/1911/105768 This thesis presents the self-assembling recurrent neural network, SFA (Sequential Function Approximation), as a time series forecasting method for wind speed prediction. We compare its multi-step prediction performance against a proven recurrent neural network, NARX (Non-linear Auto-Regressive neural network with eXogenous inputs), on several univariate and multivariate time series, including weather measurements from the Bogdanci Wind Park in Macedonia. Artificial neural networks, such as NARX, require a good deal of trial and error in finding the optimal network configuration. Training these types of networks also comes with high fluctuations in closed-loop prediction performance on each training initialization due to parameter randomization. The SFA method sidesteps these drawbacks while providing comparable or better prediction. This is achieved with the SFA algorithm assembling the input-output mapping by itself to achieve a tolerance set by the user. application/pdf eng Copyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder. Machine learning Artificial Intelligence Neural Networks NARX SFA Sequential Function Approximation Nonlinear Autoregressive network with Exogenous inputs Time Series Forecasting Prediction Wind speed Wind Power Wind Speed Forecasting for Power Generation Using a Self-Assembling Closed-Loop Recurrent Neural Network Thesis Text Mechanical Engineering Engineering Rice University Masters Master of Science open.access