Picture offshore wind farm

Open Access research that is improving renewable energy technology...

Strathprints makes available scholarly Open Access content by researchers across the departments of Mechanical & Aerospace Engineering (MAE), Electronic & Electrical Engineering (EEE), and Naval Architecture, Ocean & Marine Engineering (NAOME), all of which are leading research into aspects of wind energy, the control of wind turbines and wind farms.

Researchers at EEE are examining the dynamic analysis of turbines, their modelling and simulation, control system design and their optimisation, along with resource assessment and condition monitoring issues. The Energy Systems Research Unit (ESRU) within MAE is producing research to achieve significant levels of energy efficiency using new and renewable energy systems. Meanwhile, researchers at NAOME are supporting the development of offshore wind, wave and tidal-current energy to assist in the provision of diverse energy sources and economic growth in the renewable energy sector.

Explore Open Access research by EEE, MAE and NAOME on renewable energy technologies. Or explore all of Strathclyde's Open Access research...

Time-series Gaussian process regression based on toeplitz computation of O(N2) operations and O(N)-level storage

Zhang, Y. and Leithead, W.E. and Leith, D.J. (2005) Time-series Gaussian process regression based on toeplitz computation of O(N2) operations and O(N)-level storage. In: Proceedings of the 44th IEEE Conference on Decision and Control, 2005 and 2005 European Control Conference. CDC-ECC '05. IEEE, pp. 3711-3716. ISBN 0-7803-9567-0

Full text not available in this repository. Request a copy from the Strathclyde author

Abstract

Gaussian process (GP) regression is a Bayesian nonparametric model showing good performance in various applications. However, its hyperparameter-estimating procedure may contain numerous matrix manipulations of O(N3) arithmetic operations, in addition to the O(N2)-level storage. Motivated by handling the real-world large dataset of 24000 wind-turbine data, we propose in this paper an efficient and economical Toeplitz-computation scheme for time-series Gaussian process regression. The scheme is of O(N2) operations and O(N)-level memory requirement. Numerical experiments substantiate the effectiveness and possibility of using this Toeplitz computation for very large datasets regression (such as, containing 10000~100000 data points).