Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Power Prediction of Airborne Wind Energy Systems Using Multivariate Machine Learning

Journal Article · · Energies (Basel)
DOI:https://doi.org/10.3390/en13092367· OSTI ID:1644068

Kites can be used to harvest wind energy at higher altitudes while using only a fraction of the material required for conventional wind turbines. In this work, we present the kite system of Kyushu University and demonstrate how experimental data can be used to train machine learning regression models. The system is designed for 7 kW traction power and comprises an inflatable wing with suspended kite control unit that is either tethered to a fixed ground anchor or to a towing vehicle to produce a controlled relative flow environment. A measurement unit was attached to the kite for data acquisition. To predict the generated tether force, we collected input–output samples from a set of well-designed experimental runs to act as our labeled training data in a supervised machine learning setting. We then identified a set of key input parameters which were found to be consistent with our sensitivity analysis using Pearson input–output correlation metrics. Finally, we designed and tested the accuracy of a neural network, among other multivariate regression models. The quality metrics of our models show great promise in accurately predicting the tether force for new input/feature combinations and potentially guide new designs for optimal power generation.

Research Organization:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); European Union Horizon 2020
Grant/Contract Number:
AC04-94AL85000; 642682
OSTI ID:
1644068
Report Number(s):
SAND-2020-3742J; 685128
Journal Information:
Energies (Basel), Vol. 13, Issue 9; ISSN 1996-1073
Publisher:
MDPI AGCopyright Statement
Country of Publication:
United States
Language:
English

References (19)

Crosswind kite power (for large-scale wind power production) journal May 1980
Machine learning applications in cancer prognosis and prediction journal January 2015
Using machine learning to predict wind turbine power output journal April 2013
Predictive Control of Autonomous Kites in Tow Test Experiments journal July 2017
Adaptive Flight Path Control of Airborne Wind Energy Systems journal February 2020
Improving reliability and safety of airborne wind energy systems journal February 2020
System identification, fuzzy control and simulation of a kite power system with fixed tether length journal January 2018
Airborne Wind Energy Systems: A review of the technologies journal November 2015
Machine learning ensembles for wind power prediction journal April 2016
Simplified model of offshore Airborne Wind Energy Converters journal April 2016
Laddermill, a novel concept to exploit the energy in the airspace journal June 2001
Airborne wind energy resource analysis journal October 2019
Wake modeling of wind turbines using machine learning journal January 2020
Performance assessment of a rigid wing Airborne Wind Energy pumping system journal April 2019
Cascaded Pumping Cycle Control for Rigid Wing Airborne Wind Energy Systems journal November 2019
Aerodynamic characterization of a soft kite by in situ flow measurement journal January 2019
Optimal Crosswind Towing and Power Generation with Tethered Kites journal January 2008
Quasi-steady model of a pumping kite power system journal February 2019
Dynamic Nonlinear Aeroelastic Model of a Kite for Power Generation journal September 2014

Cited By (1)

Towing test data of the Kyushu University kite system dataset January 2020