TY - GEN
T1 - Uncertainty-aware photovoltaic generation estimation through fusion of physics with harmonics information using Bayesian neural networks
AU - Pylorof, Dimitrios
AU - Garcia, Humberto E.
N1 - Funding Information:
The work presented herein was funded in part by Project PV-NOW of the U.S. Department of Energy Office of Electricity through Contract No. DE-AC07-05ID14517. Neither the United States Government nor any agency thereof, nor Contractor, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency or Contractor thereof.
Publisher Copyright:
© 2023 IEEE.
PY - 2023/3/22
Y1 - 2023/3/22
N2 - We develop an aggregate photovoltaic generation estimation methodology that uses diverse inputs and can reason on its current input-dependent predictive uncertainty. Named PV-PHEst, for PhotoVoltaic Physics- & Harmonics-driven Estimator, the resulting tool is intelligently weighing and fusing information carried by the output of physics models, harmonics, and line sensors, using Bayesian neural networks and related techniques aimed at solving machine learning problems with intrinsic uncertainty quantification. As each of the three input classes carries heterogeneous information that only sheds light on one facet of the estimation problem but its value can diminish in the face of diverse grid phenomena, PV-PHEst with its estimation and uncertainty reasoning capabilities perform a nontrivial and potentially mission-critical task of value to grid operators.
AB - We develop an aggregate photovoltaic generation estimation methodology that uses diverse inputs and can reason on its current input-dependent predictive uncertainty. Named PV-PHEst, for PhotoVoltaic Physics- & Harmonics-driven Estimator, the resulting tool is intelligently weighing and fusing information carried by the output of physics models, harmonics, and line sensors, using Bayesian neural networks and related techniques aimed at solving machine learning problems with intrinsic uncertainty quantification. As each of the three input classes carries heterogeneous information that only sheds light on one facet of the estimation problem but its value can diminish in the face of diverse grid phenomena, PV-PHEst with its estimation and uncertainty reasoning capabilities perform a nontrivial and potentially mission-critical task of value to grid operators.
KW - Analytics
KW - Bayesian methods
KW - Machine learning
KW - Photovoltaic systems
KW - Uncertainty quantification
UR - https://www.scopus.com/pages/publications/85151539454
UR - https://www.mendeley.com/catalogue/43f440c4-8cce-31cc-8339-b97e3c0f07d3/
U2 - 10.1109/ISGT51731.2023.10066417
DO - 10.1109/ISGT51731.2023.10066417
M3 - Conference contribution
AN - SCOPUS:85151539454
SN - 9781665453554
T3 - 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023
SP - 1
EP - 5
BT - 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023
Y2 - 16 January 2023 through 19 January 2023
ER -