TY - GEN
T1 - Accuracy of Probabilistic Harmonic Estimation in Sparsely Monitored Transmission Networks
AU - Zhao, Yuqi
AU - Milanovic, Jovica V.
AU - Rodrıguez-Pajaron, Pablo
AU - Hernandez-Bayo, araceli
N1 - Funding Information:
ACKNOWLEDGMENT This work was partly supported by Grant RTI2018-097424-B-I00 funded by MCIN/AEI/10.13039/501100011033 and by “ERDF A way of making Europe". This paper reflects only the author’s views and neither the Agency nor the Commission are responsible for any use that may be made of the information contained therein.
Publisher Copyright:
© 2022 IEEE.
PY - 2022/6
Y1 - 2022/6
N2 - Accurate estimation of harmonics in uncertain, power electronics interfaced large transmission networks without installation of excessive number of power quality monitors can significantly improve and facilitate the probabilistic harmonic propagation studies. Traditional harmonic state estimation methods have been widely studied but are still very challenging in practical application due to the requirement of a large number of synchronized monitoring devices and real-time operational structure of the network. Based on a preliminary study that demonstrates the effectiveness of sequential artificial neural networks (ANNs) in the probabilistic harmonic estimation in uncertain transmission networks, this paper presents further comprehensive accuracy assessment in terms of different types/numbers of harmonic measurements, different stop errors to optimise training time and limited numbers of installed power quality monitors due to realistic reasons. It has been demonstrated that the sequential ANNs is sufficiently accurate and applicable in estimating harmonics in uncertain transmission network, thus contributing to facilitate the identification of potential harmonic issues, benchmarking, standard compliance and the deployment of appropriate harmonic propagation and mitigation solutions.
AB - Accurate estimation of harmonics in uncertain, power electronics interfaced large transmission networks without installation of excessive number of power quality monitors can significantly improve and facilitate the probabilistic harmonic propagation studies. Traditional harmonic state estimation methods have been widely studied but are still very challenging in practical application due to the requirement of a large number of synchronized monitoring devices and real-time operational structure of the network. Based on a preliminary study that demonstrates the effectiveness of sequential artificial neural networks (ANNs) in the probabilistic harmonic estimation in uncertain transmission networks, this paper presents further comprehensive accuracy assessment in terms of different types/numbers of harmonic measurements, different stop errors to optimise training time and limited numbers of installed power quality monitors due to realistic reasons. It has been demonstrated that the sequential ANNs is sufficiently accurate and applicable in estimating harmonics in uncertain transmission network, thus contributing to facilitate the identification of potential harmonic issues, benchmarking, standard compliance and the deployment of appropriate harmonic propagation and mitigation solutions.
KW - ANN
KW - harmonic estimation
KW - renewable energy source
KW - sparsely monitored transmission system
KW - uncertainties
U2 - 10.1109/PMAPS53380.2022.9810613
DO - 10.1109/PMAPS53380.2022.9810613
M3 - Conference contribution
SN - 9781665412117
T3 - 2022 17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022
SP - 1
EP - 6
BT - 2022 17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022
ER -
