TY - GEN
T1 - A Novel AI-driven Hybrid Method for Flicker Estimation in Power Systems
AU - Enayati, Javad
AU - Asef, Pedram
AU - Yousefi, Aliakbar
AU - Asadpourahmadchali, M. B.
AU - Benoit, Alexandre
PY - 2024/9/12
Y1 - 2024/9/12
N2 - This paper introduces a novel hybrid method using a combination of an H-infinity filter and artificial neural network (ANN) to estimate flicker components within power distribution system voltages. The H-infinity filter first extracts the estimated envelope of the applied voltage waveforms, incorporating a new voltage fluctuation model that realistically accounts for both harmonic and flicker components. Furthermore, an ADALINE (adaptive linear neuron) extracts the specific flicker components within the envelope. The hybrid process decouples prediction states, enhancing convergence behavior. Additionally, it showcases robust flicker component tracking even in the presence of power harmonics and noise, offering advantages over traditional signal processing methods. The algorithm's performance in flicker estimation is validated through statistical analysis using Monte Carlo (MC) simulations and real world data.
AB - This paper introduces a novel hybrid method using a combination of an H-infinity filter and artificial neural network (ANN) to estimate flicker components within power distribution system voltages. The H-infinity filter first extracts the estimated envelope of the applied voltage waveforms, incorporating a new voltage fluctuation model that realistically accounts for both harmonic and flicker components. Furthermore, an ADALINE (adaptive linear neuron) extracts the specific flicker components within the envelope. The hybrid process decouples prediction states, enhancing convergence behavior. Additionally, it showcases robust flicker component tracking even in the presence of power harmonics and noise, offering advantages over traditional signal processing methods. The algorithm's performance in flicker estimation is validated through statistical analysis using Monte Carlo (MC) simulations and real world data.
KW - adaptive linear neuron
KW - estimation process
KW - Flicker
KW - H-Infinity
KW - machine learning
KW - voltage fluctuations
UR - http://www.scopus.com/inward/record.url?scp=85207657746&partnerID=8YFLogxK
U2 - 10.1109/SEST61601.2024.10694472
DO - 10.1109/SEST61601.2024.10694472
M3 - Chapter in a published conference proceeding
AN - SCOPUS:85207657746
T3 - 2024 International Conference on Smart Energy Systems and Technologies: Driving the Advances for Future Electrification, SEST 2024 - Proceedings
BT - 2024 International Conference on Smart Energy Systems and Technologies
PB - IEEE
CY - U. S. A.
T2 - 2024 International Conference on Smart Energy Systems and Technologies, SEST 2024
Y2 - 10 September 2024 through 12 September 2024
ER -