Time-series clustering of solar PV output for enhanced LOLP estimation
Nguyen, King Zeidan, Fayrouz Alexander, Demy Melagoda, Adithya Bataduvaarachchi, Nirasha Aravinthan, Visvakumar Yokley, Ryan Tamimi, Al
Nguyen, King
Zeidan, Fayrouz
Alexander, Demy
Melagoda, Adithya
Bataduvaarachchi, Nirasha
Aravinthan, Visvakumar
Yokley, Ryan
Tamimi, Al
An error occurred retrieving the object's statistics
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2025-03-04
Type
Conference paper
Genre
Keywords
Dynamic time warping,K-Medoids,Loss of load probability,Renewable energy,Time series clustering
Subjects (LCSH)
Citation
K. Nguyen et al., "Time-Series Clustering of Solar PV Output for Enhanced LOLP Estimation," 2025 IEEE International Conference on Energy Technologies for Future Grids (ETFG), Wollongong, Australia, 2025, pp. 1-6, doi: 10.1109/ETFG61999.2025.11401814.
Abstract
The high variability and large data volumes in renewable-rich power systems make Loss of Load Probability (LOLP) assessment computationally challenging. This paper proposed a time-series clustering method to aggregate solar PV output data which simplifies these calculations without losing important variability patterns. Hourly solar generation data are converted into daily profiles and grouped using hierarchical clustering, followed by K-Medoids with Dynamic Time Warping. This approach captures both typical seasonal behavior and rare high-impact, low-frequency events. The resulting representative profiles are then used in a non-sequential Monte Carlo simulation to estimate LOLP. Results show that the proposed method significantly reduces computational time while maintaining accuracy when compared with full-data simulations. © 2025 IEEE.
Table of Contents
Description
Click on the DOI link to access this article at the publishers website (may not be free).
Publisher
Institute of Electrical and Electronics Engineers Inc.
Journal
Book Title
Series
2025 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2025
7 December 2025 through 11 December 2025
Wollongong
221814
7 December 2025 through 11 December 2025
Wollongong
221814