Conv-Ensemble for Solar Power Prediction With First Nations Seasonal Information

Conv-Ensemble for Solar Power Prediction With First Nations Seasonal Information

Power generation forecasting, especially for solar power, is crucial for future energy planning. In this study, a novel framework, namely <italic>FNS-Metrics</italic>, is proposed to integrate seasonal information from First Nations calendars into solar power forecasting. Furthermore, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Selvarajah Thuseethan, Sandipkumar Gangajaliya, Luke Hamlin, Bharanidharan Shanmugam, Suresh Thennadil
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Computer Society
Subjects:
Deep learning
first nations seasons
LSTM
solar power forecasting
transformer
Online Access:https://ieeexplore.ieee.org/document/11037463/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Power generation forecasting, especially for solar power, is crucial for future energy planning. In this study, a novel framework, namely <italic>FNS-Metrics</italic>, is proposed to integrate seasonal information from First Nations calendars into solar power forecasting. Furthermore, a novel Conv-Ensemble framework is proposed, leveraging the high-level feature extraction capabilities of Conv1D layers along with the low-level feature extraction abilities of transformer and LSTM networks. A weighted feature concatenation technique is also integrated into the proposed approach to combine the features effectively. To validate the proposed FNS-Metrics and Conv-Ensemble framework, a new dataset is constructed by collecting power and weather data from the Desert Knowledge Australia Solar Center in Alice Springs and integrating data related to First Nations seasonal cycles. Experiments on this dataset show that the Conv-Ensemble framework with FNS-Metrics outperforms traditional approaches, achieving state-of-the-art solar power prediction with the highest <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> of 0.8641 and the lowest MSE of 22.41. These represent a 14.60&#x0025; and 26.21&#x0025; increase compared to the baseline configuration of Conv-Transformer. The ablation study demonstrates that the Conv-Ensemble framework improves performance compared to the baselines. Furthermore, the results for individual and combined FNS-Metrics features show a progressive improvement in performance.
ISSN:2644-1268

Similar Items