SolarFlux Predictor: A Novel Deep Learning Approach for Photovoltaic Power Forecasting in South Korea

Electronics, Год журнала: 2024, Номер 13(11), С. 2071 - 2071

Опубликована: Май 27, 2024

We present SolarFlux Predictor, a novel deep-learning model designed to revolutionize photovoltaic (PV) power forecasting in South Korea. This uses self-attention-based temporal convolutional network (TCN) process and predict PV outputs with high precision. perform meticulous data preprocessing ensure accurate normalization outlier rectification, which are vital for reliable analysis. The TCN layers crucial capturing patterns energy data; we complement them the teacher forcing technique during training phase significantly enhance sequence prediction accuracy. By optimizing hyperparameters Optuna, further improve model’s performance. Our incorporates multi-head self-attention mechanisms focus on most impactful features, thereby improving In validations against datasets from nine regions Korea, outperformed conventional methods. results indicate that is robust tool systems’ management operational efficiency can contribute Korea’s pursuit of sustainable solutions.

Язык: Английский

Load Equipment Segmentation and Assessment Method Based on Multi-Source Tensor Feature Fusion

Electronics, Год журнала: 2025, Номер 14(5), С. 1040 - 1040

Опубликована: Март 5, 2025

The state monitoring of power load equipment plays a crucial role in ensuring its normal operation. However, densely deployed environments, the target often exhibits low clarity, making real-time warnings challenging. In this study, segmentation and assessment method based on multi-source tensor feature fusion (LSA-MT) is proposed. First, lightweight residual block attention mechanism introduced into backbone network to emphasize key features devices enhance efficiency. Second, 3D edge detail perception module designed facilitate multi-scale while preserving boundary different devices, thereby improving local recognition accuracy. Finally, decomposition reorganization are employed guide visual reconstruction conjunction with images, mapping data utilized for automated fault classification. experimental results demonstrate that LSE-MT produces visually clearer segmentations compared models such as classic UNet++ more recent EGE-UNet when segmenting multiple achieving Dice mIoU scores 92.48 92.90, respectively. Regarding classification across four datasets, average accuracy can reach 92.92%. These findings fully effectiveness LSA-MT alarms grid operation maintenance.

Язык: Английский

A cross-modal deep learning method for enhancing photovoltaic power forecasting with satellite imagery and time series data

Energy Conversion and Management, Год журнала: 2024, Номер 323, С. 119218 - 119218

Опубликована: Ноя. 13, 2024

Язык: Английский