This study presents YOLOv11n-GhostLite, an innovative lightweight deep learning architecture optimized for real-time localization of photovoltaic (PV) faults in electroluminescence (EL) images, specifically designed for edge deployment. A Deep Convolutional Generative Adversarial Network (DCGAN)-based synthetic augmentation pipeline is presented to address the issues of class imbalance and limited resource availability, generating high-fidelity, class-conditional EL images that include realistic banding artifacts. This method enhances the representation of minority defect categories by more than 150%, elevating the mean Average Precision (mAP@50) by 4% and decreasing false negatives by 5%. The proposed model incorporates GhostConv for efficient early feature extraction, C3k2 residual blocks for deep representation learning, GhostSPPF for multi-scale context aggregation, C2PSA attention for adaptive feature refinement, and an anchor-free detection head, achieving high performance with only 2.34 million parameters and 6.2 GFLOPs. Detailed experiments on two benchmark datasets PVEL-AD and PV Multi-Defect exhibit the model’s efficacy, attaining 97.2% mAP@50 on PVEL-AD, and 96.4% mAP@50 on PV Multi-Defect, outperforming larger models in both accuracy and speed. The model is further deployed on a Google Coral Edge TPU, demonstrating its real-time functionality with minimal power consumption (~2W) and suitable latency for drone-based solar inspections. YOLOv11n-GhostLite’s integration of efficient architecture and data-driven augmentation renders it an effective solution for scalable, real-time photovoltaic fault detection in resource-limited settings.

To ensure the reliability and sustained performance of industrial photovoltaic (PV) systems, fault detection frameworks must achieve both high detection accuracy and computational efficiency, particularly for deployment on resource-constrained edge platforms. This work proposes a lightweight and low-latency photovoltaic defect detection framework that integrates DCGAN-based generative augmentation with the proposed GhostViT-YOLOv10n architecture. The augmentation strategy helps address class imbalance, improve representation of rare defects, and enhance generalization capability in electroluminescence (EL) imagery through structured geometric and photometric transformations. The proposed framework integrates lightweight Ghost-based optimization, Cross-Stage Partial Fusion (C2f), Spatial Pyramid Pooling—Fast (SPPF), MobileViT contextual learning, and SimAM-based attention refinement to improve multi-scale feature extraction while maintaining low computational complexity. Experimental evaluation on the PVEL-AD and PV Multi Defect benchmark datasets demonstrates strong detection performance. On the PVEL-AD dataset, the BaseLine achieves a mAP@0.5 of 71.6% with only 2.7 M parameters and 8.4 GFLOPs, while our proposed GhostViT-YOLOv10n framework with DCGAN-enhanced version further improves detection performance to 93.6% mAP@0.5 with only 2.19 M parameters and 6.6 GFLOPs. On the PV Multi Defect dataset, the BaseLine achieves a mAP@0.5 of 74.0% with 2.71 M parameters and 8.4 GFLOPs, and the optimized framework with DCGAN-augmented configuration further improves performance to 95.4% mAP@0.5 with 2.58 M parameters and 7.7 GFLOPs. These results demonstrate the effectiveness of combining lightweight architectural optimization with generative augmentation for improving rare defect representation and multi-scale photovoltaic defect detection. To validate practical deployment feasibility, the optimized framework was deployed on a Raspberry Pi 5 using ONNX Runtime under CPU-only conditions. The deployed model achieved an average inference time of 43.05 ms and a real-time processing speed of 23.23 FPS while maintaining moderate CPU utilization and stable thermal behavior. These deployment results demonstrate the suitability of the proposed framework for lightweight edge-oriented photovoltaic inspection applications without requiring GPU acceleration. All evaluations were conducted exclusively on real test datasets, while synthetic samples were used only during training to improve data diversity and rare defect representation. Overall, the proposed framework provides a balanced solution that combines detection accuracy, computational efficiency, lightweight edge deployment capability, and generative augmentation for practical photovoltaic defect inspection applications with potential suitability for future drone-assisted inspection scenarios.