Bakka Arun Kumar

A framework for using satellite images to estimate pv systems' generating capacities

• Authors Details :  
• Bakka Arun Kumar,  
• Dheninn Chowdari Ambadipudi,  
• Abhishek Bashetty,  
• Venkata Sireesha

66 Views Research reports

Numerous initiatives to rely on new renewable energy sources, such solar electricity, have been sparked by the increased interest in global warming. With an increase in home photovoltaic (PV) panels that are available to the public, more precise calculations of energy generation are now possible. Segmenting satellite images offers a straightforward and inexpensive way to categorize solar panels..This work suggests a method for classifying and segmenting solar panels that combines the watershed algorithm with deep learning approaches. First, a Convolutional Neural Network (CNN) architecture with the ResNet, EfficientNet, and Inception architectures is used for classification. Through the fine-tuning of pre-trained networks on a heterogeneous dataset of solar panels, transfer learning improves performance. The categorization model recognizes solar panels in a variety of settings with accuracy, making maintenance and monitoring easier. After classification, the watershed method uses intensity gradients to precisely delineate solar panels from the background. Tasks like defect detection and layout optimization are made easier when deep learning-based classification and watershed segmentation are combined. The outcomes of the experiments show how well the suggested method performs in terms of segmenting and classifying solar panels under various circumstances. A flexible automated solar panel management solution is provided by the combination of deep learning and the watershed algorithm, which promotes increased sustainability and efficiency in solar energy systems.

Article Subject Details

• Computer Science
• Computer Science Applications

Article Keywords Details

• Deep learing
• Photovoltaic (PV)
• Renewable energy
• Satellite image
• Segmenation
• Watershed method

Article File

Full Text PDF

---

---