International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
A FRAMEWORK FOR USING SATELLITE IMAGES TO ESTIMATE PV SYSTEMS' GENERATING CAPACITIES Venkata Sireesha
Information Technology Institute of Aeronautical Engineering Hyderabad, India
Bakka Arun Kumar
Information Technology Institute of Aeronautical Engineering Hyderabad, India
Dheninn Chowdari Ambadipudi
Information Technology Institute of Aeronautical Engineering Hyderabad, India
Abhishek Bashetty
Information Technology Institute of Aeronautical Engineering Hyderabad, India
---------------------------------------------------------------------------***--------------------------------------------------------------------Abstract— Numerous initiatives to rely on new pivotal solution in combatting climate change while
diminishing reliance on finite fossil fuels. This surge in solar panel adoption owes much to advancements in technology, heightened environmental consciousness, and compelling economic incentives. Advancements in solar panel technology have revolutionized the renewable energy landscape, rendering solar power more accessible and efficient than ever before. Breakthroughs in photovoltaic cell design, battery storage systems, and manufacturing techniques have notably enhanced the efficacy and affordability of solar panels, rendering them a feasible choice for residential as well as commercial applications. Additionally, the modular nature of solar panel setups allows for scalability, permitting users to tailor systems according to their energy requirements and available space. Nevertheless, despite the remarkable strides made in solar technology, the initial costs associated with solar panel installations remain a significant consideration for potential adopters. Estimating the capacity and cost of solar panel systems conventionally involves intricate calculations and evaluations, often necessitating specialized expertise and knowledge. Factors such as geographical location, solar irradiance, shading, and system configuration all exert considerable influence on determining the optimal size and output of a solar installation. Traditional methods of estimating solar panel capacity typically entail utilizing solar irradiance data, conducting site surveys, and undertaking engineering analyses to evaluate the solar potential of a particular location. This process demands meticulous planning and assessment to ensure optimum performance and cost-effectiveness. Furthermore, the financial aspects of solar installations, encompassing incentives, rebates, and financing options, must be carefully evaluated to gauge the overall return on investment. In this regard, the proliferation of online solar calculators and software tools has streamlined the process of estimating solar panel capacity and costs for consumers and businesses alike. These tools harness geographic data, system specifications, and energy consumption patterns to generate precise projections of solar energy production and financial returns. By empowering users to assess the feasibility and economic viability of solar investments more efficiently, these tools are propelling further adoption of solar energy across diverse markets. In conclusion, the escalating deployment
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. Keywords— renewable energy; photovoltaic (PV); Satellite image; segmenation; watershed method; deep learing I. INTRODUCTION In the current era, the spotlight on sustainability and renewable energy sources has led to a surge in the utilization of solar panels, marking a significant stride towards a more eco-friendly future. Solar energy, drawn from the boundless radiance of the sun, emerges as a
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 925