International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 09 | Sep 2025
p-ISSN: 2395-0072
www.irjet.net
The Solar Powered Remote Sensing and Data Acquisition using IoT Devika R1, Dr. J. Leema Rose2 1PG Scholar, Dept. of Electrical and Electronics Engineering, PSN College of Engineering and Technology,
Tamil Nadu, India.
2Associate Professor, Dept. of Electrical and Electronics Engineering, PSN College of Engineering and Technology,
Tamil Nadu, India. ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The Solar Powered Remote Sensing and Data
historical data, such as sun movement, seasonal variations, and weather conditions. By
Acquisition using IoT is an innovative approach to harnessing solar energy more efficiently by using predictive algorithms and real-time tracking. This system combines embedded technology and machine learning to improve energy capture by accurately aligning solar panels with the sun’s position throughout the day. Unlike traditional solar tracking systems, which follow predefined paths or respond directly to sunlight, this system leverages predictive analytics to anticipate the sun's position based on historical and real-time data. By using a machine learning model trained with data from seasonal, geographical, and weather patterns, the system continuously refines its alignment, enhancing the efficiency of solar panels even in variable weather conditions.
leveraging machine learning, the system aims to reduce the frequency of real-time adjustments, minimizing energy consumption associated with constant movement and extending the lifespan of mechanical components. The system's ability to make informed decisions based on predictive analytics reduces the need for frequent, real-time sensor readings and motor movements, allowing for smoother operation with fewer mechanical interventions. Another key objective is to create a system adaptable to various environmental conditions and geographic locations. Solar energy systems face varying conditions such as cloudy weather, high winds, or seasonal changes that can impact energy capture. By incorporating weather and environmental data into the machine learning model, the system can account for these factors and still position the panels optimally, even under less-than-ideal conditions. This adaptability makes the system suitable for global deployment in diverse regions and climates, improving its scalability. The system also seeks to enhance overall energy efficiency by conserving power within the solar tracking mechanism itself. Through predictive positioning, the energy used to move the panels is minimized, ensuring that a greater portion of the harvested solar energy is directed towards storage and consumption rather than system operation. The Solar Tracking System with Machine Learning for Predictive Positioning represents an innovative approach to solar energy optimization. Integrating LDR sensors, an embedded control system, and machine learning not only maximizes energy capture but also enhances system longevity and efficiency. The data stored in data logger is 4 LDR values and servomotor positions. By using current and voltage sensors we can get the value of maximum power output. By using this data machine learning algorithm get maximised energy positions of sun’s radiation
The system is designed with low-power embedded hardware that integrates sensors, a microcontroller, and actuators. Light intensity sensors provide real-time feedback, and motorized actuators adjust the panel’s orientation, ensuring optimal alignment. A predictive model, embedded within the system, is capable of offline operation and selfcalibration, minimizing dependence on internet connectivity and external computational resources. The integration of machine learning enables the system to adapt over time, considering weather forecasts and previous operational data to enhance decision-making for panel alignment.
Key Words: Machine Learning, Solar panel, Tracking system, Sensors, self calibration. 1.INTRODUCTION The Solar Powered Remote Sensing and Data Acquisition using IoT is to develop an advanced solar tracking mechanism that significantly improves the efficiency of solar energy capture by optimizing the orientation of solar panels throughout the day. Traditional solar tracking systems rely on real-time feedback from sensors to adjust the panel’s position, often requiring continuous movement and fine adjustments to ensure optimal alignment with the sun. However, this method is not always energy efficient and can lead to increased mechanical wear over time. The integration of machine learning into the solar tracking system introduces a predictive component that allows the system to anticipate the sun’s position based on patterns learned from
© 2025, IRJET
|
Impact Factor value: 8.315
2. BLOCK DIAGRAM This block diagram represents an Automatic Solar Tracker System using the ESP32 WROOM 32 microcontroller. The ESP32 collects data from the LDRs, processes it, and controls the servo motors to adjust the solar panel’s position automatically. This helps maintain optimal alignment with the sun, enhancing the solar panel's energy output
|
ISO 9001:2008 Certified Journal
|
Page 432