International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 04 | Apr 2025
p-ISSN: 2395-0072
www.irjet.net
AI Based Solar Energy Forecasting Vivek Shingne1, Animesh Tiwari2, Vinay Yadav3, Divyesh Surve4, Dr. Anil Kale5 1,2,3,4Student at Mahatma Gandhi Mission’s College of Engineering And Technology, Navi Mumbai
5Associate Professor at Mahatma Gandhi Mission’s College of Engineering And Technology, Navi Mumbai
---------------------------------------------------------------------***--------------------------------------------------------------------who often fail to adapt to the sudden changes in the weather Abstract – Due to increase in demand for electricity and
factors like for example, unexpected cloud cover , changes in temperature or dust in the atmosphere. This factors have a direct effect on the potential of the solar panels, which might lead to fluctuations in the energy generation that are very hard to predict with the old models.
rising depletion of fossil fuels, there is a growing shift towards the renewable sources of energy. Out of which, solar energy is a crucial one. However, its dependency on weather conditions creates challenges in forecasting and efficient usage. Our aim is to build an intelligent system that provides accurate solar energy predictions based on location and helps the user to estimate energy generation, cost savings and environmental impact. In this paper, we propose a system titled “AI Based Solar Energy Forecasting” that will predict solar energy generation using weather-based parameters. The system utilizes a Linear Regression model trained on historical solar and weather data to provide reliable energy forecasts based on location. In addition to this it also offers option to input number of solar panels, panel area, efficiency and local electricity rate to estimate electrical energy output, cost savings and C02 emissions avoided.
Further many of these approaches were strongly dependent on manual feature selection and static formulas which made them less flexible when applied across different locations. This challenges gave rise to the need for more dynamic system providing consistent and reliable forecasts, regardless of location, time or year. 1. By taking these limitations into consideration, we thoroughly explored the machine learning techniques and developed a Linear Regression based model for solar energy prediction. Our approach removes the need for difficult manual computations by automatically learning meaningful patterns from the environmental data like temperature, cloud cover and solar irradiation.
Key
Words: Solar Energy, Renewable Energy Forecasting, Linear Regression, Machine Learning, CO2 Emission Reduction.
2. Inspired by modern data driven methods we trained and fine-tuned our model using historical weather and solar generation datasets that allows it to adapt to the varying conditions and give more accurate predictions as compared to the standard rule based forecasting techniques.
1.INTRODUCTION The increase in the need for clean and sustainable energy is increasing day by day. In such conditions, the solar energy has come out as one of the proper solution to this. Solar energy is renewable, widely available and environmentally friendly. But the production of solar energy relies on the weather factors which makes it difficult to predict it accurately. So the inaccurate forecasts might lead to the energy loss and increased dependency on non-renewable energy. Accurate forecasting will help people plan their energy usages much better and also save money while also contributing to the environment due to reduced carbon footprint. In this project, we focus on building an AI Based Solar Energy Forecasting using machine learning techniques, particularly Linear Regression to predict solar energy based on the weather factors of a location. Also our system allows user to estimate their energy outputs, cost savings and environmental benefit through an easy to use web application.
3. When compared with the conventional solar forecasting systems, this framework achieves an effective balance between the prediction accuracy and computational simplicity which makes it highly suitable for both residential and small scale commercial use. In addition to that, our system not only provides forecasts but also gives insight into potential cost savings and environmental impact (through CO2 emissions reductions) which makes it a practical application in the field of smart energy management.
3. Literature Survey As we previously discussed traditional solar energy forecasting methods/techniques strongly depend upon the statistical models and weather based simulations, which were focusing upon historical datasets of temperature, sunlight hours and other related factors. While these methods provide a reasonable accuracy in stable weather conditions but they often fail to adapt to sudden changes like temperatures shifts etc. These limitations create a reduction in their effectiveness in real world situations where weather
2. Motivation In the old one or we can say traditional solar energy generation systems, getting the predictions regarding the solar energy has always been difficult. Most of the conventional methods rely on static data or fixed assumption,
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 574