Research Article
Solar Energy Prediction using Machine Learning with Support Vector Regression Algorithm
@INPROCEEDINGS{10.1007/978-3-031-28975-0_2, author={Idamakanti Kasireddy and K. Padmini and R. V. D. Ramarao and B. Seshagiri and B. Venkata Naga Rani}, title={Solar Energy Prediction using Machine Learning with Support Vector Regression Algorithm}, proceedings={Cognitive Computing and Cyber Physical Systems. Third EAI International Conference, IC4S 2022, Virtual Event, November 26-27, 2022, Proceedings}, proceedings_a={IC4S}, year={2023}, month={3}, keywords={Solar energy Machine learning Support Vector Regression (SVR)}, doi={10.1007/978-3-031-28975-0_2} }- Idamakanti Kasireddy
K. Padmini
R. V. D. Ramarao
B. Seshagiri
B. Venkata Naga Rani
Year: 2023
Solar Energy Prediction using Machine Learning with Support Vector Regression Algorithm
IC4S
Springer
DOI: 10.1007/978-3-031-28975-0_2
Abstract
Machine Learning is almost applied in every field such as engineering, science, medical etc. In this work, the concept of machine learning has been adopted for predicting solar energy. The solar Energy is widely known renewable energy due to its massive advantages. Solar energy prediction can help to determine the energy consumption beforehand and plays a major role in future planning. The grid operators are facing hardships because of unreliable weather conditions, which lead to the reduction in solar energy output. So, they are unable to satisfy the needs of consumers. Our proposed solution intends to make prediction models by using machine learning algorithms such as Linear Regression, Lasso Regression, Ridge Regression and Support Vector Regression (SVR). These algorithms use past weather data including temperature, dew, wind, cloud and visibility. Based on these data, analysis has been carried out in Jupyter Notebook. From the analysis, it has found that, SVR algorithm performed well when compared with other algorithms.
