Volume- 10
Issue- 4
Year- 2023
DOI: 10.55524/ijirem.2023.10.4.7 | DOI URL: https://doi.org/10.55524/ijirem.2023.10.4.7 Crossref
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0) (http://creativecommons.org/licenses/by/4.0)
Article Tools: Print the Abstract | Indexing metadata | How to cite item | Email this article | Post a Comment
Manjeet Singh , Dr. Satish Saini
This paper compares data-driven algorithms (Linear Regression, Random Forest, and Decision Tree) for solar energy prediction. It analyzes variables like Daily Yield, Total Yield, Ambient Temperature, Module Temperature, Irradiation, and DC Power using a dataset with unprecedented granularity. The algorithms were trained and tuned for optimal performance, resulting in high accuracy levels. Linear Regression achieved 99.4% accuracy, Random Forest achieved 99.2% accuracy, and Decision Tree had the highest accuracy at 99.8%. The analysis identified strengths and weaknesses of each algorithm, indicating their suitability for different prediction scenarios. These findings have significant implications for integrating solar energy into the power system, instilling confidence in the reliability of data-driven algorithms for precise solar energy forecasting.
M. Tech Scholar, Department of Electrical Engineering, RIMT University, Mandi Gobindgarh, India
No. of Downloads: 25 | No. of Views: 511
Xiaoan Zhan, Yang Xu, Yingchia Liu.
December 2024 - Vol 11, Issue 6
Pradeep Kumar, Dr Suresh Chand, Rohit Kumar Gupta, Amar Bahadur Singh.
August 2024 - Vol 11, Issue 4
Vivek Kushawaha, Gaurav Gupta, Lalit Singh.
April 2024 - Vol 11, Issue 2