Smart Solar Forecasting: Machine Learning Approaches for Predicting Solar Power
Authors:
- 1 December 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1344-1349
Abstract
Solar energy is one of the most popular renewable energy sources in recent years. These solar systems not only reduce the need for electricity but also greatly improve the environment. Due to our excessive dependence on fossil fuels and their limited sources and the pollution caused by them, most people are turning to solar energy to power their homes and industries. It's critical to understand the location of the solar panel and the local weather since solar power efficiency is highly dependent on environmental factors. With the inherent unpredictability of photovoltaic power output, machine learning is a useful tool for predicting how weather conditions affect solar power plants, and there are various other viable prediction methods available. This research evaluates several meteorological characteristics for PV forecasting using numerous machine learning algorithms. Using the collected historical data set, a machine learning model is created. Necessary preprocessing techniques such as univariate and bivariate analysis are used. Machine learning algorithms benefit from data visualization as it makes it easier to understand features and create a robust classification model. Accuracy-related performance metrics such as MAE, MSE, and RMSE are used to compare the methods. We evaluate and contrast the various models' performances. This evaluation approach helps to choose the algorithm that best suits the task at hand.Keywords
This publication has 16 references indexed in Scilit:
- Solar PV Power Prediction System Based on Machine Learning Approach2023
- Machine Learning Based Solar Photovoltaic Power Forecasting: A Review and ComparisonIEEE Access, 2023
- Comprehensive Review of Conventional and Emerging Maximum Power Point Tracking Algorithms for Uniformly and Partially Shaded Solar Photovoltaic SystemsIEEE Access, 2023
- Solar Power Forecasting Using Deep Learning TechniquesIEEE Access, 2022
- A Hybrid Approach of Solar Power Forecasting Using Machine Learning2019
- Modelling and Parameter Estimation of Solar Cell using Genetic Algorithm2019
- Solar photovoltaic power forecasting using optimized modified extreme learning machine techniqueEngineering Science and Technology, an International Journal, 2018
- A Refinement of Lasso Regression Applied to Temperature ForecastingProcedia Computer Science, 2018
- Performance analysis of sloped solar chimney power plants in the southwestern region of IranInternational Journal of Ambient Energy, 2016
- A study on global solar PV energy developments and policies with special focus on the top ten solar PV power producing countriesRenewable and Sustainable Energy Reviews, 2015