Forecasting and analysing renewable and non-renewable energy generation and demand patterns using machine learning and deep learning techniques

View at publisher Summarise with VIRAT
Authors: V. Jeya Ramya, Ashwini N. Shinde, Gautam Dasaka
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This research paper examines the different analyses for forecasting renewable and non-renewable energy and observes the implementation of machine learning (ML) and deep learning (DL) models in forecasting and analysing on energy, focusing on model architecture and training outcomes. Five models, including traditional ML algorithms and DL novelty of multimodal architectures, are evaluated on a dataset comprising energy generation and demand patterns market available data. Notably, Linear Regression, Decision trees, and Support Vector Machines exhibit superior demonstration of three multi-model performances on both training and testing datasets, with low Mean Squared Error (MSE) scores and high predictive accuracy (R²). Linear Regression achieves a train MSE of 0.04 and a test MSE of 0.54. Decision Tree achieves a train MSE close to zero but a significantly higher test MSE at 21.69. Support Vector Machine shows high MSEs at 0.90 for training and 0.10 for testing, indicating results. Time series and Auto-Regressive Integrated performed. It shows Various trends in time series. However, traditional Linear sequential regression performs slightly worse, with a train MSE of 21.69 and a test MSE of 0.89. Lastly, the ARIMA time series Architecture demonstrates a good performance with a training analysis as well as forecasting of different trends. These findings underscore the importance of model selection and performance architecture design in stock price prediction tasks and provide insights into the strengths and limitations of various ML and DL approaches in renewable and non-renewable energy forecasting.

Fields of Study & Subjects

Energy Load and Power Forecasting Stock Market Forecasting Methods Forecasting Techniques and Applications

Publication details

Journal / source
CRC Press eBooks
Pages
123–128
Publication date
25 March 2026
Language
EN
Document type
Book chapter