학술논문
Comparative Analysis of Machine Learning and Deep Learning Strategies for Solar Irradiation Forecasting
Document Type
Conference
Source
2023 International Conference on Electrical Engineering and Advanced Technology (ICEEAT) Electrical Engineering and Advanced Technology (ICEEAT), 2023 International Conference on. 1:1-6 Nov, 2023
Subject
Language
Abstract
In this work, we conduct a comparative analysis of Machine Learning (ML) and Deep Learning (DL) approaches for solar irradiation forecasting at Batna station. Specifically, we examine six different ML methods: Linear Regression (LR), Multilayer Perceptron (MLP), Extreme Learning Machine (ELM), Kernel Ridge Regression (KRR), Support Vector Regression (SVR), and Gaussian Process Regression (GPR). Furthermore, we investigate a deep learning-based regression approach considered a relatively recent field technique. We propose to use three DL methods, namely Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Bi-directional Long Short-Term Memory (Bi-LSTM). We present and discuss the experimental outcomes obtained from the Batna station data.