A Comparison Between Deep Learning and Support Vector Regression Techniques Applied to Solar Forecast in Spain-Reference-Cited by-同舟云学术

A Comparison Between Deep Learning and Support Vector Regression Techniques Applied to Solar Forecast in Spain

Published:2021-08-16 Issue:1 Volume:144 Page:
ISSN:0199-6231
Container-title:Journal of Solar Energy Engineering
language:en
Short-container-title:

Author:

Lima Marcello Anderson F. B.¹,Fernández Ramírez Luis M.²,Carvalho Paulo C. M.³,Batista Josias G.¹,Freitas Deivid M.³

Affiliation:

1. Department of Industrial Mechatronics, Federal Institute of Education, Science and Technology, Limoeiro do Norte, CE 62.930-000, Brazil

2. Research Group in Sustainable and Renewable Electrical Technologies (PAIDI-TEP-023), Department of Electrical Engineering, University of Cadiz, EPS Algeciras, Algeciras, Cadiz 11202, Spain

3. Department of Electrical Engineering, Federal University of Ceará, Fortaleza, CE 60455-760, Brazil

Abstract

Abstract Solar energy is one of the main renewable energy sources capable of contributing to global energy demand. However, the solar resource is intermittent, making its integration into the electrical system a difficult task. Here, we present and compare two machine learning techniques, deep learning (DL) and support vector regression (SVR), to verify their behavior for solar forecasting. Our testing from Spain showed that the mean absolute percentage error for predictions using DL and SVR is 7.9% and 8.52%, respectively. The DL achieved the best results for solar energy forecast, but it is worth mentioning that the SVR also obtained satisfactory results.

Publisher

ASME International

Subject

Energy Engineering and Power Technology,Renewable Energy, Sustainability and the Environment

Link

http://asmedigitalcollection.asme.org/solarenergyengineering/article-pdf/144/1/010802/6739905/sol_144_1_010802.pdf

Reference61 articles.

1. Improved SuDoKu Reconfiguration Technique for Total-Cross-Tied PV Array to Enhance Maximum Power Under Partial Shading Conditions;Krishna;Renew. Sustain. Energy Rev.,2019

2. Enhanced Leader Particle Swarm Optimisation (ELPSO): An Efficient Algorithm for Parameter Estimation of Photovoltaic (PV) Cells and Modules;Jordehi;Sol. Energy,2018

3. Fractional Chaotic Ensemble Particle Swarm Optimizer for Identifying the Single, Double, and Three Diode Photovoltaic Models’ Parameters;Yousri;Energy,2020

4. Portfolio Theory Applied to Solar and Wind Resources Forecast;Lima;IET Renew. Power Gener.,2017

5. Solar Irradiance Measurement Instrumentation and Power Solar Generation Forecasting Based on Artificial Neural Networks (ANN): A Review of Five Years Research Trend;Pazikadin;Sci. Total Environ.,2020

Cited by 20 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Hybrid machine learning model combining of CNN-LSTM-RF for time series forecasting of Solar Power Generation;e-Prime - Advances in Electrical Engineering, Electronics and Energy;2024-09

2. Renewable Energy MicroGrid Power Forecasting: AI Techniques with Environmental Perspective;2024-04-18

3. Watershed groundwater level multistep ahead forecasts by fusing convolutional-based autoencoder and LSTM models;Journal of Environmental Management;2024-02

4. Global horizontal irradiance prediction model considering the effect of aerosol optical depth based on the Informer model;Renewable Energy;2024-01

5. Development of solar based dryer for grapes drying using IoT and machine learning;AIP Conference Proceedings;2024