Forecasting Univariate Solar Irradiance using Machine learning models: A case study of two Andean Cities

被引:8
|
作者
Diaz-Bedoya, Daniel [1 ]
Gonzalez-Rodriguez, Mario [1 ]
Clairand, Jean-Michel [1 ,2 ]
Serrano-Guerrero, Xavier [3 ]
Escriva-Escriva, Guillermo [4 ]
机构
[1] Univ Amer, Fac Ingeneria & Ciencias Aplicadas, Quito 170122, Ecuador
[2] Bur Etud Tech, Capgemini Engn, 4 Ave Didier Daurat, F-31700 Blagnac, France
[3] Univ Politecn Salesiana, Energy Transit Res Grp, Cuenca 010103, Ecuador
[4] Univ Politecn Valencia, Inst Energy Engn, Valencia 46022, Spain
关键词
Deep learning; Forecasting; Random Forest; Recurrent Neural Networks; Solar energy; PREDICTION; NETWORKS; RADIATION;
D O I
10.1016/j.enconman.2023.117618
中图分类号
O414.1 [热力学];
学科分类号
摘要
The integration of solar energy into power systems is essential for the future sustainability of power systems, particularly for isolated systems, such as microgrids, where establishing a primary transmission network is difficult. Therefore, the development of prediction methods becomes crucial to enable accurate forecasting of solar energy generation, facilitating efficient planning and operation of these systems and ensuring their long-term viability. This study proposes distinct forecasting models for solar irradiance forecasting: an autoregressive (AR) model, a Random Forest model, and a Long Short-Term Memory (LSTM) neural network. The methodology involves preprocessing the historical solar irradiance data and performing feature engineering to extract relevant input features. The architectural design, hyperparameter tuning, and training procedures of each model are discussed in detail. The findings indicate that the LSTM model exhibits enhanced performance compared to the AR model, while maintaining similar predictive accuracy to the Random Forest model in forecasting global solar irradiance. Both models yield a mean absolute percentage error of roughly 25%, with the LSTM exhibiting the lower error rate. Moreover, the LSTM model showcases an advancement over the AR model, resulting in a reduction of approximately 10 W/m2 for both root mean square error and mean absolute error. This finding highlights the effectiveness of LSTM networks in capturing long-term dependencies for accurate solar irradiance forecasting. Furthermore, an analysis of the models' interpretability is conducted, offering valuable insights into the key factors that contribute to the shaping of solar irradiance patterns. These insights hold practical significance for the optimization of renewable energy systems.
引用
收藏
页数:16
相关论文
共 50 条
  • [41] Weather forecasting prediction of Tamilnadu cities using machine learning
    Krishna Sai, B.
    Magesh Kumar, S.
    Mahalakshmi, D.
    Test Engineering and Management, 2019, 81 (11-12): : 5472 - 5477
  • [42] Solar Irradiance Prediction with Machine Learning Algorithms: A Brazilian Case Study on Photovoltaic Electricity Generation
    Viscondi, Gabriel de Freitas
    Alves-Souza, Solange N.
    ENERGIES, 2021, 14 (18)
  • [43] Forecasting Solar Energy Production Using Machine Learning
    Vennila, C.
    Titus, Anita
    Sudha, T. Sri
    Sreenivasulu, U.
    Reddy, N. Pandu Ranga
    Jamal, K.
    Lakshmaiah, Dayadi
    Jagadeesh, P.
    Belay, Assefa
    INTERNATIONAL JOURNAL OF PHOTOENERGY, 2022, 2022
  • [44] Forecasting Solar Radiation: Using Machine Learning Algorithms
    Chaudhary, Pankaj
    Gattu, Rohith
    Ezekiel, Soundarajan
    Rodger, James Allen
    JOURNAL OF CASES ON INFORMATION TECHNOLOGY, 2021, 23 (04)
  • [45] Forecasting Groundwater Quality Parameters using Machine Learning Models: a Case Study of Khemismiliana Plain, Algeria
    A. Tachi
    M. Metaiche
    A. Messoul
    H. Bouguerra
    S. E. Tachi
    Doklady Earth Sciences, 2023, 512 : 907 - 914
  • [46] Forecasting Groundwater Quality Parameters using Machine Learning Models: a Case Study of Khemismiliana Plain, Algeria
    Tachi, A.
    Metaiche, M.
    Messoul, A.
    Bouguerra, H.
    Tachi, S. E.
    DOKLADY EARTH SCIENCES, 2023, 512 (01) : 907 - 914
  • [47] Machine Learning Approach for Solar Irradiance Estimation on Tilted Surfaces in with Models Prediction
    Mbah, O. M.
    Madueke, C. I.
    Umunakwe, R.
    Okafor, C. O.
    JOURNAL OF ENGINEERING SCIENCES-UKRAINE, 2022, 9 (02): : G1 - G6
  • [48] Can we justify producing univariate machine-learning forecasts with satellite-derived solar irradiance?
    Yagli, Gokhan Mert
    Yang, Dazhi
    Gandhi, Oktoviano
    Srinivasan, Dipti
    APPLIED ENERGY, 2020, 259 (259)
  • [49] Comparison of physical and machine learning models for estimating solar irradiance and photovoltaic power
    Ramadhan, Raden A. A.
    Heatubun, Yosca R. J.
    Tan, Sek F.
    Lee, Hyun-Jin
    RENEWABLE ENERGY, 2021, 178 : 1006 - 1019
  • [50] Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning
    Verbois, Hadrien
    Huva, Robert
    Rusydi, Andrivo
    Walsh, Wilfred
    SOLAR ENERGY, 2018, 162 : 265 - 277