Machine Learning Models for Regional Photovoltaic Power Generation Forecasting with Limited Plant-Specific Data

被引:0
|
作者
Tucci, Mauro [1 ]
Piazzi, Antonio [2 ]
Thomopulos, Dimitri [1 ]
机构
[1] Univ Pisa, Dept Energy Syst Terr & Construct Engn, Lgo Lucio Lazzarino 1, I-56122 Pisa, Italy
[2] I EM Srl, Via Lampredi 45, I-57121 Livorno, Italy
关键词
renewable energy prediction; solar photovoltaic forecasting; machine learning; regional electricity production prediction; PREDICTION; REGRESSION; TREE;
D O I
10.3390/en17102346
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Predicting electricity production from renewable energy sources, such as solar photovoltaic installations, is crucial for effective grid management and energy planning in the transition towards a sustainable future. This study proposes machine learning approaches for predicting electricity production from solar photovoltaic installations at a regional level in Italy, not using data on individual installations. Addressing the challenge of diverse data availability between pinpoint meteorological inputs and aggregated power data for entire regions, we propose leveraging meteorological data from the centroid of each Italian province within each region. Particular attention is given to the selection of the best input features, which leads to augmenting the input with 1-hour-lagged meteorological data and previous-hour power data. Several ML approaches were compared and examined, optimizing the hyperparameters through five-fold cross-validation. The hourly predictions encompass a time horizon ranging from 1 to 24 h. Among tested methods, Kernel Ridge Regression and Random Forest Regression emerge as the most effective models for our specific application. We also performed experiments to assess how frequently the models should be retrained and how frequently the hyperparameters should be optimized in order to comprise between accuracy and computational costs. Our results indicate that once trained, the model can provide accurate predictions for extended periods without frequent retraining, highlighting its long-term reliability.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] Photovoltaic Power Generation Forecasting for Regional Assessment Using Machine Learning
    Borunda, Monica
    Ramirez, Adrian
    Garduno, Raul
    Ruiz, Gerardo
    Hernandez, Sergio
    Jaramillo, O. A.
    [J]. ENERGIES, 2022, 15 (23)
  • [2] Machine Learning Algorithms in Forecasting of Photovoltaic Power Generation
    Su, Di
    Batzelis, Efstratios
    Pal, Bikash
    [J]. 2019 2ND INTERNATIONAL CONFERENCE ON SMART ENERGY SYSTEMS AND TECHNOLOGIES (SEST 2019), 2019,
  • [3] A Machine-Learning Approach for Regional Photovoltaic Power Forecasting
    Li, Yuan
    Sun, Qian
    Lehman, Brad
    Lu, Siyuan
    Hamann, Hendrik F.
    Simmons, Joseph
    Black, Jon
    [J]. 2016 IEEE POWER AND ENERGY SOCIETY GENERAL MEETING (PESGM), 2016,
  • [4] Analysis of deceptive data attacks with adversarial machine learning for solar photovoltaic power generation forecasting
    Kuzlu, Murat
    Sarp, Salih
    Catak, Ferhat Ozgur
    Cali, Umit
    Zhao, Yanxiao
    Elma, Onur
    Guler, Ozgur
    [J]. ELECTRICAL ENGINEERING, 2024, 106 (02) : 1815 - 1823
  • [5] Analysis of deceptive data attacks with adversarial machine learning for solar photovoltaic power generation forecasting
    Murat Kuzlu
    Salih Sarp
    Ferhat Ozgur Catak
    Umit Cali
    Yanxiao Zhao
    Onur Elma
    Ozgur Guler
    [J]. Electrical Engineering, 2024, 106 : 1815 - 1823
  • [6] A Review and Analysis of Forecasting of Photovoltaic Power Generation Using Machine Learning
    Kumar, Abhishek
    Kumar, Ashutosh
    Segovia Ramirez, Dubey Isaac
    Munoz del Rio, Alba
    Garcia Marquez, Fausto Pedro
    [J]. PROCEEDINGS OF THE SIXTEENTH INTERNATIONAL CONFERENCE ON MANAGEMENT SCIENCE AND ENGINEERING MANAGEMENT - VOL 1, 2022, 144 : 492 - 505
  • [7] Deep and Machine Learning Models to Forecast Photovoltaic Power Generation
    Cantillo-Luna, Sergio
    Moreno-Chuquen, Ricardo
    Celeita, David
    Anders, George
    [J]. ENERGIES, 2023, 16 (10)
  • [8] Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques
    Akhter, Muhammad Naveed
    Mekhilef, Saad
    Mokhlis, Hazlie
    Shah, Noraisyah Mohamed
    [J]. IET RENEWABLE POWER GENERATION, 2019, 13 (07) : 1009 - 1023
  • [9] A Review on Machine Learning Models in Forecasting of Virtual Power Plant Uncertainties
    Ahmet Dogan
    Demet Cidem Dogan
    [J]. Archives of Computational Methods in Engineering, 2023, 30 : 2081 - 2103
  • [10] A Review on Machine Learning Models in Forecasting of Virtual Power Plant Uncertainties
    Dogan, Ahmet
    Cidem Dogan, Demet
    [J]. ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING, 2023, 30 (03) : 2081 - 2103