Dynamic line rating forecasting using recurrent neural networks

被引:0
|
作者
Martinez, Roberto Fernandez [1 ]
Zamora, Ramon [2 ]
Perera, Uvini [2 ]
Alberdi, Rafael [1 ]
Fernandez, Elvira [1 ]
Albizu, Igor [1 ]
Bedialauneta, Miren Terese [1 ]
机构
[1] Univ Basque Country, Dept Elect Engn, UPV EHU, Bilbao, Spain
[2] Auckland Univ Technol, Dept Elect & Elect Engn, Auckland, New Zealand
来源
18TH INTERNATIONAL CONFERENCE ON PROBABILISTIC METHODS APPLIED TO POWER SYSTEMS, PMAPS 2024 | 2024年
关键词
ampacity prediction; artificial neural networks; long short-term memory; gated recurrent unit; dynamic line rating;
D O I
10.1109/PMAPS61648.2024.10667135
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
Dynamic thermal rating forecasting plays an important role in the efficient management of operating conditions for overhead lines on power distribution systems. In this study, a novel framework that allows generating models that accurately forecast ampacity feature of an overhead transmission line is proposed, in order to optimize the amount of transmitted energy. For this purpose, several techniques based on artificial neural networks are used in the process. The techniques range from the classic multi-layer perceptron neural network to the more advanced recurrent neural networks: long short-term memory and gated recurrent unit. The predictions from these three techniques are analyzed and compared to finally determine which of the generated models is the most appropriate to obtain ampacity forecasts at a horizon of 24 hours. The results obtained provide valuable information within the studied area and provide accurate models for ampacity forecasting.
引用
收藏
页码:396 / 401
页数:6
相关论文
共 50 条
  • [41] Recurrent Neural Networks for Transmission Opportunity Forecasting
    Ferreira, Paulo A. L.
    Fernandes, Silas S.
    Bezerra, Rodrigo R.
    Lamar, Marcus V.
    Bordim, Jacir L.
    PROCEEDINGS 2016 IEEE 13TH INTERNATIONAL CONFERENCE ON MOBILE AD HOC AND SENSOR SYSTEMS (MASS 2016), 2016, : 382 - 383
  • [42] Probabilistic forecasting of dynamic thermal line rating with temporal correlations
    Barton, Tomas
    Musilek, Petr
    INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2022, 134
  • [43] Dynamic line rating forecasting based on numerical weather prediction
    Fernandez, Elvira
    Albizu, Igor
    Buigues, Garikoitz
    Valverde, Victor
    Etxegarai, Agurtzane
    Olazarri, Jon G.
    2015 IEEE EINDHOVEN POWERTECH, 2015,
  • [44] Nonlinear observer design using dynamic recurrent neural networks
    Kim, YH
    Lewis, FL
    Abdallah, CT
    PROCEEDINGS OF THE 35TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 1996, : 949 - 954
  • [45] Reinforcement learning of dynamic behavior by using recurrent neural networks
    Ahmet Onat
    Hajime Kita
    Yoshikazu Nishikawa
    Artificial Life and Robotics, 1997, 1 (3) : 117 - 121
  • [46] Dynamic input/output linearization using recurrent neural networks
    Delgado, A
    Kambhampati, C
    Warwick, K
    ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 1721 - 1726
  • [47] Dynamic forecasting model for indoor pollutant concentration using recurrent neural network
    Hu, Lulu
    Fan, Na
    Li, Jingguang
    Liu, Yingwen
    INDOOR AND BUILT ENVIRONMENT, 2021, 30 (10) : 1835 - 1845
  • [48] Solar radiation forecasting using boosting decision tree and recurrent neural networks
    Kim, Hyojeoung
    Park, Sujin
    Kim, Sahm
    COMMUNICATIONS FOR STATISTICAL APPLICATIONS AND METHODS, 2022, 29 (06) : 709 - 720
  • [49] Hourly Forecasting of Solar Photovoltaic Power in Pakistan Using Recurrent Neural Networks
    Khan, Sohrab
    Shaikh, Faheemullah
    Siddiqui, Mokhi Maan
    Hussain, Tanweer
    Kumar, Laveet
    Nahar, Afroza
    INTERNATIONAL JOURNAL OF PHOTOENERGY, 2022, 2022
  • [50] Time Series Forecasting using Recurrent Neural Networks and Wavelet Reconstructed Signals
    Garcia-Pedrero, Angel
    Gomez-Gil, Pilar
    20TH INTERNATIONAL CONFERENCE ON ELECTRONICS COMMUNICATIONS AND COMPUTERS (CONIELECOMP 2010), 2010, : 169 - 173