A Model-Free Deep Reinforcement Learning-Based Approach for Assessment of Real-Time PV Hosting Capacity

被引:1
作者
Suchithra, Jude [1 ]
Robinson, Duane A. [1 ]
Rajabi, Amin [2 ]
机构
[1] Univ Wollongong, Australian Power Qual Res Ctr, Wollongong 2522, Australia
[2] DIgSILENT Pacific, Sydney 2000, Australia
关键词
hosting capacity; deep reinforcement learning; deep learning; low voltage networks; quasi-static time series;
D O I
10.3390/en17092075
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
Assessments of the hosting capacity of electricity distribution networks are of paramount importance, as they facilitate the seamless integration of rooftop photovoltaic systems into the grid, accelerating the transition towards a more carbon neutral and sustainable system. This paper employs a deep reinforcement learning-based approach to evaluate the real-time hosting capacity of low voltage distribution networks in a model-free manner. The proposed approach only requires real-time customer voltage data and solar irradiation data to provide a fast and accurate estimate of real-time hosting capacity at each customer connection point. This study addresses the imperative for accurate electrical models, which are frequently unavailable, in evaluating the hosting capacity of electricity distribution networks. To meet this challenge, the proposed approach utilizes a deep neural network-based, data-driven model of a low-voltage electricity distribution network. This proposed methodology incorporates model-free elements, enhancing its adaptability and robustness. In addition, a comparative analysis between model-based and model-free hosting capacity assessment methods is presented, highlighting their respective strengths and weaknesses. The utilization of the proposed hosting capacity estimation model enables distribution network service providers to make well-informed decisions regarding grid planning, leading to cost minimization.
引用
收藏
页数:12
相关论文
共 15 条
  • [1] [Anonymous], 2020, AS/NZS 4777.2
  • [2] Electrical Model-Free Voltage Calculations Using Neural Networks and Smart Meter Data
    Bassi, Vincenzo
    Ochoa, Luis F.
    Alpcan, Tansu
    Leckie, Christopher
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2023, 14 (04) : 3271 - 3282
  • [3] Model-free voltage control of active distribution system with PVs using surrogate model-based deep reinforcement learning
    Cao, Di
    Zhao, Junbo
    Hu, Weihao
    Ding, Fei
    Yu, Nanpeng
    Huang, Qi
    Chen, Zhe
    [J]. APPLIED ENERGY, 2022, 306
  • [4] Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges
    Chen, Xin
    Qu, Guannan
    Tang, Yujie
    Low, Steven
    Li, Na
    [J]. IEEE TRANSACTIONS ON SMART GRID, 2022, 13 (04) : 2935 - 2958
  • [5] Fast Quasi-Static Time-Series (QSTS) for yearlong PV impact studies using vector quantization
    Deboever, Jeremiah
    Grijalva, Santiago
    Reno, Matthew J.
    Broderick, Robert J.
    [J]. SOLAR ENERGY, 2018, 159 : 538 - 547
  • [6] Ebe Falko, 2017, CIRED - Open Access Proceedings Journal, V2017, P2265, DOI 10.1049/oap-cired.2017.0848
  • [7] Haarnoja T, 2018, Arxiv, DOI [arXiv:1801.01290, 10.48550/arXiv.1801.01290, DOI 10.48550/ARXIV.1801.01290]
  • [8] Haarnoja T, 2019, Arxiv, DOI [arXiv:1812.05905, DOI 10.48550/ARXIV.1812.05905]
  • [9] Probabilistic load flow for distribution systems with uncertain PV generation
    Kabir, M. N.
    Mishra, Y.
    Bansal, R. C.
    [J]. APPLIED ENERGY, 2016, 163 : 343 - 351
  • [10] Safe deep reinforcement learning-based constrained optimal control scheme for active distribution networks
    Kou, Peng
    Liang, Deliang
    Wang, Chen
    Wu, Zihao
    Gao, Lin
    [J]. APPLIED ENERGY, 2020, 264 (264)