@inproceedings{20b6ac7d261b4b0b84ed4ef7cca80ab9,
title = "Day-Ahead Optimal Dispatch in Active Distribution Network Based on Deep Reinforcement Learning with Improved Feature Extraction Network",
abstract = "The access of renewable energy will challenge the economic and stable operation of active distribution network (AND). Based on the deep reinforcement learning algorithm, this paper proposes a multi-objective intelligent day-ahead optimal dispatch method for resources in distribution network. In the day-ahead optimal dispatch, the deep reinforcement learning (DRL) method is used to deal with the uncertainty of load and renewable resources. In order to achieve the economic operation of the distribution network and reduce the peak shaving pressure of the superior power grid, the regulation scheme of energy storage system and flexible load is formulated, and an improved feature extraction network is proposed to better deal with the problem of information redundancy. The effectiveness and superiority of this method are verified by an modified IEEE-33 example.",
keywords = "active distribution network, deep reinforcement learning, multi-objective, optimal dispatch",
author = "Hanming Zhong and Peng Li and Jiahao Wang and Kecheng Li and Shaojie Zhu and Zhihao Yang",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023 ; Conference date: 15-12-2023 Through 18-12-2023",
year = "2023",
doi = "10.1109/EI259745.2023.10512578",
language = "English",
series = "2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "667--672",
booktitle = "2023 IEEE 7th Conference on Energy Internet and Energy System Integration, EI2 2023",
address = "United States",
}
