基于深度学习和蒙特卡洛树搜索的机组恢复在线决策

SUN Runjia

您当前的位置：

首页 >

文章列表页 >

基于深度学习和蒙特卡洛树搜索的机组恢复在线决策

更新时间：2025-08-13

- 基于深度学习和蒙特卡洛树搜索的机组恢复在线决策
- Automation of Electric Power Systems Vol. 42, Issue 14, Pages: 40-47(2018)
- 作者机构：
  
  电网智能化调度与控制教育部重点实验室(山东大学),山东省,济南市,250061
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2018
- 稿件说明：
移动端阅览
SUN Runjia. [J]. Automation of electric power systems, 2018, 42(14): 40-47.
DOI：

SUN Runjia. [J]. Automation of electric power systems, 2018, 42(14): 40-47. DOI：

摘要

针对大停电后电力系统初始状态和恢复过程中线路恢复状况的不确定性，提出一种基于深度学习和蒙特卡洛树搜索(MCTS)的机组恢复在线决策方法。采用一种深度学习算法——稀疏自动编码器(SAE)对自动生成的训练集进行训练，建立估值网络；根据系统状态，利用改进的上限置信区间(UCT)算法、支路修剪技术和估值网络对机组恢复措施进行MCTS；汇总并行的多次MCTS结果，以加权机组发电量为决策指标确定最终的恢复措施。以新英格兰10机39节点系统和山东西部电网为例验证了所提方法的可行性和有效性；相比于传统方法，所提方法能够获得具有较高鲁棒性的恢复方案，并有效应对机组恢复过程中的多种不确定性状况。

Abstract

For the uncertainty of the initial condition of power system after blackout and the restoration condition of transmission lines during restoration

an online decision-making strategy for generator start-up is proposed based on deep learning and Monte Carlo tree search(MCTS). A method for training samples is proposed to generate samples of generator start-up atomically. The sparse autoencoder(SAE)is introduced to train the training samples for a value network. Based on the condition of power system

the modified upper confidence bound apply to tree(MUCT)algorithm

value network and move pruning are applied in MCTS to search the next restored line. The weighted total generation capability is proposed as a decision-making index to summarize the parallel computing results of MCTS and decide the next restored lines. Results of IEEE New England 10-unit 39-bus power system and the Western Shandong power grid demonstrate the feasibility and effectiveness of the proposed strategy

and the online strategy is compared with traditional strategy to show its robustness and ability of handling different uncertain situations during generator start-up.

关键词

Keywords

references

Views

2230

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Probabilistic Prediction Method for Interpretable Net Load Based on Kolmogorov-Arnold Network

Log Abnormity Detection for Distribution Master Station Based on Large Language Models

Fault Location for Active Distribution Network with High Penetration Rate Based on Improved Spatio-Temporal Graph Neural Network

Transient Stability Assessment of Power Systems Based on Multi-scale Graph Attention Network

Related Author

WU Weimin

LYU Fengqi

LEI Shunbo

LIU Qixing

LIANG Liang

HOU Yunhe

LIU Dong

GUO Guodong

Related Institution

School of Science and Engineering, The Chinese University of Hong Kong

Power Dispatch and Control Center of China Southern Power Grid

School of Mechanical Engineering and Automation, Harbin Institute of Technology

Department of Electrical and Electronic Engineering, The University of Hong Kong

State Grid Economic and Technological Research Institute Co., Ltd.

⁰