Scenario Generation Method Covering Extreme Form Load Based on Improved Diffusion Model

DOU Xun; NIU Pengyi; ZHENG Yaxian; FENG Shuhai; SHI Fei; YANG Hanyu

doi:10.13334/j.0258-8013.pcsee.241362

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Scenario Generation Method Covering Extreme Form Load Based on Improved Diffusion Model

更新时间：2026-01-04

- Scenario Generation Method Covering Extreme Form Load Based on Improved Diffusion Model
- Issue 23, Pages: 9152-9164(2025)
- 作者机构：
  
  1. 南京工业大学电气工程与控制科学学院,江苏省,南京市,211816
  2. 中国电力科学研究院南京分院,江苏省,南京市,222200
- 作者简介：
- 基金信息：
- DOI：10.13334/j.0258-8013.pcsee.241362
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
DOU Xun, NIU Pengyi, ZHENG Yaxian, et al. Scenario Generation Method Covering Extreme Form Load Based on Improved Diffusion Model[J]. 2025, (23): 9152-9164.
DOI：

DOU Xun, NIU Pengyi, ZHENG Yaxian, et al. Scenario Generation Method Covering Extreme Form Load Based on Improved Diffusion Model[J]. 2025, (23): 9152-9164. DOI： 10.13334/j.0258-8013.pcsee.241362.

摘要

新能源规模化接入及极端天气导致电力需求剧烈波动的极端场景频发，对电力系统安全运行产生较大影响。针对这一问题，提出一种基于改进扩散模型的涵盖极端形态场景构建方法，模拟生成电力系统中各种可能的极端场景，为制定有效的策略和应对措施提供数据基础，降低试错成本。首先，定义低谷、平段、高峰3个时段的极端/正常状态，基于马尔科夫链构建各时段状态转移概率矩阵并生成场景状态集；然后，利用改进扩散模型生成各时段的不同形态数据，构建数据采样群，通过从数据采样群中随机采样并填充至场景状态集以实现场景构建；最后，通过算例分析，验证所提方法在涵盖极端形态的场景生成上的可靠性及高效性。

Abstract

In the power system

the rapid integration of new energy and extreme weather leads to frequent extreme scenarios of severe fluctuations in power demand

which has a great impact on the safe operation of the power system. In order to solve this problem

this paper proposes a method of constructing extreme scenarios based on improved diffusion model. By simulating various possible extreme scenarios in power system

it can provide data basis for formulating effective strategies and countermeasures

and reduce the cost of trial and error. The definition of extreme and normal states of trough

flat and peak periods is proposed. Based on Markov chain

the state transition probability matrix of each period is constructed and the scene state set is generated. The improved diffusion model is used to generate different forms of data in each period

and the data sampling group is constructed. The scene construction is realized by randomly sampling from the data sampling group and filling it into the scene state set. Through the example analysis

the reliability and efficiency of the proposed method in the generation of scenes covering extreme forms are verified.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A WGAN-GP Approach for Multi-scenario Specific Photovoltaic Generation With Feature-constrained and Target-driven Optimization

Collaborative Planning of Flexible Resources Considering the Transformation of Coal-fired Units in Typical and Extreme Scenarios

A Methodology for Generating Wind Power Extreme Scenarios Triggered by Medium-range Weather Processes

基于连续时间马尔可夫链的继电保护装置动作行为预测模型

基于条件生成对抗网络的可再生能源日前场景生成方法

Related Author

QIU Jian

DONG Shufeng

PENG Weifeng

CHEN Xinyi

LIU Lu

ZHANG Xiaohu

CHENG Haozhong

XU Ling

Related Institution

浙江大学电气工程学院

Key Laboratory of Control of Power Transmission and Conversion of Ministry of Education (Shanghai Jiao Tong University), Minhang District

East China Power Grid Company, Pudong New Area

State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources (North China Electric Power University), Changping District

Department of Electrical Engineering, Tsinghua University, Haidian District

AI问答

⁰