Long Step Spatial-temporal Prediction of Spot Electricity Price Based on STD-ST-Former

ZHANG Pengfei; HU Bo; HU Zhanshuo; LUO Huanhuan; LIU Hengyu; XING Zuoxia

doi:10.13334/j.0258-8013.pcsee.240616

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Long Step Spatial-temporal Prediction of Spot Electricity Price Based on STD-ST-Former

更新时间：2026-07-27

- Long Step Spatial-temporal Prediction of Spot Electricity Price Based on STD-ST-Former
- Vol. 45, Issue 19, Pages: 7456-7467(2025)
- 作者机构：
  
  1. 沈阳工业大学电气工程学院,辽宁省,沈阳市,110870
  2. 国网大连供电公司,辽宁省,大连市,116001
  3. 沈阳工程学院国际教育学院,辽宁省,沈阳市,110136
  4. 辽宁电力交易中心有限公司,辽宁省,沈阳市,110055
  5. 国网辽宁省电力有限公司电力科学研究院,辽宁省,沈阳市,110000
- 作者简介：
- 基金信息：
- DOI：10.13334/j.0258-8013.pcsee.240616
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
ZHANG Pengfei, HU Bo, HU Zhanshuo, et al. Long Step Spatial-temporal Prediction of Spot Electricity Price Based on STD-ST-Former[J]. 2025, 45(19): 7456-7467.
DOI：

ZHANG Pengfei, HU Bo, HU Zhanshuo, et al. Long Step Spatial-temporal Prediction of Spot Electricity Price Based on STD-ST-Former[J]. 2025, 45(19): 7456-7467. DOI： 10.13334/j.0258-8013.pcsee.240616.

摘要

精准的现货电价预测能够为市场参与者的交易策略提供有利的指导，为提高区域现货电价的长步时空预测精度，提出一种基于季节趋势分解-双通道时空transformer(spatial- temporal transformer，ST-Former)的区域现货电价预测框架。该预测框架采用分解的思想，通过解开区域现货电价中纠缠的时间模式，从而获得更可预测的稳定的趋势部分和波动的季节部分，在此基础上，提出一种基于可变Patch时间注意力和空间自注意力相结合的ST-Former模型，以挖掘区域现货电价的长步时空特征；然后，通过ST-Former模型分别对趋势部分和季节部分进行建模构成双通道模型框架；最后，将双通道模型框架的输出结果进行聚合得到最终预测结果，实现区域现货电价的长步时空预测。以澳大利亚电力市场的区域现货电价数据为例，与12种预测方法进行对比，验证所提预测框架的有效性和优越性。

Abstract

Accurate prediction of spot price can provide beneficial guidance for market participants in trading strategies. In order to improve the long step spatial-temporal prediction accuracy of regional spot electricity price

a prediction framework using dual channel spatial-temporal transformer (ST-Former) based on seasonal trend decomposition is proposed. This prediction framework adapts the idea of decomposition

and obtain more predictable results including a stable trend part and a fluctuating seasonal part by untangling the entangled time patterns in regional spot electricity prices. On this basis

a ST-Former model based on the combination of variable Patch temporal attention and spatial self-attention is proposed

to explore the long step spatial- temporal features of regional spot electricity prices. Then

the ST-Former model is used to model the trend part and seasonal part

forming a dual channel model framework. Finally

the output results of the dual channel model framework are aggregated to obtain the final prediction of regional spot electricity prices. Taking the spot electricity price data of the Australian electricity market as an example

the effectiveness and superiority of the proposed prediction framework are verified by comparing with twelve prediction methods.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Industrial User Decision Model Considering Differentiated Power Quality Services in the Context of Carbon Market

Edge Computing Approach for Electricity Theft Detection Utilizing Lightweight Multi-channel Attention Fusion Network

Tiered Marginal Pricing Mechanism in Electricity Spot Markets Considering Consumer-side Affordability

Liquidity Risk Quantification and Management of Utility Companies Based on Auction Revenue Rights

Integrated Power Balancing Under the Unified National Electricity Market Environment

Related Author

ZHANG Yi

XIANG Mengru

ZHENG Zonghua

JIN Tao

WANG Wanhao

HUANG Qinyu

LIU Yulong

Related Institution

福州大学电气工程与自动化学院

College of Electrical Engineering and Automation, Fuzhou University

School of Electrical Engineering, Zhengzhou University

State Key Laboratory of Power Transmission Equipment Technology (Chongqing University), Shapingba District

State Grid Henan Electric Power Company Economic and Technical Research Institute

AI问答

⁰