Method, system, device and medium for generating scenario data of electricity spot market

By combining nonparametric kernel density estimation and multidimensional Copula function with Latin hypercube sampling, high-fidelity electricity spot market scenario data is generated, solving the problem of pseudo-scenario generation in existing technologies and improving the accuracy of simulation evaluation.

CN122414944APending Publication Date: 2026-07-17CHINA THREE GORGES CORPORATION
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA THREE GORGES CORPORATION
Filing Date
2026-04-23
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies cannot generate data that accurately reflects real-world electricity spot market scenarios, leading to severe distortions in downstream simulation assessments and consequently, economic losses.

Method used

By employing a method that combines nonparametric kernel density estimation, multidimensional Copula function, and conditionally constrained Latin hypercube sampling, we can accurately characterize the nonlinear coupling features between renewable energy output and spot market electricity prices, and generate high-fidelity time-series data of the electricity spot market.

Benefits of technology

By eliminating the generation of false scenarios, the generated data is ensured to conform to real electricity market conditions, thereby improving the accuracy of downstream simulation assessments and avoiding economic losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122414944A_ABST
    Figure CN122414944A_ABST
Patent Text Reader

Abstract

本申请公开了电力现货市场的场景数据生成方法、系统、设备及介质,属于电力系统分析技术领域,包括:获取电力系统中目标节点的新能源出力时序和现货市场电价时序;采用非参数核密度估计构建任意时刻的边缘累积分布函数和;利用概率积分变换,得到边缘概率序列和;采用多维Copula函数构建边缘概率序列中的概率变量和之间的非线性联合累积分布模型;将其一阶条件偏导数作为拉丁超立方抽样算法的硬约束方程,生成满足条件概率关系的序列对;计算概率序列对应的真实物理量并生成三维数据张量作为无伪场景时序数据。本方法能够捕捉新能源出力与电力现货市场电价的非线性耦合关系,生成符合市场真实规律的时序场景数据。
Need to check novelty before this filing date? Find Prior Art