基于BP-MIV的风电调峰受阻电量影响因素贡献度分析
摘要:随着风电装机容量的不断增长，弃风电量也随之增加，研究弃风电量的影响因素势在必行。为此，提出了一种风电调峰受阻电量影响因素贡献度计算方法。以影响因素为输入，风电调峰受阻电量为输出，构建了反向(back propagation, BP)神经网络模型；应用平均影响值(mean impact value, MIV)算法，计算各影响因素的贡献度；利用我国西北某电网2018年运行数据进行案例分析。结果表明，本文所提方法能对风电调峰受阻电量影响因素进行量化分析，明确影响因素的重要程度，为促进风电消纳提供理论基础。
Abstract：In recent years, wind power curtailment has been a big concern with the rapid growth of wind power installed capacity in China. It is essential to investigate influential factors of wind power curtailment and how much these factors affect wind power curtailment. A novel method to quantify influential factors of wind power curtailment caused by lack of load-following capability is proposed. First, this paper applies back propagation(BP) neural network to model the nonlinear relationship between influential factors and wind power curtailment caused by lack of load-following capability. Then, this paper utilizes mean impact value(MIV) to compute contribution of influential factors. Finally, case study on a provincial power grid in northwest region of China is carried out to validate the proposed method. The study result indicates that the proposed method can quantify the importance of each influential factor.
标题：基于BP-MIV的风电调峰受阻电量影响因素贡献度分析
title:Contribution Analysis of Influential Factors for Wind Power Curtailment Caused by Lack of Load-Following Capability Based on BP-MIV
作者：谢桦,吕晓茜,张沛
authors:XIE Hua,LYU Xiaoxi,ZHANG Pei
关键词：风电调峰受阻,反向(BP)神经网络,平均影响值(MIV)算法,影响因素,贡献度,
keywords:wind power curtailment,back propagation (BP) neural network,mean impact value (MIV),influential factors, contribution,
发表日期：2019-12-30
- 文件大小:
- 1.08 MB
- 下载次数:
- 60
-
高速下载
|
|
