Scholarlink

In order to cope with the fluctuation of wind power generation, compressed air energy storage (CAES) system is employed to compensate the error between the actual and the predicted wind power generation(WPG) with the rapid adjustment ability of CAES. In this paper wavelet neural network model is established to forecast WPG. first. Then the probability density distribution function(PDF) and the cumulative distribution function(CDF) of WPG prediction error are established by empirical distribution model. On this basis, nonparametric kernel density estimation method is used to estimate the wind power prediction error. CAES expansion/compression rated power and the capacity of the air storage chamber are determined by the analysis of WPG prediction error. Finally, the effectiveness and the applicability of the proposed model are verified by simulation.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Capacity Configuration of CAES Based on Nonparametric Kernel Density Estimation

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Cheng Yang,
  • Shilin Lv,
  • Hao Li,
  • Chenxi Wu

摘要

In order to cope with the fluctuation of wind power generation, compressed air energy storage (CAES) system is employed to compensate the error between the actual and the predicted wind power generation(WPG) with the rapid adjustment ability of CAES. In this paper wavelet neural network model is established to forecast WPG. first. Then the probability density distribution function(PDF) and the cumulative distribution function(CDF) of WPG prediction error are established by empirical distribution model. On this basis, nonparametric kernel density estimation method is used to estimate the wind power prediction error. CAES expansion/compression rated power and the capacity of the air storage chamber are determined by the analysis of WPG prediction error. Finally, the effectiveness and the applicability of the proposed model are verified by simulation.