| 基于小波分解的改进神经网络MCP预测方法及应用 |
| |
| 引用本文： | 魏平,李均利,陈刚,张永吉.基于小波分解的改进神经网络MCP预测方法及应用[J].电力系统自动化,2004,28(11):17-21. |
| |
| 作者姓名： | 魏平 李均利 陈刚 张永吉 |
| |
| 作者单位： | [1]浙江大学数学系，浙江省杭州市310027 [2]宁波大学信息科学与工程学院，浙江省宁波市315211 |
| |
| 基金项目： | 国家自然科学基金资助项目(60302012)，宁波市重点博士基金资助项目(2003A61006) |
| |
| 摘 要： | 电力工业的市场化改革突出了市场清算价格(MCP)预测的重要性。文中以浙江电力市场为背景，提出了一种基于小波分解和神经网络的MCP预测方法。该方法对原电价数据进行了预处理，将经小波分解去除细节后的重构电价序列作为输入参数，并且依据“重近轻远”的原则及考虑到电价具有星期的周期性的特点，重新设计了神经网络拟合误差的代价函数。对浙江电力市场下一交易日的MCP进行了预测，预测精度达到90％左右。
|
| 关 键 词： | 市场清算价格 神经网络 小波变换 价格预测 |
| 收稿时间： | 1/1/1900 12:00:00 AM |
| 修稿时间： | 1/1/1900 12:00:00 AM |
FORECASTING MCP USING A WAVELET-IMPROVED NEURAL NETWORK METHOD |
| |
| Wei Ping,Li Junli,Chen Gang,Zhang Yongji.FORECASTING MCP USING A WAVELET-IMPROVED NEURAL NETWORK METHOD[J].Automation of Electric Power Systems,2004,28(11):17-21. |
| |
| Authors: | Wei Ping Li Junli Chen Gang Zhang Yongji |
| |
| Abstract: | Reforms of power industry to open electricity markets make market clearing price (MCP) forecasting more important. According to Zhejiang circumstance, this paper presents a wavelet-improved neural network method, which inherits the advantage of neural network model. In addition, by adding a data preprocess procedure, price series after subtracting details with wavelet transform are choosed as an input parameter, and error function of ANN is redesigned by "emphasizing recent data" principle and considering "week period" in MCP series. Application to the real power system shows the accuracy of the proposed method is about 90% . |
| |
| Keywords: | market clearing price (MCP) neural networks wavelet transform price forecasting |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《电力系统自动化》浏览原始摘要信息 |
|
点击此处可从《电力系统自动化》下载全文 |
