基于最大Lyapunov指数的市场出清电价预测

来源期刊:中南大学学报(自然科学版)2011年第12期

论文作者:杨淑霞 徐琳茜 刘达 韩奇 张丽 丁晖

文章页码:3791 - 3796

关键词:混沌;Lyapunov指数;市场出清价;预测

Key words:chaos; Lyapunov exponent; market clear price; forecast

摘    要:应用相空间重构和最大Lyapunov指数的计算方法对市场出清电价序列特性进行判定。依据最大Lyapunov指数预报模式,构建基于一种新的出清电价预测模型。对某电力市场1999-01-01—1999-08-31的电价进行混沌时间序列判定,采用最大Lyapunov指数预报模型和AR(2)模型进行预测。研究结果表明:采用最大Lyapunov指数预报模型预测所得市场出清电价预测值与实际值的平均绝对误差率为7.234 7%,最大绝对误差率为17.017 5%;采用AR(2)模型预测预测所得市场出清电价预测值与实际值的平均绝对误差率为5.540 8%,最大绝对误差率为11.830 0%;总体上,最大Lyapunov指数预报模型预测结果的精度略比AR(2)模型预测结果的精度低,但绝对误差率大于6%的时点数少于AR(2)的预测数,这表明应用最大Lyapunov指数对出清电价进行预测具有可行性。

Abstract: The reconstruction of phase space and the calculation method of maximum Lyapunov exponent were used to analyze the feature of market clear electricity price series. On the basis of chaotic time series, the maximum Lyapunov exponent forecasting model, i.e, a new promoted power clear price forcasting method was proposed. Then, after determination of the electricity price data from January 1 to August 31 in 1999 of certain electricity market was applied to forecast clear electricity price. The results show that the mean absolute error rate between the forecasting results and actual values is 7.234 7% and maximum absolute error rate is 17.017 5% using the maximum Lyapunov exponent forecasting model . Using AR(2) model, the mean absolute error rate between the forecasting results and actual values is 5.540 8% and the maximum absolute error rate is 11.830 0%. In general, compared with the results of the market clear electricity price predicated by AR(2) model, the predication accuracy based on the maximum Lyapunov exponent forecasting mode is slightly lower than that based on AR(2) model, but its time points when the absolute error rate is less than 6% are higher than the latter, which shows that it is feasible to forecast the clear electricity price by the maximum Lyapunov exponent.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号