[1]李益国,沈炯.基于ν-支持向量机的边际电价预测及置信区间估计[J].东南大学学报(自然科学版),2007,37(1):70-73.[doi:10.3969/j.issn.1001-0505.2007.01.016]
 Li Yiguo,Shen Jiong.System marginal price prediction and confidence interval estimation with ν-support vector machine[J].Journal of Southeast University (Natural Science Edition),2007,37(1):70-73.[doi:10.3969/j.issn.1001-0505.2007.01.016]
点击复制

基于ν-支持向量机的边际电价预测及置信区间估计()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
37
期数:
2007年第1期
页码:
70-73
栏目:
电气工程
出版日期:
2007-01-20

文章信息/Info

Title:
System marginal price prediction and confidence interval estimation with ν-support vector machine
作者:
李益国 沈炯
东南大学能源与环境学院, 南京 210096
Author(s):
Li Yiguo Shen Jiong
School of Energy and Environment, Southeast University, Nanjing 210096, China
关键词:
电力市场 边际电价 ν-支持向量机 置信区间
Keywords:
electricity market system marginal price ν-support vector machine confidence intervals
分类号:
TM73
DOI:
10.3969/j.issn.1001-0505.2007.01.016
摘要:
引入ν-支持向量机,通过构造和求解一个凸优化问题,同时实现了对边际电价的预测和对置信区间的估计,且无需假定预测偏差的概率分布.在ν-支持向量回归中,当ε>0时,ν是错误样本的个数占总样本个数份额的上界.利用该性质,边际电价预测的置信度和置信区间可以很自然地用参数1和变量ε来表示,这为发电公司进行竞价方案的风险分析打下了很好的基础.算例仿真表明,该方法具有较好的泛化性能和较高的预测精度.
Abstract:
ν-support vector machine is employed to achieve system marginal price prediction and confidence interval estimation simultaneously by constructing and solving a convex optimization problem. Hypothesis for prediction-error distribution is unnecessary in this method. In ν-support vector regression, ν is an upper bound on the fraction of errors if the resulting ε is greater than zero, therefore prediction confidence level and confidence interval can be expressed with the parameter 1 and variable ε naturally, which will play important role in risk assessment of bidding strategy. Simulation results demonstrate that this method has better generalization performance and prediction accuracy.

参考文献/References:

[1] Nogales Francisco J,Contreras J,Conejo A J,et al.Forecasting next-day electricity price by time series models[J]. IEEE Trans on Power Systems, 2002,17(2):342-348.
[2] Kim Chang-il,Yu In-keun.Prediction of system marginal price of electricity using wavelet transform analysis[J].Energy Conversion and Management,2002,43(14):1839-1851.
[3] 张春辉,闵勇.级联相关的神经网络模型在边际电价预测中的应用[J].电力系统自动化,2003,27(3):28-30.
  Zhang Chunhui,Min Yong.Application of the cascaded correlation network to forecast the marginal clearing price in power market[J].Automation of Electric Power Systems,2003,27(3):28-30.(in Chinese)
[4] 赵庆波,周原冰.模糊神经网络在电力系统边际电价预测中的应用[J].电网技术,2004,28(7):45-48.
  Zhao Qingbo,Zhou Yuanbing.Application of fuzzy neural network in power system marginal price forecasting[J].Power System Technology,2004,28(7):45-48.(in Chinese)
[5] 许涛,贺仁睦.基于输入空间压缩的短期负荷预测[J].电力系统自动化,2004,28(6):51-54.
  Xu Tao,He Renmu.Short-term load forecasting based on input dimension reduction[J].Automation of Electric Power Systems,2004,28(6):51-54.(in Chinese)
[6] Chen Bojuen,Chang Mingmei.Load forecasting using support vector machines:a study on EUNITE competition 2001[J].IEEE Trans on Power Systems,2004,19(4):1821-1830.
[7] 郑华,谢莉.电力市场下系统边际价格混合预测模型的新研究[J].中国电机工程学报,2005,25(17):66-71.
  Zheng Hua,Xie Li.Study on hybrid model for system marginal price forecasting in electricity market [J].Proceedings of the CSEE,2005,25(17):66-71.(in Chinese)
[8] Scholkopf B,Bartlett P. Advances in neural information processing systems:shrinking the tube:a new support vector regression algorithm[M].Cambridge:MIT Press,1998.
[9] Chalimourda A,Scholkopf B,Smola A J.Experimentally optimal v in support vector regression for different noise models and parameter settings[J]. Neural Networks,2004,17(1):127-141.

相似文献/References:

[1]刘福斌,李扬,魏萍,等.电力市场中一种新型有效的潮流搜索策略[J].东南大学学报(自然科学版),2002,32(2):232.[doi:10.3969/j.issn.1001-0505.2002.02.018]
 Liu Fubin,Li Yang,Wei Ping,et al.Novel practicable approach for power flow tracing in electric power market[J].Journal of Southeast University (Natural Science Edition),2002,32(1):232.[doi:10.3969/j.issn.1001-0505.2002.02.018]

备注/Memo

备注/Memo:
作者简介: 李益国(1973—),男,博士,副教授,lyg@seu.edu.cn.
更新日期/Last Update: 2007-01-20