电力市场价格钉预测模型研究  

Research on Forecasting Model of Price Spikes in Power Market

作　　者：赵林度[1] 李正欣[1] 罗文彬[1] 

机构地区：[1]东南大学系统工程研究所,南京210096

出　　处：《电力学报》2009年第2期90-93,100,共5页Journal of Electric Power

摘　　要：为威胁电力系统稳定安全运行的一个重要方面。从电价价格钉的经济学分析着手,给出价格钉判别标准。最大Lyapunov指数为正数是一个时间序列具有混沌特性的必要条件。对具有混沌特性的电价序列,提出了一种基于混沌理论的价格钉预测模型——基于径向基函数的神经网络模型。运用新西兰NEMCO电力市场中昆士兰区域的电价时间序列为例,识别出电价时间序列的混沌特性,并通过数值仿真验证了模型的有效性。The deregulation of power industry brings the competitive environment, and makes the industry more efficient while the price spikes threat the power system at the same time. Based on economical analysis,criterions are given for the price spikes. A positive largest lyapunov expo- nent is a necessary condition for a time series. A neural network forecasting model based on RBF is proposed for the chaotic price spikes time series. The price series of NEMCO electricity market＇s Queensland zone is analysised as an example. Its chaos is checked,and the RBF forecasting model is proved to be effective in the market.

关 键 词：价格钉 电力市场 预测模型 混沌理论 

分 类 号：TM73[电气工程—电力系统及自动化] TP123.9[自动化与计算机技术—控制理论与控制工程]