【作者】 秦磊； 邹斌；

【Author】 QIN Lei ZOU Bin (School of Communication and Control Engineering,Southern Yangtze University,Wuxi 214122,China.

【机构】 江南大学 通信与控制工程学院；

【摘要】 对基于小波分析和神经网络的3种短期电价预测模型进行了研究,提出了一种预测误差分布函数的概念, 并以此作为指标对3种预测模型的预测结果进行评估．为了对比分析,以美国加州电力市场的实际运行数据为基础, 连续预测了该市场的1个月电价,结果证明了提出的具有滚动预测概念的模型Ⅲ有良好的预测精度,同时其误差分布还显示出该模型有较高的预测置信度．更多还原

【Abstract】 Three forecasting models based on wavelet analysis and neural network are analyzed.A conception of forecasting error probability distribution is presented,which is used as an important factor to evaluate the forecasting result.To compare the results,one month continuously is forecasted by using three models based on the historical hourly electricity prices of the California electricity market.The results show that the forecasting model Ⅲ has higher accuracy of forecasting,and the error probability distribution indicates it has a good confidence degree.更多还原