| 基于EUNITE竞赛数据的中期电力负荷预测 |
| |
| 引用本文： | 李炎,翟永杰,周倩,韩璞.基于EUNITE竞赛数据的中期电力负荷预测[J].华北电力大学学报,2007,34(4):22-26. |
| |
| 作者姓名： | 李炎 翟永杰 周倩 韩璞 |
| |
| 作者单位： | 1. 华北电力大学,后勤与资产管理处,河北,保定,071003
2. 华北电力大学控制科学与工程学院,河北,保定,071003 |
| |
| 基金项目： | 华北电力大学博士学位教师科研基金资助项目(200512014) |
| |
| 摘 要： | 应用自组织模糊神经网络(SOFNN)算法,基于欧洲智能技术网络(EUNITE)竞赛数据进行了中期电力负荷预测的应用研究。算法能够自动决定神经模型的结构并得出模型的参数,具有很好的实用价值。研究了训练数据选取和输入特征向量编码等实际应用问题,结果表明负荷预测精度高,优于竞赛的优胜者,之后提出了结合周平均负荷预测修正日负荷预测的方法,精度得到进一步地提高。
|
| 关 键 词： | 模糊神经网络 自组织 负荷预测 |
| 文章编号： | 1007-2691（2007）04-0022-05 |
| 修稿时间： | 2007-03-30 |
Mid-term load forecasting based on EUNITE competition data |
| |
| LI Yan,ZHAI Yong-jie,ZHOU Qian,HAN Pu.Mid-term load forecasting based on EUNITE competition data[J].Journal of North China Electric Power University,2007,34(4):22-26. |
| |
| Authors: | LI Yan ZHAI Yong-jie ZHOU Qian HAN Pu |
| |
| Affiliation: | 1. Department of Logistics and Assets Adrninistation, North China Electric Power University, Baoding 071003, China; 2.School of Control Science and Engineering, North China Electric Power University,Baoding 071003, China |
| |
| Abstract: | The self-organizing fuzzy neural network(SOFNN) algorithm was applied for load forecasting with the data of EUNITE competition.The algorithm can automatically determine the model structure and identify the model parameters.The training data selection and input variables encoding problems were also discussed in details.The results show that SOFNN can outperform winners' models by providing very promising prediction accuracy.Further more,the average load value in each week was forecasted to revise the daily load.Through this procedure,better forecasting accuracy can be achieved. |
| |
| Keywords: | fuzzy neural networks self-organizing load forecasting |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
