| 混合粒子群优化的BP网络在电力负荷预测中的应用 |
| |
| 引用本文： | 刘玲,严登俊,刘振国. 混合粒子群优化的BP网络在电力负荷预测中的应用[J]. 江苏电机工程, 2006, 25(1): 1-3 |
| |
| 作者姓名： | 刘玲 严登俊 刘振国 |
| |
| 作者单位： | 河海大学电气工程学院,江苏,南京,210098;江苏省电力公司,江苏,南京,210024 |
| |
| 摘 要： | 提出了混合粒子群算法和BP算法相结合的短期负荷预测方法,有效地克服了人工神经网络学习速度慢、存在局部极小点的固有缺陷。与传统神经网络方法相比,该方法可加快网络学习速度和提高学习精度。用混合粒子群算法来训练网络参数,直到误差趋于一稳定值,然后将优化的权值用BP算法处理,实现短期负荷预测。
|
| 关 键 词： | 混合粒子群 BP神经网络 短期负荷预测 |
| 文章编号： | 1009-0665（2006）01-0001-03 |
| 收稿时间： | 2005-09-06 |
| 修稿时间： | 2005-09-06 |
Applications of BP Networks Trained by Hybrid Particle Swarm Optimization in Short Term Load Forecasting of Power System |
| |
| LIU Ling,YAN Deng-jun,LIU Zhen-guo. Applications of BP Networks Trained by Hybrid Particle Swarm Optimization in Short Term Load Forecasting of Power System[J]. Jiangsu Electrical Engineering, 2006, 25(1): 1-3 |
| |
| Authors: | LIU Ling YAN Deng-jun LIU Zhen-guo |
| |
| Affiliation: | 1 .Hohai University, Nanjing 210098, China; 2. Jiangsu Electric Power Company, Nanjing 210024, China |
| |
| Abstract: | In this paper,a modified method(PSONN) for short-term load forecast is presented,which can quicken the learning speed of the network and improve the predicting precision compared with the traditional artificial neural network.We use PSO to train connection weights of multi-layer feed forward neural network(BP) until the learning error has tended to stability here;the best initial weight have been found.Then we use BP method to finish short-term load forecast process.The intrinsic defects of artificial neural network e.g.,its slow learning speed,existence of partial minimun points,are solved. |
| |
| Keywords: | hybrid particle swarm BP neural network short-term load forecasting |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
