| 引用本文: | 吴忠强,张伟,李峰,杜春奇.基于云神经网络自适应逆系统的电力系统负荷频率控制[J].电力自动化设备,2017,37(11): |
| WU Zhongqiang,ZHANG Wei,LI Feng,DU Chunqi.Load frequency control of power system based on cloud neural network adaptive inverse system[J].Electric Power Automation Equipment,2017,37(11): |
|
| 摘要: |
| 针对区域互联电力系统受到风电及负荷扰动后，系统频率会出现大幅度波动的问题，提出一种基于云神经网络自适应逆系统的多区域互联电力系统负荷频率控制方法。在分析单一区域电力系统有功输出特性的基础上，建立计及多区域有功输出的互联电力系统负荷频率控制模型。采用自适应逆控制有效解决系统响应和扰动抑制的矛盾。将云模型引入自适应逆系统构建云神经网络辨识器。利用云模型在处理模糊性和随机性等不确定性方面的优势，进一步提高神经网络的辨识能力。仿真结果表明，所设计的云神经网络自适应逆系统不仅可以得到好的动态响应，还可以使风电及负荷引起的扰动减小到最小。 |
| 关键词: 互联电力系统 神经网络 云模型 自适应逆控制 负荷频率控制 |
| DOI：10.16081/j.issn.1006-6047.2017.11.014 |
| 分类号:TP273;TM761 |
| 基金项目:河北省自然科学基金资助项目(F2016203006) |
|
| Load frequency control of power system based on cloud neural network adaptive inverse system |
|
WU Zhongqiang, ZHANG Wei, LI Feng, DU Chunqi
|
|
Key Laboratory of Industrial Computer Control Engineering of Hebei Province, College of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China
|
| Abstract: |
| The system frequency will fluctuate sharply after the area interconnected power system suffered from wind power and load disturbance, for which, a load frequency control method for multi-area interconnected power system is proposed based on the cloud neural network adaptive inverse control system. The active power output characteristics of a single area power system is analyzed, based on which, the load frequency control model of interconnected power system considering multi-area active power output is built. The contradiction between system response and disturbance restrain is effectively solved by the adaptive inverse control. The cloud model is introduced into the adaptive inverse control system to construct the cloud neural network identifier. The identification ability of neural network is further improved by the advantages of cloud model in dealing with uncertainties such as fuzziness and randomness. Simulative results show that the proposed cloud neural network adaptive inverse control system can not only obtain good dynamic response, but also minimize the disturbance caused by wind power and load. |
| Key words: interconnected power system neural network cloud model adaptive inverse control load frequency control |
