摘要
针对电力通信网络的事前预警需求,在对基于模糊神经网络技术研究的基础上,提出了一种利用蚁群算法改进模糊神经网络,提高其全局搜索能力和收敛速度,解决了传统模糊神经网络训练过程易陷入局部极小点的问题。通过实验仿真结果表明,基于改进模糊神经网络的电力通信性能预警方法拟合度很高,具有较强的泛化能力,能够快速给运维人员提供较为可信的性能预警信息,具有较强的实用性。
On the basis of the research on fuzzy neural network technology,an ant colony algorithm is proposed to improve the fuzzy neural network based on the research of fuzzy neural network technology,which improves the global search ability and convergence speed,and solves the problem that the traditional fuzzy neural network training process is easy to fall into the local minima.The experimental simulation results show that the improved fuzzy neural network based on the power communication performance early warning method is very high fitting,has a strong generalization ability,can quickly provide the operational and maintenance personnel with more credible performance early warning information,and has strong practicability.
作者
刘文军
史慧革
周伯阳
吕卓
LIU Wenjun;SHI Huige;ZHOU Boyang;LV Zhuo(State Grid Henan Electric Power Company,Zhengzhou 450000;State Grid Henan Power Company Nanyang Power Supply Company,Nanyang 473000;State Grid Henan Electric Power Company Electric Power Research Institute,Zhengzhou 450000)
出处
《计算机与数字工程》
2020年第3期713-718,共6页
Computer & Digital Engineering
关键词
BP神经网络
性能预警
电力通信
BP neural network
performance early warning
power communication
