RS-RBFNN在电力通信网可靠性评估中的应用  

Applications of RS-RBFNN on Reliability Evaluation of Communication Networks

作　　者：高勇[1] 赵振东[1] 肖学东[2] 李宝洪[2] 

机构地区：[1]华北电力大学电子与通信工程系,河北保定071003 [2]黑龙江省电力有限公司通信自动化中心,黑龙江哈尔滨150090

出　　处：《电子质量》2010年第4期41-43,共3页Electronics Quality

摘　　要：指标体系的建立是通信网可靠性评估工作中的一个重要环节,然而由于指标的不确定性和指标间的复杂关系,使得指标的选取以及合理指标体系的建立都变得非常困难。为了解决指标的选取问题,文章采用粗糙集(RS)理论中的属性约简与径向基神经网络(RBFNN)相结合的方法对电力通信网可靠性进行仿真评估。该方法通过降低径向基神经网络输入的维数来提高神经网络的训练速度和评估能力。仿真结果验证了该方法在通信网可靠性评估中的有效性与可行性。The establishment of index system is an important part in the reliability evaluation of electric power communication networks, The uncertainty of the indexes and the complicated relationship among them makes it difficult to select the indexes, and to establish a truly reasonable index system as well. To solve the problem, we introduce a new method, which combines the rough set （RS） attribute reduction theory with radial based function neural network （PBFNN）, to evaluate the reliability of electric power communication networks. The method can improve both the training speed of the neural network and the accuracy of the evaluation results by reducing the input dimensions of the network. Simulation examples demonstrate its good performance and the effectiveness in the evaluation of electric power communication networks.

关 键 词：粗糙集 属性约简 径向基神经网络 通信网评估 可靠性指标 

分 类 号：TN915.853[电子电信—通信与信息系统]