首页> 外文会议>Asia Conference on Power and Electrical Engineering >Reliability Assessment Study of Typical Connection Mode Medium Voltage Distribution Networks using Neural Network based on MIV and MEA
【24h】

Reliability Assessment Study of Typical Connection Mode Medium Voltage Distribution Networks using Neural Network based on MIV and MEA

机译:基于MIV和MEA的神经网络典型连接方式中压配电网可靠性评估研究

获取原文

摘要

A reliability evaluation model of distribution network based on improved Elman feedback dynamic neural network is proposed. A self-feedback connection gain coefficient is added to the receiving layer of Elman neural network to measure the influence of historical information on the future state. In addition, the relevant parameters of Elman neural network are optimized by Mean Impact Value(MIV) and Mind Evolutionary Algorithm(MEA). Before the evaluation, the input variables of neural network are preprocessed by grey relational analysis. Taking several typical cable connection modes of typical medium voltage distribution networks as examples, the reliability evaluation is carried out by using the above methods. The evaluation results showes that the average relative error of the proposed method decreases from 5.24e-4 to 3.238e-5 compared with the general neural network evaluation model. It is shown that this method can effectively improve the reliability evaluation accuracy of medium voltage distribution network.
机译:提出了一种基于改进的埃尔曼反馈动态神经网络的配电网可靠性评估模型。将自反馈连接增益系数添加到Elman神经网络的接收层,以测量历史信息对未来状态的影响。此外,通过平均影响值(MIV)和思维进化算法(MEA)对Elman神经网络的相关参数进行了优化。在评估之前,通过灰色关联分析对神经网络的输入变量进行预处理。以典型的中压配电网的几种典型的电缆连接方式为例,通过上述方法进行可靠性评估。评估结果表明,与通用神经网络评估模型相比,该方法的平均相对误差从5.24e-4降低至3.238e-5。结果表明,该方法可以有效提高中压配电网的可靠性评估精度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号