基于扩充样本的电力系统可靠性动态与实时研究

Dynamic and Real-time Research on Reliability Evaluation of Electric Power System Based on Extended Sample

结合动态与实时机制,研究基于BP神经网络模型生成扩充样本的电力系统可靠性评估方法。基于原始的小样本数据对BP神经网络进行学习训练,并得到特征相似的扩充样本,分析了适用于电力系统可靠性评估的经验公式和分布模型,使用最小二乘法对分布模型进行参数估计完成评估。通过继电保护系统算例分析,证明利用指数分布模型对扩充样本进行评估误差最小,同时选择数学期望经验公式最为合适。

Combined with dynamic and real-time mechanism,the paper makes a study on the reliability evaluation method of power system based on BP neural network model and extended sample.Specifically,the BP neural network model is trained through the original small sample data,and the original sample is extended to obtain the extended sample with similar characteristics.The empirical formula and distribution model for the reliability evaluation of the power system is analyzed.The parameters estimation of the distribution model is carried out with least square method.The analysis of relay protection system proves that a minor error is obtained in evaluating the expanded sample with exponential distribution model,and expectation empirical formula is the best choice.