改进熵权法及其在电能质量评估中的应用

A New Improved Entropy Method and Its Application in Power Quality Evaluation

提出了一种新的基于改进熵权法的电能质量评估方法,修正了传统熵权法在所有熵值都趋近于1时熵权与熵值传递的信息不一致的问题,并通过设计反向传播(BP)神经网络模型提高该算法的快捷性。首先结合序关系分析法和改进熵权法计算各项电能质量指标的综合权重,得到多指标的综合量化值,避免了过于主观或过于客观的片面评估结果;然后设计BP网络的计算模型实现该评估方法,使该评估更快捷、更具实用性;最后利用实际数据进行实例分析,验证了该算法的有效性。

This paper is concerned with a power quality evaluation method based on the improved entropy method, which fixes the problem of the traditional entropy weight method that entropy weights present a wrong message of entropy when all the entropy values are close to 1. The proposed method achieves efficient performance by designing a back propagation （BP） network calculation model. Firstly, the synthetic weights of power quality indices are calculated by sequential correlation analysis and the improved entropy method, thereby by passing the one-sidedness of being subjective or objective. And the quantitative values of multi-index are obtained. Then a BP network calculation model is designed to make the evaluation method more efficient and more practical. The evaluation by a power supply bureau has verified the effectiveness of the proposed algorithm.