多资源均衡优化中基于专家权重聚类的权重优选法

The Weight Optimal Choice Method Based on Experts' Weights Clustering Analysis in Multi-resource Leveling Optimization

针对多资源均衡优化中如何恰当确定多资源权重系数问题,本文提出了基于专家权重聚类的权重优选法,将专家权重分为类别间权重和类别内权重,对专家聚类步骤和类别间权重的计算方法进行了改进。通过专家给出的判断矩阵构建相容度矩阵,利用系统聚类原理,对相容度矩阵聚类得到最大相容度谱系图。通过最大相容度间的距离和给定阈值的比较,对专家恰当分类,从而避免了根据现有研究步骤只能将专家分为两类的不足。此外,在确定类别间权重时,除继续对容量较大的类赋予较大的类别间权重系数外,还引入专家判断矩阵的属性权重一致性来反映类别间的差异,从而有效避免当某几类专家中含有相等数目专家时,赋予这几类专家相同类别间权重系数的问题。所提方法结构清晰、计算简便,并使得资源权重计算结果更为合理准确。最后运用一个算例对比验证了该方法的可行性和有效性。

In order to appropriately determine the weight coefficient of multi-resource in multi-resource leveling optimization,this paper proposes a weight optimal choice method based on experts' weights clustering.The experts' weight is divided into the weights between categories and within category.The steps of experts' clustering and the calculation method of the weights between categories are improved.The clustering pedigree chart of the maximum compatibility degree is got by building the expert judgment compatibility matrix according to the expert judgment matrix,making use of the system clustering principle to cluster the compatibility degree matrix.The experts are classified properly according to the comparison of the distance between the maximum compatibility degree and the given threshold value,which overcomes the shortcoming of only clustering the experts into two categories in existing literatures.In addition,while determining the weights between categories,it not only gives greater weight for the larger capacity,but also reflects the difference between categories by introducing the attribute's weight consistence of the experts' judgment matrix,which avoids giving the same weights between categories for those who have the same number experts.The structure of the proposed method is clear and the calculation is simple,which makes the final result of resources' weights more reasonable and accurate.Finally,an example is compared to validate the feasibility and effectiveness of the presented method.