Ordered visibility graph weighted averaging aggregation operator: A methodology based on network analysis

Abstract

The ordered weighted averaging (OWA) operators are widely used in many applications. Determining the OWA operator weights is still an open issue. In this paper, an ordered visibility graph weighted averaging (OVGWA) aggregation operator is proposed based on complex network methodology. After the argument values are ordered in descending order, a network is constructed using ordered visible graph (OVG) method. The arriving probabilities of random walker in the network are utilized as the weights of the corresponding data. Compared with the classical OWA, the proposed OVGWA not only takes the information of orders but also the argument values themselves into consideration to determine the weights. An application of produced water management is used to illustrate the application of the proposed OVGWA aggregation operator. In addition, the aggregated results are compared with those obtained by maximal entropy method. The results show that the proposed method is effective. To study the impacts of the influencing factors, a sensitivity analysis has been carried out. It is utility to understand the role of different indicators on aggregated value.