SCRN: A Complex Network Reconstruction Method Based on Multiple Time Series
Abstract
Complex network reconfiguration has always been an important task in complex network research. Simple and effective complex network reconstruction methods can promote the understanding of the operation of complex systems in the real world. There are many complex systems, such as stock systems, social systems and thermal power systems. These systems generally produce correlated time series of data. Discovering the relationships among these multivariate time series is the focus of this research. This paper proposes a Spearman coefficient reconstruction network (SCRN) method based on the Spearman correlation coefficient. In the SCRN method, we select entities in the real world as the nodes of the network and determine connection weights of the network edges by calculating the Spearman correlation coefficients among nodes. In this paper, we selected a stock system and boiler equipment in a thermal power generation system to construct two complex network models. For the stock network model, we used the classic Girvan–Newman (GN) algorithm for community discovery to determine whether the proposed network topology is reasonable. For the boiler network model, we built a predictive model based on an support vector regression (SVR) model in machine learning, and we verified the rationality of the boiler model by predicting the amount of boiler steam.
The original version of this paper has been published in the Proceedings of the 2019 IEEE International Conference on Cyber, Physical and Social Computing (IEEE CPSCom-2019), Atlanta, Geogia, USA, July 12–14, 2019. Compared with the previous version, we have adjusted the structure of the paper, rewritten the first part, and revised the related work part to Preliminary information. Secondly, we have newly added Experiment A and described Experiment B in more detail. This paper was recommended by Regional Editor Tongquan Wei.
