Behavior Reconstruction Models for Large-scale Network Service Systems

Abstract

In large-scale network service systems, the phenomenon of instantaneous gathering of a large number of users can cause system abnormality, whenever the load imposed by the user behaviors does not match the system load. This paper proposes a behavior reconstruction model for large-scale network service systems integrated with Petri net reconstruction methodology, for the purpose of achieving load balancing in the system under increasing number of users. Based on the features of the user interaction behavior sequence, the behavioral load balancing model defines a user behavior membership function. Then, a random fuzzy Petri net with delay is presented to control the user behavior reconstruction. Experiments conducted by considering various changes in the number of user behaviors and their distribution in unit time demonstrate that the proposed methodology can effectively trigger the reconstructed model to balance the system load when the system load exceeds the defined warning point.

Fog computing systems: State of the art, research issues and future trends, with a focus on resilience

“…This verification of potential system vulnerabilities is designated as penetration testing. In addition, the literature has a considerable number of SDN-based solutions to enhance diverse network features, such as network security [118][119] [120], network communications [121][122] [123], energy efficiency [124] and network lifetime [125].…”

A Model Based on Convolutional Neural Network for Online Transaction Fraud Detection

“…Zhang and J. Cui proposed a method to discover user's abnormal behavior from a system perspective. Zhang Z., Ge L. [16] et al proposed an effective way to solve user behavior anomalies through system behavior reconstruction.…”

A Scalable Method of Maintaining Order Statistics for Big Data Stream

“…The traditional application is built on the concept of persistent data sets that are stored reliably in stable storage and queried or updated several times throughout their lifetime ]. Nowadays, large volumes of stream data arise rapidly, such as transactions in bank account ] or e-commerce business [Yu, Ding, Liu et al (2018)], credit card operations, data collection in Internet of Things (IoT) [Miao, Liu, Xu et al (2018)], information in disaster management systems [Wu, Yan, Liu et al (2015); Xu, Zhang, Liu et al (2012); Wang, Zhang and Pengwei (2018)], behavior data analysis and anomaly detection in large-scale network service system [Zhang, Ge, Wang et al (2017); Zhang and Cui (2017)] and data mining in live streaming [Li, Zhang, Xu et al (2018)]etc. Analysis of order statistics plays an important role in analyzing data stream, which can help us to know the distribution of the data, make decisions, detect the anomaly data or help further data mining.…”