Routing Protocols in Opportunistic Mobile Social Networks Based on Human Behavior Pattern Detection

Abstract

With the increasing number of smart device users, a network architecture called opportunistic mobile social network (OMSN) is gaining attention. OMSNs have been used in a variety of applications, such as environmental monitoring, intelligent transportation systems, and public safety. However, routing in OMSNs is a challenging problem due to the frequent disconnection between nodes and the absence of paths from the source to the destination. It results in a complex topology and a low packet transmission success rate. Therefore, this thesis studies routing protocols in OMSNs. Specifically, a human mobility model that generates human movements is first designed. Then, a temporal social interaction-based routing protocol is developed, and the proposed human mobility model is used to validate the performance of this routing protocol. Finally, we extend our work by studying a human location prediction model and proposing a human location prediction-based routing protocol. First, human movement patterns are important for validating the performance of routing protocols. Several traces of human movements in real life have been collected. However, collecting data about human movements is costly and time-consuming. Moreover, multiple traces are demanded to test various network scenarios. As a result, a lot of synthetic models of human movement have been proposed. Nevertheless, most of the proposed models were often based on random generation, and cannot produce realistic human movements. Although there have been a few models that tried to capture the characteristics of human movement in real life, those models still cannot reflect realistic human movements due to a lack of consideration for social context among people. To address those limitations, we propose a novel human mobility model called the social relationship-aware human mobility model (SRMM), which considers social context as well as the characteristics of human movement (e.g., flights, inter-contact times, and pause times following the truncated power-law distribution). SRMM partitions people into social groups by exploiting information from a social graph. Then, the movements of people are determined by considering the distances and social relationships. In the second part of this work, we design a routing algorithm called the temporal social interactions-based routing protocol (TSIRP) for solving challenges in OMSNs. First, we focus on the temporal context of social interactions. Specifically, at a certain time of the day, a person usually interacts with specific people (e.g., workers usually meet co-workers during working hours; students usually meet their classmates during class). Based on temporal social interactions between nodes, potential forwarding metrics are proposed and calculated for each time of the day to make forwarding decisions. Second, we propose a new scheme to control the message spreading rate, which allows achieving a balance between delivery latency and overhead ratio. In addition, an analytical model is also designed using an absorbing Markov chain to estimate the performance of TSIRP. SRMM is used to generate human movements for evaluating the performance of TSIRP. In the third part of this work, a specific scenario for transmitting data in urban sensor networks is studied and a human location prediction-based routing protocol (HLPRP) is proposed for this network model. Specifically, a human location prediction (HLP) model is designed to estimate the location of mobile nodes. The proposed HLP model is based on a recurrent neural network with long short-term memory cells. The movement history of each person is used in the HLP model to predict their future locations. Then, using predicted location information from the HLP model, packet delivery predictability is obtained. Packet delivery predictability represents the possibility that a node will deliver a packet to its destination and is used to select optimal relay nodes to maximize the packet delivery ratio, minimize the packet delivery cost, and reduce delivery latency. In addition, the proposed routing protocol also considers social strength for relay selection. Simulations on a synthetic map and a real road map are considered to evaluate SRMM. The results of SRMM are compared with a real trace and other synthetic mobility models. The obtained results indicate that SRMM is consistently better at reflecting both human movement characteristics and social relationships. Then, using the generated human movements from SRMM, we conduct experiments with different parameters to validate TSIRP. Simulations on real traces (e.g., UB datasets) are used to evaluate HLPRP. The evaluated results show that TSIRP and HLPRP can achieve better performance than existing routing protocols.