Vehicular ad hoc networks (VANETs) have been widely used in intelligent transportation systems (ITSs) for purposes such as the control of unmanned aerial vehicles (UAVs) and trajectory prediction. However, an efficient and reliable data routing decision scheme is critical for VANETs due to the feature of self-organizing wireless multi-hop communication. Compared with wireless networks, which are unstable and have limited bandwidth, wired networks normally provide longer transmission distances, higher network speeds and greater reliability. To address this problem, this paper proposes a reliable VANET routing decision scheme based on the Manhattan mobility model, which considers the integration of roadside units (RSUs) into wireless and wired modes for data transmission and routing optimization. First, the problems of frequently moving vehicles and network connectivity are analyzed based on road networks and the motion information of vehicle nodes. Second, an improved greedy algorithm for vehicle wireless communication is used for network optimization, and a wired RSU network is also applied. In addition, routing decision analysis is carried out in accordance with the probabilistic model for various transmission ranges by checking the connectivity among vehicles and RSUs. Finally, comprehensive experiments show that our proposed method can support real-time planning and improve network transmission performance compared with other baseline protocol approaches in terms of several metrics, including package delivery ratio, time delay and wireless hops.

V2VR: Reliable Hybrid-Network-Oriented V2V Data Transmission and Routing Considering RSUs and Connectivity Probability

With the emergence of smartphones and location-based services, user mobility prediction has become a critical enabler for a wide range of applications, like location-based advertising, early warning systems, and citywide traffic planning. A number of techniques have been proposed to either conduct spatio-temporal mobility prediction or forecast the next-place. However, both produce diverse prediction performance for different users and display poor performance for some users. This paper focuses on investigating the effect of living habits on the models of spatio-temporal prediction and next-place prediction, and selects one from these two models for an individual to achieve effective mobility prediction at users’ points of interest. Based on the hidden Markov model (HMM), a spatio-temporal predictor and a next-place predictor are proposed. Living habits are analyzed in terms of entropy, upon which users are clustered into distinct groups. With large-scale factual mobile data captured from a big city, we compare the proposed HMM-based predictors with existing state-of-the-art predictors and apply them to different user groups. The results demonstrate the robust performance of the two proposed mobility predictors, which outperform the state of the art for various user groups.

Big Data Driven Hidden Markov Model Based Individual Mobility Prediction at Points of Interest

Human mobility prediction is of great importance in a wide range of modern applications in different fields such as personalized recommendation systems, the fifth-generation (5G) mobile communication systems, and so on. Generally, the prediction goal varies from different application scenarios. For the applications of 5G network including resource allocation and mobility management, it is essential to predict the positions of mobile users in the near future from dozens of seconds to a few minutes so as to make preparation in advance, which is actually a trajectory prediction problem. In this paper, with the particular focus on multi-user multi-step trajectory prediction, we first design a basic deep learning-based prediction framework, where the long short-term memory (LSTM) network is directly applied as the most critical component to learn user-specific mobility pattern from the user's historical trajectories and predict his/her movement trends in the future. Motivated by the related findings after testifying and analyzing this basic framework on a model-based dataset, we extend it to a region-oriented prediction scheme and propose a multi-user multi-step trajectory prediction framework by further incorporating the sequence-to-sequence (Seq2Seq) learning. The experimental results on a realistic dataset demonstrate that the proposed framework has significant improvements on generalization ability and reduces error-accumulation effect for multi-step prediction.

/pdf/exploring-trajectory-prediction-through-machine-learning-4iayxj1fb3.pdf

Exploring Trajectory Prediction Through Machine Learning Methods

Geographic routing in the presence of location errors

The high-level contribution of this paper is a simulation based analysis of the network connectivity, hop count and lifetime of the routes determined for mobile ad hoc networks (MANETs) using the Gauss-Markov mobility model. The Random Waypoint mobility model is used as a benchmark in the simulation studies. Two kinds of routes are determined: routes with the longest lifetime (stable paths) and routes with the minimum hop count. Extensive simulations have been conducted for different network density, node mobility values and different values of the degree of randomness parameter for the Gauss-Markov model. In low-density network scenarios, we observe that the network connectivity under the Gauss-Markov model is significantly lower than that obtained under the Random Waypoint model. In moderate and high density network scenarios, the network connectivity obtained under the two mobility models is almost equal. The minimum hop paths determined under the Gauss-Markov model have a larger number of hops than those computed under the Random Waypoint model. The lifetime of stable paths determined under the Gauss-Markov model is smaller than those determined under the Random Waypoint model. Low-density networks using the Gauss-Markov mobility model attain larger connectivity for intermediate values of the degree of randomness parameter, while the connectivity of moderate and high-density networks is not significantly dependent on the degree of randomness parameter. The minimum hop count of the paths is not much affected by different values of the degree of randomness parameter, while maximum lifetime stable paths are obtained for larger intermediate values of the degree of randomness parameter, but not for unity.

Impact of the Gauss-Markov Mobility Model on Network Connectivity, Lifetime and Hop Count of Routes for Mobile Ad hoc Networks

A mobile ad hoc network (MANET) is a network consisting of a set of wireless mobile nodes that communicate with each other without centralized control or established infrastructure. The mobility model represents the moving behavior of each mobile node (MN) in the MANET that should be realistic. It is a crucial part in the performance evaluation of MANET. Random Waypoint mobility model is the only mobility model that has been widely used in the simulation study of MANET despite some unrealistic movement behaviors such as sudden stop and sharp turn. Whilst Gauss-Markov mobility model has been proved that it can solve both of these problems. This paper presents a comparative simulation study of Random Waypoint and Gauss-Markov mobility models on the performance study of MANET that uses Ad-hoc On-Demand Distance Vector (AODV) as the routing protocol. The results show that both mobility models are not different in case each MN is moving at human running speed. Therefore, it is suggested to use Random Waypoint mobility model because of its less computational overhead comparing to Gauss-Markov mobility model. When the speed of MNs is as high as fast automobiles, the performance result using Random Waypoint mobility model is significant different from Gauss-Markov mobility model. Therefore, Gauss-Markov mobility model should be used instead. Moreover, different levels of randomness setting have no effect on the accuracy of throughput and end-to-end delay.

Jinthana Ariyakhajorn

Papers

A Comparative Study of Random Waypoint and Gauss-Markov Mobility Models in the Performance Evaluation of MANET