Search

Intelligent Transportation Systems (ITS) are gaining substantial attention owing to the great benefits offered to the vehicle users. In ITS paradigm, content data is normally obtained from road side units (RSUs). However, in some scenarios, terrestrial networks are partially/temporarily out-of-service. Unmanned Aerial Vehicle (UAV) or drone cells are expected to be one of the pillars of future networks to assist the vehicular networks in such scenarios. To this end, we propose a collaborative framework between UAVs and in-service RSUs to partial service vehicles. Our objective is to maximize the amount of downloaded contents to vehicles while considering the dynamic nature of the network. Motivated by the success of machine learning (ML) techniques particularly deep Reinforcement learning in solving complex problems, we formulate the scheduling and content management policy problem as a Markov Decision Process (MDP) where the system state space considers the vehicular network dynamics. Proximal Policy Optimization (PPO) is utilized to govern the content decisions in the vehicular network. The simulation-based results show that during the mission time, the proposed algorithm learns the vehicular environment and its dynamics to handle the complex action space.

The advent of autonomous vehicles demands powerful processing capabilities of on-board units to handle the dramatic increase of sensor data used to make safe self-driving decisions. Those com- putational resources, being constantly available on the highways, represent valuable assets that can be leveraged to serve as fog computing facility to computational tasks generated from other vehicles or even from different networks. In this paper, we propose a fog-enabled system scheme that can be deployed on a road side unit (RSU) to schedule and offload requested computational tasks over the available vehicles' on-board units (OBUs). The goal is to maximize the weighted sum of the admitted tasks. We model the problem as a Mixed Integer Linear Programming (MILP), and due to NP-hardness, we propose a Dantzig-Wolfe decomposition method to provide a scalable solution. The experiment shows that our ap- proach has a sufficient effectiveness in terms of both computational complexity and tasks acceptance rate.

Real-time interactive application workloads (e.g. web search, social networking, etc.) are composed of a remarkably large number of mini request partitions that require stringent delayminimal aggregation of responses and their delivery back to the user. This paper presents a novel Time-Deadline-AwarepFabric (TDA-pFabric) being a data transport design whose objectives are two-fold: i) reducing the mean Flow Completion Time (FCT), the deadline mismatch and blocking probabilities as well as ii) improving the mean application throughput. A stochastic queueing model is proposed herein to capture TDA-pFabric's dynamics and evaluate its performance. The model is validated through extensive simulations whose results also show that TDA-pFabric exhibits significant improvements over existing designs in terms of the above-listed quality-of-service metrics. Scopus

We investigate the problem of scheduling and flexible spectrum access in multi-hop networks with software defined radios. We present a primal-dual decomposition to provide an exact solution for this complex optimization problem. We show that obtaining the optimal solution is computationally not feasible. Thus, we first relax the SINR constraint and use a simplified graph-based interference model. Second, we use a simulated annealing (SA) approach for solving the dual sub-problem. Our SA approach is then augmented with a feasibility check so that only SINR-feasible schedules are passed back to the primal.

This paper describes a new vulnerability for the IEEE 802.11 protocol and studies its impact on degrading the performance of ad hoc networks. A host that exploits this new simple, but practical, vulnerability could cause devastating effects on the proper operation of the network protocols and hence severe performance degradation. Here, a misbehaving node fully cooperates by forwarding packets for other nodes and completely adheres to the proper selection of backoff intervals; however, it maliciously forces the forwarding operation to fail in order to either disrupt the route discovery process or to cause damage to existing flows routed though that node. As a result, the medium around the misbehaving node will be less congested and hence the node will obtain an increased unfair access to the channel. We use network simulations to show that such malicious misbehaviors have devastating effect on demoting the network performance and disrupting the protocol functioning. Hence, necessary extensions for existing detection systems are required to mitigate the effects of these new vulnerabilities.