Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Edge-aided V2X collision avoidance with platoons: Towards a hybrid evaluation toolsetPublication . Pereira, João; Kurunathan, Harrison; Filho, Ênio; Santos, Pedro M.Infrastructure-brokered collision avoidance is an Intelligent Transportation Systems (ITS) application built on top of Vehicle-to-Everything (V2X) links. An edge-hosted ITS service receives information from road-side sensors (or CAM messages in V2X-enabled vehicles) and detects impending collisions where vehicles cannot sense or contact each other directly. If so happens, it issues a warning message through network-to-vehicle links. Another relevant ITS application is platooning, through which vehicles following each other closely can benefit of improved fuel economy, and that can be further enhanced through communication. In case of emergency braking in platoons, the response times of network and edge-hosted services must be minimal to ensure no collision amongst the platoon or any other road user. In this paper we present the implementation of a simulation framework tailored (but not limited) to evaluate the presented use-case. This complex and multi-layered use-case can be handled by a dedicated ITS service that leverages the sensing, radio and computing resources available at infrastructure and vehicles, and requires a realistic evaluation framework prior to deployment. Such framework is mostly based on simulation, albeit, to the extent possible, actual devices or services should be used; the present work is a step towards that hybrid setup.
- Energy savings and emissions reduction of BEVs at an isolated complex intersectionPublication . Reddy, Radha; Almeida, Luis; Santos, Pedro Miguel; Kurunathan, Harrison; Tovar, EduardoImproving urban dwellers quality of life requires mitigating traffic congestion, minimizing waiting delays, and reducing fuel wastage and associated toxic air pollutants. Battery-electric vehicles (BEVs) are envisioned as the best option, thanks to zero exhaust emissions and regenerative braking. BEVs can be human-driven or autonomous and will co-exist with internal combustion engine vehicles (ICEVs) for years. BEVs can help at complex intersections where traffic is saturated. However, their benefits can be reduced by poor intersection management (IM) strategies that coordinate mixed traffic configurations inefficiently. This paper studies energy savings and emissions reduction using BEVs mixed with human-driven ICEVs under eight relevant IM approaches. It shows that adding BEVs has impacts on throughput, energy consumption, waiting delays, and tail-pipe emissions that depend on the specific IM approach used. Thus, this study provides the information needed to support an optimal choice of IM approaches considering the emerging trend towards electrical mobility.
- Data-driven Deep Reinforcement Learning for Online Flight Resource Allocation in UAVaided Wireless Powered Sensor NetworksPublication . Li, Kai; Ni, Wei; Kurunathan, Harrison; Dressler, FalkoIn wireless powered sensor networks (WPSN), data of ground sensors can be collected or relayed by an unmanned aerial vehicle (UAV) while the battery of the ground sensor can be charged via wireless power transfer. A key challenge of resource allocation in UAV-aided WPSN is to prevent battery drainage and buffer overflow of the ground sensors in the presence of highly dynamic lossy airborne channels which can result in packet reception errors. Moreover, state and action spaces of the resource allocation problem are large, which is hardly explored online. To address the challenges, a new data-driven deep reinforcement learning framework, DDRL-RA, is proposed to train flight resource allocation online so that the data packet loss is minimized. Due to time-varying airborne channels, DDRL-RA firstly leverages long short-term memory (LSTM) with pre-collected offline datasets for channel randomness predictions. Then, Deep Deterministic Policy Gradient (DDPG) is studied to control the flight trajectory of the UAV, and schedule the ground sensor to transmit data and harvest energy. To evaluate the performance of DDRL-RA, a UAV-ground sensor testbed is built, where real-world datasets of channel gains are collected. DDRL-RA is implemented on Tensorflow, and numerical results show that DDRL-RA achieves 19\% lower packet loss than other learning-based frameworks.
- Joint spectrum and antenna selection diversity for V2V links with ground reflectionsPublication . Robles, Ramiro; Gutiérrez Gaitán, Miguel; Javanmardi, Gowhar; Kurunathan, HarrisonThis paper addresses the study of a fading-rejection algorithm based on joint spectrum and antenna selection in a vehicle-to-vehicle (V2V) multiple antenna system. The central objective of this selective scheme is to provide resilience against the destructive effects of the superposition of line-of-sight (LOS) and ground-reflected signals. The paper also provides an extension to channels that combine such deterministic superposition of multiple paths and reflections with an uncorrelated double scattering component, which shows how the algorithm is also beneficial under more general channel modelling assumptions. A multiple-ray performance model is used to describe the deterministic signal interactions between multiple antennas across contiguous vehicles. The antenna selection component is shown to reject deterministic fading, particularly at short values of the inter-vehicular distance. By contrast, when the spectrum bands are correctly chosen, the spectrum selection component can exhibit gains for a wider range of inter-vehicular distances than its antenna selection counterpart. This indicates that both components of the proposed solution are, in some cases, complementary, and therefore, they should be considered together in V2V multiple antenna design. Derivation of the statistics of the selective scheme considering an additional double scattering stochastic channel component is here proposed. Simulation results from all expressions show important gains for a given range of inter-vehicular distances.