Search for: All records

We investigate a novel communications system that integrates scalable multi-layer 360-degree video tiling, viewport-adaptive rate-distortion optimal resource allocation, and VR-centric edge computing and caching, to enable future high-quality untethered VR streaming. Our system comprises a collection of 5G small cells that can pool their communication, computing, and storage resources to collectively deliver scalable 360-degree video content to mobile VR clients at much higher quality. Our major contributions are rigorous design of multi-layer 360-degree tiling and related models of statistical user navigation, and analysis and optimization of edge-based multi-user VR streaming that integrates viewport adaptation and server cooperation. We also explore the possibility of network coded data operation and its implications for the analysis, optimization, and system performance we pursue here. We demonstrate considerable gains in delivered immersion fidelity, featuring much higher 360-degree viewport peak signal to noise ratio (PSNR) and VR video frame rates and spatial resolutions. 

We consider an LTE downlink scheduling system where a base station allocates resource blocks (RBs) to users running delay-sensitive applications. We aim to find a scheduling policy that minimizes the queuing delay experienced by the users. We formulate this problem as a Markov Decision Process (MDP) that integrates the channel quality indicator (CQI) of each user in each RB, and queue status of each user. To solve this complex problem involving high dimensional state and action spaces, we propose a Deep Reinforcement Learning based scheduling framework that utilizes the Deep Deterministic Policy Gradient (DDPG) algorithm to minimize the queuing delay experienced by the users. Our extensive experiments demonstrate that our approach outperforms state-of-the-art benchmarks in terms of average throughput, queuing delay, and fairness, achieving up to 55% lower queuing delay than the best benchmark. 

Internet of Things (IoT) sensors often operate in unknown dynamic environments comprising latency-sensitive data sources, dynamic processing loads, and communication channels of unknown statistics. Such settings represent a natural application domain of reinforcement learning (RL), which enables computing and learning decision policies online, with no a priori knowledge. In our previous work, we introduced a post-decision state (PDS) based RL framework, which considerably accelerates the rate of learning an optimal decision policy. The present paper formulates an efficient hardware architecture for the action evaluation step, which is the most computationally-intensive step in the PDS based learning framework. By leveraging the unique characteristics of PDS learning, we optimize its state value expectation and known cost computational blocks, to speed-up the overall computation. Our experiments show that the optimized circuit is 49 times faster than its software implementation counterpart, and six times faster than a Q-learning hardware accelerator. 

Recent advances in multi-rotor vehicle control and miniaturization of hardware, sensing, and battery technologies have enabled cheap, practical design of micro air vehicles for civilian and hobby applications. In parallel, several applications are being envisioned that bring together a swarm of multiple networked micro air vehicles to accomplish large tasks in coordination. However, it is still very challenging to deploy multiple micro air vehicles concurrently. To address this challenge, we have developed an open software/hardware platform called the University at Buffalo’s Airborne Networking and Communications Testbed (UB-ANC), and an associated emulation framework called the UB-ANC Emulator. In this paper, we present the UB-ANC Emulator, which combines multi-micro air vehicle planning and control with high-fidelity network simulation, enables practitioners to design micro air vehicle swarm applications in software and provides seamless transition to deployment on actual hardware. We demonstrate the UB-ANC Emulator’s accuracy against experimental data collected in two mission scenarios: a simple mission with three networked micro air vehicles and a sophisticated coverage path planning mission with a single micro air vehicle. To accurately reflect the performance of a micro air vehicle swarm where communication links are subject to interference and packet losses, and protocols at the data link, network, and transport layers affect network throughput, latency, and reliability, we integrate the open-source discrete-event network simulator ns-3 into the UB-ANC Emulator. We demonstrate through node-to-node and end-to-end measurements how the UB-ANC Emulator can be used to simulate multiple networked micro air vehicles with accurate modeling of mobility, control, wireless channel characteristics, and network protocols defined in ns-3.