arXiv subjects

Cristina Perfecto

Publications and source records attributed to Cristina Perfecto.

12 recordsLinked to original sources

arXiv2026

On-Device Deep Reinforcement Learning for Decentralized Task Offloading Performance trade-offs in the training process

Allowing less capable devices to offload computational tasks to more powerful devices or servers enables the development of new applications that may not run correctly on the device itself. Deciding where and why to run each of those applications is a complex task. Therefore, different approaches have been adopted to make offloading decisions. In this work, we propose a decentralized Deep Reinforcement Learning (DRL) agent to address the selection of computing locations. Unlike most existing work, we analyze it in a real testbed composed of various edge devices running the agent to determine where to execute each task. These devices are connected to a Multi-Access Edge Computing (MEC) server and a Cloud server through 5G communications. We evaluate not only the agent's performance in meeting task requirements but also the implications of running this type of agent locally, assessing the trade-offs of training locally versus remotely in terms of latency and energy consumption.

cs.ET↗

arXiv2021

Vehicular Cooperative Perception Through Action Branching and Federated Reinforcement Learning

Cooperative perception plays a vital role in extending a vehicle's sensing range beyond its line-of-sight. However, exchanging raw sensory data under limited communication resources is infeasible. Towards enabling an efficient cooperative perception, vehicles need to address the following fundamental question: What sensory data needs to be shared?, at which resolution?, and with which vehicles? To answer this question, in this paper, a novel framework is proposed to allow reinforcement learning (RL)-based vehicular association, resource block (RB) allocation, and content selection of cooperative perception messages (CPMs) by utilizing a quadtree-based point cloud compression mechanism. Furthermore, a federated RL approach is introduced in order to speed up the training process across vehicles. Simulation results show the ability of the RL agents to efficiently learn the vehicles' association, RB allocation, and message content selection while maximizing vehicles' satisfaction in terms of the received sensory information. The results also show that federated RL improves the training process, where better policies can be achieved within the same amount of time compared to the non-federated approach.

cs.LG↗

arXiv2020

Cross Layer Optimization and Distributed Reinforcement Learning for Wireless 360{\deg} Video Streaming

Wirelessly streaming high quality 360 degree videos is still a challenging problem. When there are many users watching different 360 degree videos and competing for the computing and communication resources, the streaming algorithm at hand should maximize the average quality of experience (QoE) while guaranteeing a minimum rate for each user. In this paper, we propose a cross layer optimization approach that maximizes the available rate to each user and efficiently uses it to maximize users' QoE. Particularly, we consider a tile based 360 degree video streaming, and we optimize a QoE metric that balances the tradeoff between maximizing each user's QoE and ensuring fairness among users. We show that the problem can be decoupled into two interrelated subproblems: (i) a physical layer subproblem whose objective is to find the download rate for each user, and (ii) an application layer subproblem whose objective is to use that rate to find a quality decision per tile such that the user's QoE is maximized. We prove that the physical layer subproblem can be solved optimally with low complexity and an actor-critic deep reinforcement learning (DRL) is proposed to leverage the parallel training of multiple independent agents and solve the application layer subproblem. Extensive experiments reveal the robustness of our scheme and demonstrate its significant performance improvement compared to several baseline algorithms.

cs.LG↗

arXiv2020

Taming the latency in multi-user VR 360$^\circ$: A QoE-aware deep learning-aided multicast framework

Immersive virtual reality (VR) applications require ultra-high data rate and low-latency for smooth operation. Hence in this paper, aiming to improve VR experience in multi-user VR wireless video streaming, a deep-learning aided scheme for maximizing the quality of the delivered video chunks with low-latency is proposed. Therein the correlations in the predicted field of view (FoV) and locations of viewers watching 360$^\circ$ HD VR videos are capitalized on to realize a proactive FoV-centric millimeter wave (mmWave) physical-layer multicast transmission. The problem is cast as a frame quality maximization problem subject to tight latency constraints and network stability. The problem is then decoupled into an HD frame request admission and scheduling subproblems and a matching theory game is formulated to solve the scheduling subproblem by associating requests from clusters of users to mmWave small cell base stations (SBSs) for their unicast/multicast transmission. Furthermore, for realistic modeling and simulation purposes, a real VR head-tracking dataset and a deep recurrent neural network (DRNN) based on gated recurrent units (GRUs) are leveraged. Extensive simulation results show how the content-reuse for clusters of users with highly overlapping FoVs brought in by multicasting reduces the VR frame delay in 12\%. This reduction is further boosted by proactiveness that cuts by half the average delays of both reactive unicast and multicast baselines while preserving HD delivery rates above 98\%. Finally, enforcing tight latency bounds shortens the delay-tail as evinced by 13\% lower delays in the 99th percentile.

cs.IT↗

arXiv2019

Wireless Edge Computing with Latency and Reliability Guarantees

Edge computing is an emerging concept based on distributing computing, storage, and control services closer to end network nodes. Edge computing lies at the heart of the fifth generation (5G) wireless systems and beyond. While current state-of-the-art networks communicate, compute, and process data in a centralized manner (at the cloud), for latency and compute-centric applications, both radio access and computational resources must be brought closer to the edge, harnessing the availability of computing and storage-enabled small cell base stations in proximity to the end devices. Furthermore, the network infrastructure must enable a distributed edge decision-making service that learns to adapt to the network dynamics with minimal latency and optimize network deployment and operation accordingly. This article will provide a fresh look to the concept of edge computing by first discussing the applications that the network edge must provide, with a special emphasis on the ensuing challenges in enabling ultra-reliable and low-latency edge computing services for mission-critical applications such as virtual reality (VR), vehicle-to-everything (V2X), edge artificial intelligence (AI), and so forth. Furthermore, several case studies where the edge is key are explored followed by insights and prospect for future work.

cs.NI↗

arXiv2019

Mobile XR over 5G: A way forward with mmWaves and Edge

This e-letter summarizes our most recent work and contributed approaches to increase the capacity, cut down on the latency and provide higher reliability in several extended reality (XR) scenarios. To that end, several technologies from emerging 5G communications systems are weaved together towards enabling a fully immersive XR experience.

eess.SP↗

arXiv2018

Edge Computing Meets Millimeter-wave Enabled VR: Paving the Way to Cutting the Cord

In this paper, a novel proactive computing and mmWave communication for ultra-reliable and low latency wireless virtual reality (VR is proposed. By leveraging information about users' poses, proactive computing and caching are used to pre-compute and store users' HD video frames to minimize the computing latency. Furthermore, multi-connectivity is exploited to ensure reliable mmWave links to deliver users' requested HD frames. The performance of the proposed approach is validated on a VR network serving an interactive gaming arcade, where dynamic and real-time rendering of HD video frames is needed and impulse actions of different players impact the content to be shown. Simulation results show significant gains of up to $30\%$ reduction in end-to-end delay and $50\%$ in the $90^{\textrm{th}}$ percentile communication delay.

cs.IT↗

arXiv2018

Towards Low-Latency and Ultra-Reliable Virtual Reality

Virtual Reality (VR) is expected to be one of the killer-applications in 5G networks. However, many technical bottlenecks and challenges need to be overcome to facilitate its wide adoption. In particular, VR requirements in terms of high-throughput, low-latency and reliable communication call for innovative solutions and fundamental research cutting across several disciplines. In view of this, this article discusses the challenges and enablers for ultra-reliable and low-latency VR. Furthermore, in an interactive VR gaming arcade case study, we show that a smart network design that leverages the use of mmWave communication, edge computing and proactive caching can achieve the future vision of VR over wireless.

cs.IT↗

arXiv2017

Millimeter Wave V2V Communications: Distributed Association and Beam Alignment

Recently millimeter-wave bands have been postulated as a means to accommodate the foreseen extreme bandwidth demands in vehicular communications, which result from the dissemination of sensory data to nearby vehicles for enhanced environmental awareness and improved safety level. However, the literature is particularly scarce in regards to principled resource allocation schemes that deal with the challenging radio conditions posed by the high mobility of vehicular scenarios. In this work we propose a novel framework that blends together Matching Theory and Swarm Intelligence to dynamically and efficiently pair vehicles and optimize both transmission and reception beamwidths. This is done by jointly considering Channel State Information (CSI) and Queue State Information (QSI) when establishing vehicle-to-vehicle (V2V) links. To validate the proposed framework, simulation results are presented and discussed where the throughput performance as well as the latency/reliability trade-offs of the proposed approach are assessed and compared to several baseline approaches recently proposed in the literature. The results obtained in our study show performance gains in terms of reliability and delay up to 25% for ultra-dense vehicular scenarios and on average 50% more paired vehicles that some of the baselines. These results shed light on the operational limits and practical feasibility of mmWave bands, as a viable radio access solution for future high-rate V2V communications.

cs.NI↗

arXiv2017

Beyond WYSIWYG: Sharing Contextual Sensing Data Through mmWave V2V Communications

In vehicular scenarios context awareness is a key enabler for road safety. However, the amount of contextual information that can be collected by a vehicle is stringently limited by the sensor technology itself (e.g., line-of-sight, coverage, weather robustness) and by the low bandwidths offered by current wireless vehicular technologies such as DSRC/802.11p. Motivated by the upsurge of research around millimeter-wave vehicle-to-anything (V2X) communications, in this work we propose a distributed vehicle-to-vehicle (V2V) association scheme that considers a quantitative measure of the potential value of the shared contextual information in the pairing process. First, we properly define the utility function of every vehicle balancing classical channel state and queuing state information (CSI/QSI) with context information i.e., sensing content resolution, timeliness and enhanced range of the sensing. Next we solve the problem via a distributed many-to-one matching game in a junction scenario with realistic vehicular mobility traces. It is shown that when receivers are able to leverage information from different sources, the average volume of collected extended sensed information under our proposed scheme is up to 71% more than that of distance and minimum delay-based matching baselines.

cs.IT↗

arXiv2016

Dynamic Proximity-aware Resource Allocation in Vehicle-to-Vehicle (V2V) Communications

In this paper, a novel proximity and load-aware resource allocation for vehicle-to-vehicle (V2V) communication is proposed. The proposed approach exploits the spatio-temporal traffic patterns, in terms of load and vehicles' physical proximity, to minimize the total network cost which captures the tradeoffs between load (i.e., service delay) and successful transmissions while satisfying vehicles's quality-of-service (QoS) requirements. To solve the optimization problem under slowly varying channel information, it is decoupled the problem into two interrelated subproblems. First, a dynamic clustering mechanism is proposed to group vehicles in zones based on their traffic patterns and proximity information. Second, a matching game is proposed to allocate resources for each V2V pair within each zone. The problem is cast as many-to-one matching game in which V2V pairs and resource blocks (RBs) rank one another in order to minimize their service delay. The proposed game is shown to belong to the class of matching games with externalities. To solve this game, a distributed algorithm is proposed using which V2V pairs and RBs interact to reach a stable matching. Simulation results for a Manhattan model shown that the proposed scheme yields a higher percentage of V2V pairs satisfying QoS as well as significant gain in terms of the signal-to-interference-plus-noise ratio (SINR) as compared to a state-of-art resource allocation baseline.

cs.NI↗

arXiv2016

Beamwidth Optimization in Millimeter Wave Small Cell Networks with Relay Nodes: A Swarm Intelligence Approach

Millimeter wave (mmWave) communications have been postulated as one of the most disruptive technologies for future 5G systems. Among mmWave bands the 60-GHz radio technology is specially suited for ultradense small cells and mobile data offloading scenarios. Many challenges remain to be addressed in mmWave communications but among them deafness, or misalignment between transmitter and receivers beams, and interference management lie among the most prominent ones. In the recent years, scenarios considering negligible interference on mmWave resource allocation have been rather common in literature. To this end, interestingly, many open issues still need to be addressed such as the applicability of noise-limited regime for mmWave. Furthermore, in mmWave the beam-steering mechanism imposes a forced silence period, in the course of which no data can be conveyed, that should not be neglected in throughput/delay calculations. This paper introduces mmWave enabled Small Cell Networks (SCNs) with relaying capabilities where as a result of a coordinated meta-heuristically optimized beamwidth/alignment-delay approach overall system throughput is optimized. Simulations have been conveyed for three transmitter densities under TDMA and naive 'all-on' scheduling producing average per node throughput increments of up to 248%. The paper further elaborates on the off-balancing impact of alignment delay and time-multiplexing strategies by illustrating how the foreseen transition that increasing the number of transmitters produces in the regime of a fixed-node size SCN in downlink operation fades out by a poor choice in the scheduling strategy.

cs.NI↗