APARICIO-PARDO , Ramon

5G services and 4K will stress even more the future access/aggregation networks, where video contents have already become the main traffic contributor. The deployment in the convergent access of local micro data-centers (DCs) nodes is one promising approach to successfully manage this challenge. These nodes will be responsible for switching...

International audience

Video traffic is a key-challenge for fixed and mobile operators facing variable and massive load and variety of Over- The-Top (OTT) videos. Energy consumption is also a heavy Opex component, where the Fixed-Mobile Convergence is a promising solution, built on on economical optic fibers and LTE base- band operations consolidation. By combining...

In this letter, we describe research activities on the global management of a live video streaming service running in the cloud. We focus on the coordination of these technologies and we show that a management policy that takes into account all the inter-dependencies among technologies can bring significant advantages. In particular, we address...

Quantum networks make use of the quantum entanglement as building block. When two qubits are entangled, their state changes exhibit non-classical correlations used to design new applications not possible with classical communication, such us quantum key distribution or distributed quantum computation. Unfortunately, quantum entanglement is a...

—In distributed file systems, Random-Linear-Coding (RLC) reduces scheduler complexity and download time by eliminating the coupon collector problem [1]. Similar benefits for video streaming in Distributed Video Caching and Sharing (DVCS) systems require segmentation of videos into codeblocks, over which RLC can be applied, to ensure videos'...

International audience

This paper addresses the problem of dynamic packet routing in overlay networks using a fully decentralized Multi-Agent Deep Reinforcement Learning (MA-DRL). Overlay networks are built by having a virtual topology on top of an Internet Service Provider (ISP) underlay network, where those nodes are running a fixed, single path routing policy...

The development through streaming of 360°videos is persistently hindered by how much bandwidth they require. Adapting spatially the quality of the sphere to the user's Field of View (FoV) lowers the data rate but requires to keep the playback buffer small, to predict the user's motion or to make replacements to keep the buffered qualities up to...

Designing editing cuts for cinematic Virtual Reality (VR) has been under active investigation. Recently, the connection has been made between cuts in VR and adaptive streaming logics for 360 • videos, with the introduction of rotational snap-cuts. Snap-cuts can benefit the user's experience both by improving the streamed quality in the FoV and...

The streaming transmissions of 360°videos is a major challenge for the development of Virtual Reality, and require a reliable head motion predictor to identify which region of the sphere to send in high quality and save data rate. Different head motion predictors have been proposed recently. Some of these works have similar evaluation metrics...

Proceedings of the ACM International Conference on Multimedia Systems (MMSys)

Head motion prediction is an important problem with 360 • videos, in particular to inform the streaming decisions. Various methods tackling this problem with deep neural networks have been proposed recently. In this article, we introduce a new deep architecture, named TRACK, that benefits both from the history of past positions and knowledge of...

Transport protocols that can exploit multiple paths, especially MPTCP, do not match the requirements of video streaming: high average transmission delay, too strict reliability, and frequent head-of-line phenomenons resulting in abrupt throughput drops. In this paper, we address this mismatch by introducing a cross-layer scheduler, which...

In recent years, several works have studied Multi-Agent Deep Reinforcement Learning for the Distributed Packet Routing problem, with promising results in various scenarios where network status changes dynamically, is uncertain, or is partially hidden (e.g., wireless ad hoc networks or wired multidomain networks). Unfortunately, these previous...

In this paper, we present PRISMA: Packet Routing Simulator for Multi-Agent Reinforcement Learning. To the best of our knowledge, this is the first tool specifically conceived to develop and test Reinforcement Learning (RL) algorithms for the Distributed Packet Routing (DPR) problem. In this problem, where a communication node selects the...

In this paper, we present prisma-v2, a new release of prisma, a Packet Routing Simulator for Multi-Agent Reinforcement Learning. prisma-v2 brings a new set of features. First, it allows simulating overlay network topologies, by integrating virtual links. Second, this release offers the possibility to simulate control packets, which allows to...

PRISMA (Packet Routing Simulator for Multi-Agent Reinforcement Learning) is a network simulation playground for developing and testing Multi-Agent Reinforcement Learning (MARL) solutions for dynamic packet routing (DPR). This framework is based on the OpenAI Gym toolkit and the ns-3 simulator.The OpenAI Gym is a toolkit for RL widely used in...

In general, the availability of an accurate machine learning (ML) model plays a particularly important role in the development of new networking solutions and is one of the main drivers for the development of 5G and beyond networking. Although an option is to update the model once inaccurate data is detected, such approach requires high...

International audience

Despite exciting prospects, the development of 360 • videos is persistently hindered by the difficulty to stream them. To reduce the data rate, existing streaming strategies adapt the video rate to the user's Field of View (FoV), but the difficulty of predicting the FoV and persistent lack of bandwidth are important obstacles to achieve best...

The emerging 5G induces a great diversity of use cases, a multiplication of the number of connections, an increase in throughput as well as stronger constraints in terms of quality of service such as low latency and isolation of requests. To support these new constraints, Network Function Virtualization (NFV) and Software Defined Network (SDN)...

This report provides the details about (i) the QoE-QoS model and (ii) the DASH representations used in the simulations performed in [2]. The report details the calculations required to find a concave Quality of Experience (QoE) curve from Quality of Service (QoS) metrics by using the reference model of ITU-T Rec. P.1202.2 [3], [6], the...

International audience