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 mismatch by introducing a cross-layer scheduler, which leverages information from both application transport layers to re-order data prioritize most significant parts video. Our objective is maximize amount received...

More and more users are watching online videos produced by non-professional sources (e.g., gamers, teachers of courses, witnesses public events) using an increasingly diverse set devices to access the smartphones, tablets, HDTV). Live streaming service providers can combine adaptive technologies cloud computing satisfy this demand. In paper, we study problem preparing live video streams for delivery infrastructure, e.g., how many representations use corresponding parameters (resolution...

Adaptive streaming addresses the increasing and heterogenous demand of multimedia content over Internet by offering several encoded versions for each video sequence. Each version (or representation) has a different resolution bit rate, aimed at specific set users, like TV or mobile phone clients. While most existing works on adaptive deal with effective playout-control strategies client side, we take in this paper providers' perspective propose solutions to improve user satisfaction...

We consider predicting the user's head motion in 360 ° videos, with 2 modalities only: past positions and video content (not knowing other users' traces). make two main contributions. First, we re-examine existing deep-learning approaches for this problem identify hidden flaws from a thorough root-cause analysis. Second, results of analysis, design new proposal establishing state-of-the-art performance. re-assessing methods that use both modalities, obtain surprising result they all perform...

Adaptive streaming addresses the increasing and heterogenous demand of multimedia content over Internet by offering several streams for each video. Each stream has a different resolution bit rate, aimed at specific set users, e.g., TV, mobile phone. While most existing works on adaptive deal with optimal playout-control strategies client side, in this paper we concentrate providers' showing how to improve user satisfaction optimizing encoding parameters. We formulate an integer linear...

Transparent optical networks are the enabling infrastructure for converged multi-granular in future Internet. The cross-layer planning of these considers physical impairments network layer design. This is complicated by diversity modulation formats, transmission rates, amplification and compensation equipments, or deployed fiber links. Thereby, concept quality (QoT) attempts to embrace effects impairments, introduce them a multi-criterium optimization process. paper contributes this field...

In translucent optical networks, the physical layer impairments degrading signal are considered in network planning. this paper, we investigate offline problem of routing and wavelength assignment (RWA) regenerator placement (RP) minimizing lightpath blocking equipment cost. We address two variants problem, which correspond to different types quality transmission (QoT) estimators, called linear nonlinear. a nonlinear QoT, like crosstalk or cross-phase modulation, account for interferences...

Streaming Virtual Reality (VR), even under the mere form of 360° videos, is much more complex than for regular videos because to lower required rates, transmission decisions must take user's head position into account. The way user exploits her/his freedom therefore crucial network load. In turn, moves depends on video content itself. VR however a whole new medium, which film-making language does not exist yet, its "grammar" only being invented. We present strongly inter-disciplinary...

While Virtual Reality (VR) represents a revolution in the user experience, current VR systems are flawed on different aspects. The difficulty to focus naturally headsets incurs visual discomfort and cognitive overload, while high-end require tethered powerful hardware for scene synthesis. One of major solutions envisioned address these problems is foveated rendering. We consider problem streaming stored 360° videos headset equipped with eye-tracking rendering capabilities. Our end research...

This paper investigates offline virtual topology design in transparent optical networks under a multihour traffic demand. The main problem variant addressed here designs reconfigurable that evolves over time to more efficiently utilize network resources (the MH-VTD-R problem). case of designing static non-reconfigurable can accommodate the time-varying MH-VTD-NR problem) is also considered. objectives are minimize: 1) number transceivers, which make up for cost; and 2) frequency...

The streaming transmissions of 360° videos is a major challenge for the development Virtual Reality, and require reliable head motion predictor to identify which region sphere send in high quality save data rate. Different predictors have been proposed recently. Some these works similar evaluation metrics or even share same dataset, however, none them compare with each other. In this article we introduce an open software that enables evaluate heterogeneous prediction methods on various...

The surge of video traffic is a challenge for service providers that need to maximize Quality Experience (QoE) while optimizing the cost their infrastructure. In this paper, we address problem routing multiple HTTP-based Adaptive Streaming (HAS) sessions QoE. We first design QoS-QoE model incorporating different QoE metrics which able learn online network variations and predict impact on representative classes adaptation logic, motion client resolution. Different are then combined into score...

With the advent and growing usage of Machine Learning as a Service (MLaaS), cloud network systems are now offering possibility to deploy ML tasks on heterogeneous clusters.Then, operators have schedule these tasks, determining both when which devices execute them.In parallel, several solutions, such neural compression, were proposed build small models can run limited hardware.These solutions allow choosing model size at inference time for any targeted processing without having re-train...

Advancements in cloud computing have boosted Machine Learning as a Service (MLaaS), highlighting the challenge of scheduling tasks under latency and deadline constraints. Neural network compression offers energy consumption reduction data centers, aligning with efforts to minimize computing's carbon footprint, despite some accuracy loss.

This paper investigates offline planning and scheduling in transparent optical networks for a given periodic traffic demand. The main objective is to minimize the number of transceivers needed which make up network cost. We call this problem “Scheduled Virtual Topology Design” consi

Optical network operators face the challenge of upgrading WDM capacity to adapt estimated traffic growths. Network upgrades are commonly carried out in scheduled intervals (i.e. every six months), using forecasts. The uncertainty forecasts is a major issue process. If it not handled appropriately, exposed service degradation caused by an unexpected progression. Despite its relevance, effects factor that has been well studied literature. In this paper, we apply robust optimization paradigm...

To deal with the explosion of mobile traffic, network operators deploy heterogeneous networks (HetNet), a combination macro and pico eNodeBs. In this paper, we propose an optimization framework for study optimal performances HetNet on uplink. We focus video traffic because technologies like WebRTC allow users to upload live streams in cellular networks. Optimization model uplink is much more complex than downlink, which previous works exist. Our integrates both management (radio resource...

This paper addresses offline virtual topology design in transparent optical networks under given periodic traffic. We call this planning problem ldquoScheduled Virtual Topology Designrdquo. Two variants are considered: for a network based on non-reconfigurable equipment and reconfigurable equipment. MILP (Mixed Integer Linear Program) formulations proposed, one each alternative. The number of transceivers the is selected cost figure to minimize. Tests performed evaluate benefits using...