The escalating demand for multimedia content requires efficient and scalable distribution solutions for adaptive streaming, particularly MPEG-DASH, in web environments. This paper presents SwarmLayer, a novel hybrid peer-to-peer (P2P) assisted streaming solution designed to enhance web content distribution. SwarmLayer integrates a traditional client-server model with a P2P paradigm, where active users concurrently serve as content distribution nodes by sharing acquired video segments. This approach aims to significantly reduce the load of the origin server, minimize redundant content transmission, and optimize network bandwidth utilization. Implemented as a transparent and non-intrusive intermediate layer between the media player and the content distribution system, SwarmLayer requires no modifications to existing application logic or infrastructure. Its design leverages standard web technologies, including WebRTC for peer connectivity, Service Workers for request interception, and Protocol Buffers for efficient data serialization, along with the MPEG-DASH standard. Experimental evaluations demonstrate substantial server offload, achieving up to a 96% reduction in server traffic, while maintaining seamless playback fluidity across diverse network conditions, including geographically distributed nodes and NAT environments.

This work addresses the integration of real-time transmission systems, including IP cameras and production systems (like OBS or vMix), that use protocols such as RTSP (Real Time Streaming Protocol) or SRT (Secure Reliable Transport), with content distribution technology based on LL-DASH (Low Latency DASH -Dynamic Adaptive Streaming over HTTP-), taking advantage of the fact that DASH offers significant well-known advantages for content distribution over the Internet and via CDNs (Content Delivery Networks). Considering the limitations of the LL-DASH standard regarding the adaptation to network conditions, this paper proposes a new solution called Server-Side Representation Switching (SSRS). SSRS uses an approach based on the server measuring the delay in the requests made by clients, whose variation may be due to a decrease in bandwidth, as occurs in Wi-Fi networks with a high number of clients. To evaluate the effectiveness of the proposed solution, a testbed has been developed that allows the performance evaluation of both the LL-DASH system and the solution based on server-side decision-making. In addition, the developed solution has been compared with known algorithms (L2A and LoL+) integrated into the Dash.js player. The results show that the Server-Side Representation Switching solution offers a good trade-off between the transmitted quality and the final delay measured at the client, compared to the other algorithms evaluated. Moreover, it holds the advantage of being straightforward to implement and does not require any modifications to the players used. • Networks • Network performance evaluation • Network performance analysis

Dynamic Streaming over HTTP (DASH) is the main standard used in online video streaming services, given that more than 1.2 billion pay subscribers around the world use this standard. This fact entails billions of streaming connections between video servers and client displays. These devices involved in the streaming connection use an Ethernet Interface Card that consumes energy. In order to reduce the energy consumption, IEEE proposed the 802.3az Energy Efficient Ethernet standard, with a mechanism to make the network card change to a low power consumption mode when it is not in transmission mode. This behavior will be beneficial for services where traffic is sent in bursts, for instance video packet bursts like in video streaming over Real Time Transport Protocol in IPTV or the widely used DASH standard. Therefore, in this study the Ethernet traffic pattern when transmitting online video content using DASH is characterized in order to analyze the efficiency of the IEEE 802.3az standard under this video streaming scenario, and to verify the convenience of activating this energy saving alternative at the network interface of billions of client devices. The experiments have been conducted using a test-bed consisting of a full DASH streaming architecture, comparing different video segment sizes and changing the available bandwidth during the experiments in different scenarios in order to analyze the effect of the DASH content segment size on the Ethernet traffic pattern to identify the trade-off between energy efficiency, the energy savings, and the impact on the performance of the dynamic adaptation on the video streaming and reproduction.

Abstract Video streaming services have restrictive delay and bandwidth constraints. Ad hoc networks represent a hostile environment for this kind of real‐time data transmission. Emerging mesh networks, where a backbone provides more topological stability, do not even assure a high quality of experience. In such scenario, mobility of terminal nodes causes link breakages until a new route is calculated. In the meanwhile, lost packets cause annoying video interruptions to the receiver. This paper proposes a new mechanism of recovering lost packets by means of caching overheard packets in neighbor nodes and retransmit them to destination. Moreover, an optimization is shown, which involves a video‐aware cache in order to recover full frames and prioritize more significant frames. Results show the improvement in reception, increasing the throughput as well as video quality, whereas larger video interruptions are considerably reduced. Copyright © 2014 John Wiley & Sons, Ltd.

This paper presents an adaptive mechanism for improving the content download in wireless environments. The solution is based on the use of the file delivery over unidirectional transport (FLUTE) protocol in multicast networks, which reduce considerably the bandwidth when there are many users interested in the same contents. Specifically, the system proposed reduces the average download time of clients within the coverage area, thus improving the Quality of Experience. To that extent, clients send periodically feedback messages to the server reporting the losses they are experiencing. With this information, the server decides which is the optimum application layer-forward error correction (AL-FEC) code rate that minimizes the average download time, taking into account the channel bandwidth, and starts sending data with that code rate. The system proposed is evaluated in various scenarios, considering different distributions of losses in the coverage area. Results show that the adaptive solution proposed is very suitable in wireless networks with limited bandwidth.

This paper proposes the use of adaptive low density parity check (LDPC) application layer-forward error correction (AL-FEC) codes for content download services over erasure channels. In adaptive LDPC codes, clients inform the content download server of the losses they are experiencing. Using this information, the server makes forward error correction (FEC) parity symbols available to the client at an optimum code rate. This paper presents an analytical model of the proposed adaptive LDPC codes. The model is validated through measurements realized with an application prototype. In addition, results show the performance of these codes in different scenarios, compared to the performance of nonadaptive AL-FEC, optimum LDPC AL-FEC codes, and an almost ideal rateless code. Adaptive LDPC AL-FEC codes achieve download times similar to almost ideal rateless codes with less coding complexity, at the expense of an interaction channel between server and clients.

This paper shows that a reasonably better network bandwidth utilization in IPTV or general video delivery networks can be obtained with an automated RSVP-TE LSP reservation mechanism and by adding some video-awareness “intelligence” to certain Label Switching Routers which are part of the service provider's MPLS core network. We have implemented this intelligence on Juniper routers taking advantage of the JUNOS SDK, deployed the solution on a network test bed, and performed some measurements to validate the previous statement.

This paper presents a performance analysis of adaptive LDPC AL-FEC codes for content download services over erasure channels. In adaptive LDPC codes, clients inform the content download server of the losses they are experiencing. Using this information, the server makes FEC parity symbols available to the client at an optimum code rate. Results show the performance of adaptive AL-FEC codes for different scenarios as compared to non-adaptive AL-FEC, to optimum LDPC AL-FEC codes and to an almost ideal rateless code. Adaptive LDPC AL-FEC codes achieves download times similar to almost ideal rateless codes with less coding complexity, at the expense of an interaction channel between server and clients1.

In Optical Burst Switching (OBS) networks one of the most challenging problems is to provide service differentiation. The lack of buffering in the intermediate nodes, makes QoS provisioning in OBS networks a difficult problem to address. In this work, we propose a scheduling algorithm that supports

Nowadays, many multimedia cluster-to-cluster applications exist, such as 3D tele-immersion (3DTI), computer-supported collaborative workspaces (CSCWs), distributed multimedia presentations (DMP).... All these applications have sophisticated data transport requirements due to the use of multiple, semantically related flows of information. A synchronization mechanism must be used to synchronize the playout of the streams, regardless of the number of receivers and the number of streams played on the receiver clusters. In this paper, we present a new solution for multimedia group synchronization in such applications. Rather than base the solution on the definition of a new synchronization protocol (as other authors do), we base it on small modifications or extensions to RTP/RTCP standard protocols already used in most multimedia applications. Due to this, the overload introduced by the approach is minimal. The suitability of the approach was evaluated in a real one-way cluster-to-cluster application, with satisfactory results.

Optical burst switching (OBS) has been proposed to be a technology for implementing the next generation optical Internet. In this architecture, burst assembly algorithms have an important influence in the traffic pattern that characterizes this sort of optical networks. On the other hand, traffic coming from new applications (such as video on demand, Voice over IP, online gaming or Grid services) that have real time and bandwidth constraints has been experimented a rapid increment. Consequently, we consider important to evaluate the performance of the real time traffic over OBS networks. In this paper, we evaluate the video transmissions performance (MPEG4/RTP/UDP) over OBS networks, for both time-based and length-based burst assembly strategies at the edge node. Through event driven simulation, we conclude about the optimal configuration values of the assembly algorithm in order guarantee high quality video transmissions.

Most of actual multimedia tools use RTP/RTCP for inter-stream synchronization, but not for group synchronization. In this paper we describe and evaluate a proposal of modification of RTCP packets to provide a sender-based method for synchronization of a group of receivers

We propose to adapt the scalable schema of content delivery networks (CDN) to the campus environment, naming the novel architecture as campus content delivery network (CCDN). This overlay network will provide scalable and balanced access to the students and teachers to e-learning facilities. The CCDN will be composed by caches used as edge delivery nodes, content routing capabilities to route the client to the closest copy of the content, distributed content distribution and management and improving the access of users in terms of speed, reliability, scalability and prevention of flash-crowds. We present as a case study the work in progress of the deployment of a CCDN in the technical university of Valencia together with an e-learning streaming application over the CCDN.

Assessing of the physical condition of the human body, and concretely musculoskeletal disorders, frequently requires evaluating different tests performed by different devices. This information has to be analysed simultaneously to derive conclusions, and so a temporal relationship must be established between the data sources, Synchronization of the data sources of information is achieved by synchronising the clocks of computers connected in a local area network (LAN) by means of NTP. The added time-stamp is used to playback the data in a synchronised way. Although the proposed system is valid for any medical application in which data synchronisation is needed, it has been specifically used to capture, process, and analyse data generated by electromyographs, lumbar equipment, isotracks and video. Afterwards, the data can be distributed through Internet using a biomedia on demand (BoD) server. The whole system has been developed using JAVA and the Java Media Framework (JMF) libraries.

In this paper we present the design and development of a real-time e-learning system at the Polytechnic University of Valencia. The main novelty of this multimedia virtual classroom is the integration of Windows Media, Java Media Framework (JMF) and MPEG4 in a web-based environment. The communication network used in this real-time e-learning system is a satellite network for the multicasting of high-quality video from the teachers to the students using RTP, together with Internet/ISDN as return channel from the remote classrooms for low-quality video questions transmission. The system is fully operational and in the following year will be used as support for an e-learning co-operation project between Spain and South-America by a satellite communications operator.

Routing problems arise in several areas of distribution management and have been the object of study by mathematicians and operational researchers. We focus on auto-guided vehicles (AGVs) scheduling and guidance algorithm based on Monte Carlo simulation, and its execution under Windows NT as a real-time operating system verifying feasibility using the earliest deadline first (EDF) scheduling policy. For these purposes we simulate the environment in the laboratory prior to its real integration in the ceramic tile factory floor, working with mobile robots instead of AGVs (increasing in this way the flexibility and avoiding the outwork infrastructure) using Profibus Fieldbus Data Link (FDL) as the fieldbus communication network.

New real-time applications like videoconference and video-on-demand as well as classical industrial and military hard real-time applications require a set of accurate services from transport protocols. Management of a global time reference in the network is one of them. Possibly, XTP will be one of the standard communication protocols for distributed real-time systems in a few years, due to its great variety of services and high performance offered. The authors propose the incorporation of a new service to the XTP offered set: the supply of a common time reference to a group of XTP users within the network. The proposed synchronization protocol to maintain this common time service works by wave sequence making use of the multicasting functionality of XTP 4.0. This proposed synchronization service maybe added to future XTP versions.