Receiver Buffer Size Research Articles

Multi-agent DRL-based Multipath Scheduling for Video Streaming with QUIC

The popularization of video streaming brings challenges in satisfying diverse Quality of Service (QoS) requirements. The multipath extension of the Quick UDP Internet Connection (QUIC) protocol, also called MPQUIC, has the potential to improve video streaming performance with multiple simultaneously transmitting paths. The multipath scheduler of MPQUIC determines how to distribute the packets onto different paths. However, while applying current multipath schedulers into MPQUIC, our experimental results show that they fail to adapt to various receive buffer sizes of different devices and comprehensive QoS requirements of video streaming. These problems are especially severe under heterogeneous and dynamic network environments. To tackle these problems, we propose MARS, a Multi-agent deep Reinforcement learning (MADRL)-based Multipath QUIC Scheduler, which is able to promptly adapt to dynamic network environments. It exploits the MADRL method to learn a neural network for each path and generate scheduling policy. Besides, it introduces a novel multi-objective reward function that takes out-of-order queue size and different QoS metrics into consideration to realize adaptive scheduling optimization. We implement MARS in an MPQUIC prototype and deploy in Dynamic Adaptive Streaming over HTTP system. Then, we compare it with the state-of-the-art multipath schedulers in both emulated and real-world networks. Experimental results show that MARS outperforms the other schedulers with better adaptive capability regarding the receive buffer sizes and QoS.

БЕСШОВНОЕ ВОСПРОИЗВЕДЕНИЕ ЖИВОЙ ПОТОКОВОЙ TCP-ТРАНСЛЯЦИИ МЕТОДОМ ОПЕРЕЖАЮЩЕЙ ЗАГРУЗКИ С НИЗКОЙ ЗАДЕРЖКОЙ

The article discusses the client-server technology for organizing seamless live TCP-streaming with the use of progressive download method. Main factors which have a major impact on the overall playback latency have been identified. A study on the most important factor – the size of the client’s receiving buffer Lbuf – was carried out. It was found that the hypothetical display time of the last frame taken consists of two components: 1) the general instability, which has the character of a pronounced “band of instability”, and 2) episodic “drawdowns” associated with spontaneous media flow retentions in data transmission channel.The result of these drawdowns is an increase in Lbuf, resulting in increased playback delay. The article proposes a method to reduce the client’s receive buffer latency downto acceptable level (100-300 ms), allowing two-way communication between clients – an algorithm for smooth correction of client receiving buffer size. The article includes the results of the smooth correction algorithm in the implementation of TCP-Streaming by means of progressive downloading method. The implementation is a distributed software package consisting of one or more encoding processes, retransmitting process, client-side software. The media-flow Encoders converts data from the media-data sources (camera, computer screen, microphone) and transmits them to the clients via Retransmitter. The client-side software is a set of web pages (HTML + JS) where the receive buffer smooth correction algorithm is implemented. It was concluded that live TCP-streaming by means of progressive download method is quite suited to organize the communication with low latency between clients.

An Adaptive and Efficient Packet Scheduler for Multipath TCP

A multipath TCP (MPTCP) scheduler selects a suitable path for each data packet and helps to improve the performance of MPTCP. In this paper, we analyze various existing schedulers and find some current open issues like head-of-line blocking problem, receive window limitation, and out-of-order packet delivery. All these issues degrade the performance of MPTCP, which can be overcome by the careful design of an MPTCP scheduler. We then propose a new MPTCP packet scheduler named as an adaptive and efficient packet scheduler (AEPS) that not only overcomes these issues but also provides high throughput with a minimum completion time by utilizing the bandwidth of all the available paths. AEPS delivers the data packets in-order to the receiver, and its performance does not affect by the size of the receiver buffer and data size that is being transferred. We show experimentally and analytically that the proposed scheduler outperforms the existing schedulers.

Energy-Efficient Pushing With Content Consumption Constraints: A Network Calculus Approach

Joint pushing and caching (JPC) holds the promise of achieving high spectral and energy efficiency in future networks, thereby attracting much attention most recently. However, few attention has been paid to the content consumption process that describes how a content item leaves the receiver buffer after the request time. Such a process bounds the amount of data that have arrived in the buffer, thereby constraining the content transmission. By taking content consumption processes into account, this paper aims to present optimal JPC policies that minimize the transmission energy under receiver buffer size and content consumption constraints. In particular, two common types of content consumption processes, instantaneous reading and sequential reading, along with two content transmission strategies, orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA), are respectively considered. Energy minimization problems are first formulated as variational problems based on the network calculus approach, and are then equivalently transformed into convex optimization problems in order to reduce the computational complexity. It is shown that JPC policies are capable of significantly reducing the energy consumption when receiver buffer sizes are large. Furthermore, the NOMA based JPC achieves higher energy efficiency than the OMA based JPC by effectively exploiting physical layer multicasting opportunities.

Destination buffer analysis for packets rejection obliteration in multi-channel networks

In this paper we study a multi-channel network, each station of which is equipped with a network interface that has a receiver buffer of multiple packets. In this way, each station is able to receive multiple packets per time instant. We adopt a synchronous access protocol which is affected by the collisions over the multiple channels and the destination conflicts. The proposed protocol performance crucially depends on the size of the receiver buffer since it determines the packet rejection probability at destination. An analytical probabilistic model based on a Markovian process is adopted for the performance measures derivation by means of closed mathematical formulas. The proposed protocol is compared to relative ones that either totally ignore the receiver collisions or assume a receiver buffer of a single packet capacity. The numerical results show that the increase of the receiver buffer size improves the performance decisively, resulting in higher throughput and lower delay and rejection probability. Also, it is shown that the appropriate receiver buffer size per station in order for the rejections at destination to be effectively eliminated is not unlimited but is limited to three packets for 0.1% accepted maximum level of rejection probability.

An Experimental Study on Multipath TCP Congestion Control With Heterogeneous Radio Access Technologies

In the near future, a large volume of the data traversing wireless networks will not only be requested and/or reported by humans but also by machines (e.g., the Internet-of-things and machine-to-machine applications). This mandates the availability of enormous radio spectrum resources and an end-to-end reliable information transfer. Currently, many wireless devices are equipped with two wireless interfaces with heterogeneous radio access technologies. Thus, the usage of a transport layer designed for multi-homed devices such as multipath transmission control protocol (MPTCP) is inevitable. This paper presents an experimental performance study of three congestion control algorithms, which can be used by MPTCP, namely, Cubic, linked-increases algorithm (LIA), and opportunistic LIA (OLIA). The testbed comprises real (not simulated) LTE and WiFi networks that are used to connect dual-homed wireless nodes to one another. We comparatively study the throughput performance of the three algorithms under varying factors, including the receiver buffer size, number of parallel connections, data volume, and flow lifetime. Our key findings reveal that, although Cubic is not designed with multipath in mind, it outperforms the multipath-based LIA and OLIA, whenever the LTE per-node capacity is higher than its WiFi counterpart. Also, in a reversed situation (WiFi per-node capacity is higher) Cubic outperforms OLIA and LIA for short-lived flows.

Exploiting Parallelism With Random Linear Network Coding in High-Speed Ethernet Systems

Parallelism has become one of the key architectural features in 40-/100-/400-Gb Ethernet multi lane distribution (MLD) standards. The MLD packetizes and distributes traffic adaptively over parallel lanes and maps them to parallel network interfaces for wide area transmission, typically over optical networks. As such, the MLD creates not only new network topology abstractions but also enables modular implementations of various new features to improve the system performance. In this paper, we study the performance of the parallelized Ethernet in combination with erasure coding and more specifically random linear network coding (RLNC). We present a novel theoretical modeling framework, including the derivation of upper and lower bounds of differential delay and the resulting receiver queue size—a critical performance measure in the high-speed Ethernet. The results show benefits of a combined usage of parallelism and RLNC: with a proper set of design parameters, the differential delay and the receiver buffer size can be reduced significantly, while cross-layer design and path computation greatly simplified.

Content Pushing With Request Delay Information

Pushing along with proactive caching, in which content items are transmitted prior to being requested by a user, holds the promise of trading scalable storage resources for substantial throughput increase in content-centric networks. In this paper, a joint pushing and caching (JPC) method is studied, which determines when and which content to be pushed to, and to be removed from, the receiver buffer based on content request delay information (RDI) that predicts a user’s request time for certain content items. Both offline and online JPC policies with noncausal, statistical, and causal RDI are proposed based on a greedy algorithm and dynamic programming. The effective throughputs of the policies are evaluated, and they are seen to increase with both the receiver buffer size and the pushing limited channel capacity. The analysis also reveals the fundamental tradeoff between communication and storage resources. Furthermore, RDI feedback is shown to significantly enhance the performance of the online JPC without incurring much signaling overhead or complexity, especially in small buffer scenarios.

Deterministic Time Markov Chain Modelling of Simultaneous Multipath Transmission Schemes

The increase in the availability of multimode devices for ubiquitous network access and the need for larger bandwidth have created a thrust for the utilization of simultaneous network connections. Unfortunately, the standard transport layer protocols such as the transmission control protocol and user datagram protocol have structural constraints. As a result, an Internet application can use only one interface at a time. The stream control transmission protocol (SCTP) provides support for concurrent multipath transfer (SCTP-CMT). In this paper, we present the mathematical modeling of simultaneous multipath transmission (SMT) schemes using the deterministic time Markov chain (DTMC) model. In this DTMC model, receiver buffer size is used for the first time to estimate the sending data rate. The DTMC model of SMT schemes are compared with the SCTP-CMT using probability-based packet dropped scenarios. DTMC modeling is used to mathematically verify simulation results of SMT Schemes i.e., modified fast retransmit (SMT-MFR) and adaptive modified fast retransmit (SMT-AMFR). The analytical model results revealed that SMT-MFR outperformed SCTP-CMT by 8.54% gain in average throughput. SMT-AMFR outperformed the SCTP-CMT and SMT-MFR by 19.65% and 11.15% gain in average throughput, respectively.

Enhancing Performance of TCP Variants in LTE

Long Term Evolution (LTE) is the 3rd Generation Partnership Project (3GPP), all-IP wireless protocol that evolved from Global System for Mobile Communications (GSM). Congestion control algorithms are an important part of Transmission Control Protocol (TCP) that directly determines the performance of the protocol in the IP Network. Several TCP variants have been proposed. It can be used to enhance quality of service (QoS). In this paper, an enhanced approach is proposed to improve the performance of LTE network. The proposed approach depends on controlling the receive buffer size in eNode B. This will be performed through dividing the memory size of eNode B between active users. Simulation results show the effectiveness of the proposed approach that lead to enhance performance in terms of network throughput and low time delay.

Temporary redundant transmission mechanism for SCTP multihomed hosts.

In SCTP's Concurrent Multipath Transfer, if data is sent to the destined IP(s) without knowledge of the paths condition, packets may be lost or delayed. This is because of the bursty nature of IP traffic and physical damage to the network. To offset these problems, network path status is examined using our new mechanism Multipath State Aware Concurrent Multipath Transfer using redundant transmission (MSACMT-RTv2). Here the status of multiple paths is analyzed, initially and periodically thereafter transmitted. After examination, paths priority is assigned before transmission. One path is temporarily employed as redundant path for the failure-expected path (FEP); this redundant path is used for transmitting redundant data. At the end of predefined period, reliability of the FEP is confirmed. If FEP is ensured to be reliable, temporary path is transformed into normal CMT path. MSACMT-RTv2 algorithm is simulated using the Delaware University ns-2 SCTP/CMT module (ns-2; V2.29). We present and discuss MSACMT-RTv2 performance in asymmetric path delay and with finite receiver buffer (rbuf) size. We extended our experiment to test robustness of this algorithm and inferred exhaustive result. It is inferred that our algorithm outperforms better in terms of increasing the throughput and reducing the latency than existing system.

Paths selection‐based resequencing queue length in concurrent multipath transfer

SummaryTraditionally, concurrent multipath transfer (CMT) is used to achieve aggregate bandwidth in next generation networks, which are expected to be heterogeneous, integrating access networks employing different technologies. Simultaneous data transfer over multiple destination addresses could increase throughput, but causes data reordering at the destination. A lot of studies assumed that the receiver buffer (RBUF) in CMT is unlimited, actually, it's not. However, limited RBUF indeed affects the whole performance and even causes RBUF blocking problem in the real situation. In this paper, we analyze the RBUF blocking problem brought by simultaneous data transfer with limited RBUF. Then, we propose a new analytical model of reliable delivery to predict the Stream Control Transmission Protocol throughput and the length expectation of the resequenceing queue in CMT. Based on the model mentioned earlier, the paths selection problem is formulated as a knapsack problem, which maximizes the overall throughput and limits the resequencing queue length expectation to the fixed RBUF size. Through the computer simulations, the proposed analytical model can predict the throughput of CMT accurately. It is proved that our proposed paths selection has achieved much better performance than the others in CMT.Copyright © 2014 John Wiley & Sons, Ltd.

SCTP performance improvement based on virtual receiver window

This article puts forward one algorithm for stream control transfer protocol (SCTP) improvement with limited receiver buffer (RBUF). As is well known, SCTP is one of the most important transfer control protocol, but most researches focus on the situations without the RBUF limit. In this study, we analyze the impact of the RBUF size on the performance. Computer simulations show that the network utility is low in reliable transfer, when the RBUF size is smaller than bandwidth delay product. By studying the transmission sequence number (TSN) transfer progress, we find that the peer receiver window (PEER_RWND), which lags behind the true receiver window (RWND), leads to the poor network utility. To improve SCTP performance with limited RBUF, the virtual receiver window (VIRTUAL_RWND) is introduced. Based on the VIRTUAL_RWND, one algorithm is proposed to increase the sending rate. Computer simulations have evaluated an excellent performance of the proposed algorithm at both ideal link without lost packet and nonideal link with lost packet.

Authentication schemes for multimedia streams

With the rapid increase in the demand for multimedia services, securing the delivery of multimedia content has become an important issue. Accordingly, the problem of multimedia stream authentication has received considerable attention by previous research and various solutions have been proposed. However, these solutions have not been rigorously analyzed and contrasted to each other, and thus their relative suitability for different streaming environments is not clear. This article presents comprehensive analysis and comparison among different schemes proposed in the literature to authenticate multimedia streams. Authentication schemes for nonscalable and scalable multimedia streams are analyzed. To conduct this analysis, we define five important performance metrics, which are computation cost, communication overhead, receiver buffer size, delay, and tolerance to packet losses. We derive analytic formulas for these metrics for all considered authentication schemes to numerically analyze their performance. In addition, we implement all schemes in a simulator to study and compare their performance in different environments. The parameters for the simulator are carefully chosen to mimic realistic settings. We draw several conclusions on the advantages and disadvantages of each scheme. We extend our analysis to authentication techniques for scalable streams. We pay careful attention to the flexibility of scalable streams and analyze its impacts on the authentication schemes. Our analysis and comparison reveal the merits and shortcomings of each scheme, provide guidelines on choosing the most appropriate scheme for a given multimedia streaming application, and could stimulate designing new authentication schemes or improving existing ones. For example, our detailed analysis has led us to design a new authentication scheme that combines the best features of two previous schemes.

Optimization of Multiservice Scheduling for Variable Bit Rate Video Transmission in DVB-H Systems

Digital Video Broadcasting for Handheld terminals (DVB-H) is assuming an ever growing importance for digital video transmission over wireless terminals. In such a context, Time Slicing has been implemented to achieve a better power saving and manage handover. Specifically, a generic user transmits bursts of data, interspaced by time periods in which no data are transmitted. In this paper, to improve time sliced multiservice transmission effectiveness, the Variable Burst Time (VBT) algorithm is presented and discussed. It dynamically varies the whole set of stream Burst Durations according to input stream data, available channel bandwidth, receiving buffer size and eventually stream priority. Burst Durations are derived by the minimization of a Total Loss Function (TLF) representing the amount of losses of the whole service set. Numerical results show the VBT effectiveness if compared with the time sliced transmission recommended in the DVB guidelines, for different numbers, types and quality degrees of VBR streams, receiving buffer sizes and stream priorities. This suggests that VBT could be efficiently exploited for transmission of VBR streams in DVB-H systems.

Variable Time Scale Multimedia Streaming Over IP Networks

This paper presents a comprehensive analysis of a variable time-scale streaming technique, VTSS, according to which rate changes are obtained by varying the inter-packet transmission interval, rather than altering, as in most cases, the source coding rate. Instead of constraining the transmitter to operate in real-time, the time scale of the packet scheduler can vary between zero, when the network is congested, to as faster than real-time as the channel bandwidth allows, when the network is lightly loaded. Although this approach is reportedly used in commercial streaming products, so far the technique has not yet been analyzed in a rigorous fashion, nor it has been compared to other state-of-the-art streaming techniques. This work first presents a theoretical analysis of the performance achievable by the VTSS approach, and it shows that, for the same channel conditions, VTSS yields a total distortion which is lower or, in the worst case, equal than the distortion of the standard real-time source-rate adaptive approach. A lower bound on receiver buffer size is also derived. Network simulations then analyze the performance of a TCP-friendly test implementation of VTSS compared with an ideal real-time source rate-adaptive technique, whose performance, being ideal, represents the upper bound of any transmission scheme based on source rate adaptation. The simulation results, also based on actual network traces, show that the VTSS approach delivers higher perceptual quality (up to 1.2 dB PSNR in the considered scenarios) and reduced video quality fluctuations (1.6 dB standard deviation PSNR, instead of 4.9 dB) for a wide range of standard video sequences. Perceptual quality evaluation by means of PVQM confirms such results. The gains, as expected, are even more pronounced (7.6 dB PSNR on average) if compared to real-time constant bit-rate video transmission.

Effect of Delay and Buffering on Jitter-Free Streaming Over Random VBR Channels

We study the optimal streaming of variable bit-rate (VBR) video over a random VBR channel. The goal of a streaming application is to enable the successful decoding of each video object before its displaying deadline is violated. Hence, we define the main performance metric of a streaming system as the probability of un-interrupted video presentation, or jitter-free probability. Previous literature has described solutions to estimate the jitter-free probability by assuming either independence in the encoded data process or simplistic channel models. In this work, we present a novel analytical framework, which requires only some basic statistical information of an arbitrary VBR channel, to bound the probability of jitter-free playout under the constraint of initial playout delay and receiver buffer size. Both the infinite and finite buffer cases are considered. This technique is then applied to investigate streaming over a wireless system modeled by an extended Gilbert channel with ARQ transmission control. Experimental results with MPEG-4 VBR encoded video demonstrates that the proposed analysis derives close bounds to the actual system performance. Finally, we show that the proposed analysis provides a theoretical foundation to quantify the tradeoffs between the initial playout delay, the receiver buffer size, and the jitter-free probability for a general class of VBR streaming over random VBR channels.

MTCP: A Transmission Control Protocol for Multi-Provider Environment

Transmission schemes that gain content from multiple servers concurrently have been highlighted due to their ability to provide bandwidth aggregation, stability on dynamic server departure, and load balancing. Previous approaches employ parallel downloading in the transport layer to minimize the receiver buffer size and maximize bandwidth utilization. However, they only focus on the receiver operations and induce considerable overhead at the senders in contradiction to the main goal of a multi-provider environment, offloading popular servers through replication. In the present work, the authors propose MTCP, a novel transport layer protocol that focuses on reduction of the sender overhead through the elimination of unnecessary disk I/Os and efficient buffer cache utilization. MTCP also balances trade-off objectives to minimize buffering at receivers and maximize the request locality at senders.

Concurrent Multipath Transfer Using SCTP Multihoming Over Independent End-to-End Paths

Concurrent multipath transfer (CMT) uses the Stream Control Transmission Protocol's (SCTP) multihoming feature to distribute data across multiple end-to-end paths in a multihomed SCTP association. We identify three negative side-effects of reordering introduced by CMT that must be managed before efficient parallel transfer can be achieved: (1) unnecessary fast retransmissions by a sender; (2) overly conservative congestion window (cwnd) growth at a sender; and (3) increased ack traffic due to fewer delayed acks by a receiver. We propose three algorithms which augment and/or modify current SCTP to counter these side-effects. Presented with several choices as to where a sender should direct retransmissions of lost data, we propose five retransmission policies for CMT. We demonstrate spurious retransmissions in CMT with all five policies and propose changes to CMT to allow the different policies. CMT is evaluated against AppStripe, which is an idealized application that stripes data over multiple paths using multiple SCTP associations. The different CMT retransmission policies are then evaluated with varied constrained receive buffer sizes. In this foundation work, we operate under the strong assumption that the bottleneck queues on the end-to-end paths used in CMT are independent

Performance evaluation of DCCP: A focus on smoothness and TCP-friendliness

Recent years have seen dramatic increases of the use of multimedia applications on the Internet, which typically either lack congestion control or use proprietary congestion control mechanisms. This can easily cause congestion collapse or compatibility problems. Datagram Congestion Control Protocol (Dccp) fills the gap betweenUdp andTcp, featuring congestion control rather than reliability for packet-switched rich content delivery with high degree of flexibility. We present aDccp model designed and implemented withOpnet Modeler, and the experiments and evaluation focused on largely the smoothness of the data rates, and the fairness between concurrentDccp flows andTcp flows. We foundDccp-ccid3 demonstrates stable data rates under different scenarios, and the fairness betweenDccp andTcp is only achieved under certain conditions. We also validated that the throughput ofDccp-Ccid3 is proportional to the average packet size, and relatively fixed packet size is critical for the optimal operation ofDccp. Problems in the slow start phase and insufficient receiver buffer size were identified and we hereby proposed solutions on this.