Multi-access Edge Computing (MEC) is a new paradigm that brings storage and computing close to the clients. MEC enables the deployment of complex network-assisted mechanisms for video stream-ing that improve clients...
详细信息
Multi-access Edge Computing (MEC) is a new paradigm that brings storage and computing close to the clients. MEC enables the deployment of complex network-assisted mechanisms for video stream-ing that improve clients' Quality of Experience (QoE). One of these mechanisms is segment prefetching, which transmits the future video segments in advance closer to the client to serve content with lower latency. In this work, for HAS-based (HTTP Adaptive Streaming) video streaming and specifically considering a cellular (e.g., 5G) network edge, we present our approach segment Prefetching and caching at the Edge for Adaptive Video Streaming (SPACE). We propose and analyze different segment prefetching policies that differ in resource utilization, player and radio metrics needed, and deployment complexity. This variety of policies can dynamically adapt to the network's current conditions and the service provider's needs. We present segment prefetching policies based on diverse approaches and techniques: past segment requests, segment transrating (i.e., reducing segment bitrate/quality), Markov prediction model, machine learning to predict future segment requests, and super-resolution. We study their performance and feasibility using met-rics such as QoE characteristics, computing times, prefetching hits, and link bitrate consumption. We analyze and discuss which segment prefetching policy is better under which circumstances, as well as the influence of the client-side Adaptive Bit Rate (ABR) algorithm and the set of available representations (bitrate ladder) in segment prefetching. Moreover, we examine the impact on segment prefetching of different caching policies for (pre-)fetched segments, including Least Recently Used (LRU), Least Frequently Used (LFU), and our proposed popularity-based caching policy Least Popular Used (LPU).
With the increasing number of different types of applications for road safety and entertainment, it demands more flexible solutions for caching and transmitting large files in vehicular networks. In order to decrease ...
详细信息
ISBN:
(纸本)9783030061616;9783030061609
With the increasing number of different types of applications for road safety and entertainment, it demands more flexible solutions for caching and transmitting large files in vehicular networks. In order to decrease the transmission delay and raise the hit ratio of cached files, there is already a lot of research on caching technology, including segmented caching technology. But the problem of long transmission delay and low successful transmission ratio caused by the high dynamic of vehicles still needs to be solved. In this paper, we proposed an algorithm named Predictive Time Division Transmission (PTDT) to reduce transmission delay and raise the ratio of successful transmission for segmented cached file in vehicular networks. Our algorithm predicts the link duration between requesting vehicle and neighboring vehicles according to the relative inter-vehicle distances and velocities. By predicting the transmit rate of each vehicle on different time point, we divide the link duration into slices for subsequent transmitter selections. And finally we compare those time points and select the vehicles that make the transmitting delay the lowest. In the mean time, we arrange the transmitting order of those vehicles to guarantee the success of full file transmission process. The simulation results show that after applying our algorithm, transmission delay has reduced and successful transmission rate has increased substantially.
To support various bandwidth requirements for mobile multimedia services for future heterogeneous mobile environments, such as portable notebooks, personal digital assistants (PDAs), and 3G cellular phones, a transcod...
详细信息
To support various bandwidth requirements for mobile multimedia services for future heterogeneous mobile environments, such as portable notebooks, personal digital assistants (PDAs), and 3G cellular phones, a transcoding video proxy is usually necessary to provide mobile clients with adapted video streams by not only transcoding videos to meet different needs on demand, but also caching them for later use. Traditional proxy technology is not applicable to a video proxy because it is less cost-effective to cache the complete videos to fit all kinds of clients in the proxy. Since transcoded video objects have inheritance dependency between different bit-rate versions, we can use this property to amortize the retransmission overhead from transcoding other objects cached in the proxy. In this paper, we propose the object relation graph (ORG) to manage the static relationships between video versions and an efficient replacement algorithm to dynamically manage video segments cached in the proxy. Specifically, we formulate a transcoding time constrained profit function to evaluate the profit from caching each version of an object. The profit function considers not only the sum of the costs of caching individual versions of an object, but also the transcoding relationship among these versions. In addition, an effective data structure, cached object relation tree (CORT), is designed to facilitate the management of multiple versions of different objects cached in the transcoding proxy. Experimental results show that the proposed algorithm outperforms companion schemes in terms of the byte-hit ratios and the startup latency. (c) 2007 Elsevier B.V. All rights reserved.
暂无评论