Measurement and Analysis of an Internet Streaming Service to Mobile Devices

Abstract

Abstract-ReceivingInternet streaming services on various mobile devices is getting increasingly popular, and cloud platforms have also been gradually employed for delivering streaming services to mobile devices. While a number of studies have been conducted at the client side to understand and characterize Internet mobile streaming delivery, little is known about the server side, particularly for the recent cloud-based Internet mobile streaming delivery. In this work, we aim to investigate the Internet mobile streaming service at the server side. For this purpose, we have collected a four-month server-side log on the cloud (with 1,002 TB delivered video traffic) from a top Internet mobile streaming service provider serving worldwide mobile users. Through trace analysis, we find that (1) a major challenge for providing Internet mobile streaming services is rooted from the mobile device hardware and software heterogeneity. In this workload, we find over 3,400 different hardware models with more than 100 different screen resolutions running 14 different mobile OS and 3 audio codecs and 4 video codecs. (2) To deal with the device heterogeneity, CPU-intensive transcoding is used on the cloud to customize the video to the appropriate versions at runtime for different devices. A video clip could be transcoded into more than 40 different versions in order to serve requests from different devices. (3) Compared to videos in traditional Internet streaming, mobile streaming videos are typically of much smaller size (a median of 1.68 MBytes) and shorter duration (a median of 2.7 minutes). Furthermore, the daily mobile user accesses are more skewed following a Zipf-like distribution but users' interests also quickly shift. Considering the huge demand of CPU cycles for online transcoding, we further examine server-side caching in order to reduce the total CPU cycle demand from the cloud. We show that a policy considering different versions of a video altogether outperforms other intuitive ones when the cache size is limited.

Resource pooling in large-scale content delivery systems

“…We analyze the performance of the system when the p i 's satisfy the Zipf distribution which is defined as follows: the fraction of requests for the i th most popular content is proportional to i −β , where β ≥ 0 is a constant, known as the Zipf parameter. This is motivated by the fact that empirical studies of many VoD services have shown that the content popularity distributions match well with the Zipf distribution [18]- [21]. Typical values of β lie between 0.6 and 2.…”

“…In Figure 13, we plot the mean transmission rate for the KS+MLP policy and the lower bound on the expected transmission rate as a function of the Zipf parameter β. Typical values of β for video of demand systems lie between 0.6 and 2 [18]- [21]. We simulate a system with 1000 contents (n = 1000) and 200 caches (m = 200) for two different values of storage per cache.…”

On information exposure through named content

“…The proliferation of mobile devices is characterised by substantial heterogeneity, i.e., a recent analysis of an Internet mobile streaming service reported "3,400 hardware models with 109 screen resolutions running 14 mobile OS, 3 audio codecs and 4 video codecs" [24]. Obviously the format of the content may be inadequate for certain devices (e.g., incompatible codecs, very low resolution) and/or it may waste network resources (e.g., streaming high resolution video to low resolution devices).…”

Performance improvement for source mobility in named data networking based on global–local FIB updates

“…Mobile devices are a necessity for people's daily life, especially since the explosion of smart phone and tablet [1]. With the fast development of wireless technologies [2,3] and wide deployment of 3G/4G/LTE base stations and WiFi hotspots [4,5], the mobile devices can be connected to the Internet at anytime and at anywhere [6], where the communication among peers becomes more convenient.…”