Jian-Guang Luo

Large-scale live media streaming over peer-to-peer networks through global internet

We describe the design and implementation of unstructured peer-to-peer networks for large-scale live media streaming through global Internet in this paper. In so called GridMedia system, we adopt gossip-based protocol to organize end nodes into an application layer overlay. Each node in GridMedia independently selects its neighbors and utilizes a novel and efficient push-pull streaming mechanism to fetch data from neighbors with low latency and little redundancy. The traditional pull mode in the unstructured overlay has inherent robustness to high churn rate which is common in peer-to-peer environment while the push mode could efficiently diminish the accumulated latency observed at end users. A practical system based on this architecture has been developed, and we evaluate its performance on PlanetLab [10] in various rigorous conditions. All the results demonstrate that the proposed push-pull method in GridMedia achieves good performance even with high group change rate and very low upload bandwidth limitation. Furthermore, this system was provided for CCTV (the largest TV station in China) to live broadcast the Gala Evening of Spring Festival 2005 over global Internet at the bit rate of 300 Kbps. It is evidenced that more than 500,000 users were attracted all over the world with the peak concurrent online users of 15,239 during the night.

Gridmedia: A Practical Peer-to-Peer Based Live Video Streaming System

In this paper, we describe the design and implementation of a peer-to-peer based live video streaming system called Gridmedia. Gridmedia organizes the nodes into an unstructured overlay, and adopts a novel push-pull streaming mechanism to fetch data from the partner nodes. The pull mode in the unstructured overlay can work well with the high churn rate in P2P environment while the push mode can efficiently reduce the accumulated latency at user side. We also depict our practical solution of traversal over network address translators (NATs) and firewalls. Gridmedia was adopted by CCTV to broadcast the CCTV Spring Festival Gala 2005 through Internet and attracted more than 500,000 users all over the world during that night, with the maximum amount of concurrent users reaches as high as 15,239

A Trace-Driven Approach to Evaluate the Scalability of P2P-Based Video-on-Demand Service

Peer-to-Peer (P2P) networks have emerged as one of the most promising approaches to improve the scalability of Video-on-Demand (VoD) service over Internet. However, despite a number of architectures and streaming protocols have been proposed in past years, there is few work to study the practical performance of P2P-based VoD service especially in consideration of real user behavior which actually has significant impact on system scalability. Therefore, in this paper, we first characterize the user behavior by analyzing a large amount of real traces from a popular VoD system supported by the biggest television station in China, cctv.com. Then we ex-amine the practical scalability of P2P-based VoD service through extensive trace-driven simula-tion under a general system framework. The results show that P2P networks scale well in provid-ing VoD service under real user behavior by obtaining a considerable good cache hit ratio. Moreover, it is observed that adopting hard cache at client side help achieves better system scal-ability than that with soft cache. We also identify the impact of various aspects of user behavior upon system scalability through detailed simulation. We believe that our study will shine insight-ful light on the understanding of practical scalability of P2P-based VoD service and be helpful to future system design and optimization.

Gridmedia: A Multi-Sender Based Peer-to-Peer Multicast System for Video Streaming

We present a novel single source peer-to-peer multicast architecture called GridMedia which mainly consists of 1) multi-sender based overlay multicast protocol (MSOMP) and 2) multi-sender based redundancy-retransmitting algorithm (MSRRA). The MSOMP deploys mesh-based two-layer structure and groups all the peers into clusters with multiple distinct paths from the source root to each peer. To address the problem of long burst packet loss, the MSRRA is proposed at the sender peers to patch the lost packets by using receiver peer loss pattern prediction. Consequently, GridMedia provides a scalable and reliable video streaming system for a large and highly dynamic population of end hosts, and ensures the quality of service in terms of continuous playback, bandwidth demanding and low latency. A real experimental system based on GridMedia architecture has been constructed over CERNET and broadcasting TV programs for seven months. More than 140,000 end users have been attracted with almost 600 simultaneously being online at Aug 2004 during Athens Olympic Games

Characterizing user behavior to improve quality of streaming service over p2p networks

The universal recognition that it is critical to improve the performance of existing systems and protocols with the understanding to practical service experiences motivates us to discuss this issue in the context of peer-to-peer (P2P) streaming. With the benefit of both practical traces from traditional client-server (C/S) service systems and logs from P2P live broadcasting system, in this paper we first characterize end user behaviors in terms of online duration and reveal the statistically positive correlation between elapsed online duration and expected remaining online time. Then we explore the feasibility to improve the quality of streaming service over P2P networks by proposing Low Disruption Tree Construction (LDTC) algorithm to take the online duration information into account when peers self-organize into the service overlay. The experiment results show that LDTC could achieve higher stability of video date delivery tree and in turn improve the quality of streaming service.

Chasing: an efficient streaming mechanism for scalable and resilient video-on-demand service over peer-to-peer networks

Provisioning scalable and resilient Video-on-Demand (VoD) service is both challenging and interesting. Recently, peer-to-peer (P2P) networks are introduced to address the scalability of VoD service over Internet. Most of existing work follows the line of cache-and-relay (CR) scheme to accommodate the asynchronous characteristic of requests from a community of end users. Aiming to take full advantages of bandwidth capacities at each node and pre-recorded feature of requested video files at streaming server, we improve traditional CR approach by efficiently exploiting surplus bandwidth and proactively prefetching media contents from either the server or other peers. Our proposed basic chasing and advanced chasing mechanism not only achieve significant reduction of workload on streaming server, which could translate into better scalability, but also help the streaming session to adapt to volatile network fluctuation. Our extensive experiments have demonstrated encouraging results with respect to increased system performance.

Characterizing user behavior model to evaluate hard cache in peer-to-peer based video-on-demand service

Peer-to-peer (P2P) based video-on-demand (VoD) systems rely on the cooperation among peers to reduce the server workload. Recently, hard cache is used to further improve the system scalability, because the contents will not be immediately cleaned up when the users get offline. However, how many practical benefits hard cache will bring to the P2P based VoD service has not been well studied and still remains far from clear. In this paper, we first characterize user behavior model with the benefit of millions of real VoD traces and identify several practical factors which potentially impact the system performance. Then we further conduct extensive trace-driven simulations to evaluate the scalability of P2P based VoD system with hard cache enabled and some interesting results are found.

Design and Deployment of a Peer-to-Peer Based IPTV System over Global Internet

IPTV is highly advocated in recent years. Today, the growth of the residential users makes it possible to broadcast live video content through global Internet to a great population of end users. In this paper, we mainly describe the design and deployment experiences of a peer-to-peer (P2P) based IPTV system called Gridmedia since P2P is universally recognized as a scalable and cost-effective means for group communication. In order to reduce the playback latency at end users as well as offer resilience to high churn rate in peer community, Gridmedia organizes end users into an unstructured overlay while proposes an efficient push-pull streaming mechanism to distribute video segments among partner nodes. To further verify the prototype, on one hand we conduct extensive experiments over PlanetLab to confirm the overlay architecture and streaming mechanism in Gridmedia can greatly reduce the average playback latency as compared to previous works; on the other hand the practical deployment of Gridmedia system over global Internet also demonstrated it could reliably support large number of users without need of network infrastructure. We also discuss, in a practical way, the issues when perfecting a prototype to a publicly released platform and system performance during live broadcasting CCTV Spring Festival Gala 2006.

Improving quality of live streaming service over p2p networks with user behavior model

In this paper, we mainly investigate how to improve the streaming quality of service over Peer-to-Peer (P2P) networks with the benefit of practical service traces. Considering that the QoS of P2P live streaming is generally affected by high dynamics in peer community, we abstract the online duration model of end users and then exploit this characteristic to improve the stability and encourage contribution in P2P networks, which in turn facilitates the quality of streaming. The first effort involves the online information when constructing video delivery tree and hence achieves less playback disruption. The other algorithm takes the online duration into account when selecting neighbor peers for data exchange and advocates more mutual cooperation between peers. The experiment results show that the proposed schemes could respectively achieve higher stability and better delivery quality.

Evaluation of Practical Scalability of Overlay Networks in Providing Video-on-Demand Service

Recently, overlay networks have been proposed to address the problem of scalability in providing video-on-demand (VoD) service. However, from the perspective of service providing, their efficiency has not been carefully studied and still remains far from clear, especially considering the impacts of user interactivities and in the case of multiple files with different and varying popularities on sharing. Towards this end, in this paper, by analyzing more than 20,000,000 real workload traces, we first identify two practical factors which we believe have determinant impacts on the scalability: user interactivities and popularity differences among files. Then we further evaluate cache-and-relay (CR), a representative scheme of overlay networks, with the real workload traces. Simulation results show that CR only saves about half of the server bandwidth even when there is no buffer constraint at clients, not so scalable as our original expectation