There has been a recent trend that video-on-demand (VoD) providers such as Netflix are leveraging resources from cloud services for multimedia streaming. In this paper, we consider the scenario that a VoD provider can make reservations for bandwidth guarantees from cloud service providers to guarantee the streaming performance in each video channel. We propose a predictive resource auto-scaling system that dynamically books the minimum bandwidth resources from multiple data centers for the VoD provider to match its short-term demand projections. We exploit the anti-correlation between the demands of video channels for statistical multiplexing and for hedging the risk of under-provision. The optimal load direction from channels to data centers is derived with provable performance. We further provide suboptimal solutions that balance bandwidth and storage costs. The system is backed up by a demand predictor that forecasts the demand expectation, volatility and correlations based on learning. Extensive simulations are conducted driven by the workload traces from a commercial VoD system.

Large-scale live peer-to-peer (P2P) streaming applications have been successfully deployed in today's Internet. While they can accommodate hundreds of thousands of users simultaneously with hundreds of channels of programming, there still commonly exist channels and times where and when the streaming quality is unsatisfactory. In this paper, based on more than two terabytes and one year worth of live traces from UUSee, a large-scale commercial P2P live streaming system, we show an in-depth network-wide diagnosis of streaming inefficiencies, commonly present in typical mesh-based P2P live streaming systems. As the first highlight of our work, we identify an evolutionary pattern of low streaming quality in the system, and the distribution of streaming inefficiencies across various streaming channels and in different geographical regions. We then carry out an extensive investigation to explore the causes to such streaming inefficiencies over different times and across different channels/regions at specific times, by investigating the impact of factors such as the number of peers, peer upload bandwidth, inter-peer bandwidth availability, server bandwidth consumption, and many more. The original discoveries we have brought forward include the two-sided effects of peer population on the streaming quality in a streaming channel, the significant impact of inter-peer bandwidth bottlenecks at peak times, and the inefficient utilization of server capacities across concurrent channels. Based on these insights, we identify problems within the existing P2P live streaming design and discuss a number of suggestions to improve real-world streaming protocols operating at a large scale.

Peer-assisted on-demand video streaming services are extremely large-scale distributed systems on the Internet. Automated demand forecast and performance prediction, if implemented, can help with capacity planning and quality control so that sufficient server bandwidth can always be supplied to each video channel without incurring wastage. In this paper, we use time-series analysis techniques to automatically predict the online population, the peer upload and the server bandwidth demand in each video channel, based on the learning of both human factors and system dynamics from online measurements. The proposed mechanisms are evaluated on a large dataset collected from a commercial Internet video-on-demand system.

Video-on-demand (VoD) servers are usually over-provisioned for peak demands, incurring a low average resource efficiency. However, bandwidth shortage may still occur for individual videos as they share and contend for server resources. In this position paper, we propose a predictive workload management system for VoD servers targeting bandwidth. The system draws belief about future demand as well as demand volatility based on demand history using time series forecasting techniques. The prediction enables dynamic and efficient server bandwidth reservation with QoS guarantees. More importantly, we use a hedging technique similar to investment portfolio management and distribute workloads to multiple servers exploiting demand anti-correlation. The proposed system consolidates the workloads, enhances resource utilization, while in the meantime effectively controlling risk of server overload. The proposed methods are evaluated based on real-world VoD traces.

Bandwidth usage in large-scale Video on Demand (VoD) systems varies rapidly over time, due to unpredictable dynamics in user demand and network conditions. Such bandwidth volatility makes it hard to provision the exact amount of server resources that matches the demand in each video channel, posing significant challenges to achieving quality assurance and efficient resource allocation at the same time. In this paper, we seek to statistically model time-varying traffic volatility in VoD servers, leveraging heteroscedastic models first used to interpret economic time series, with the goal of forecasting not only traffic patterns but also traffic volatility. We present the application of volatility forecast to efficient resource allocation that provides probabilistic service level guarantees to user groups. We also discuss volatility reduction from diversification, and its implications to new strategies for cost-effective server management. Our study is based on monitoring the workload of a large-scale commercial VoD system widely deployed on the Internet.

To guarantee the streaming quality in live peer-to-peer (P2P) streaming channels, it is preferable to provision adequate levels of upload capacities at dedicated streaming servers, compensating for peer instability and time-varying peer upload bandwidth availability. Most commercial P2P streaming systems have resorted to the practice of overprovisioning a fixed amount of upload capacity on streaming servers. In this paper, we have performed a detailed analysis on 10 months of run-time traces from UUSee, a commercial P2P streaming system, and observed that available server capacities are not able to keep up with the increasing demand by hundreds of channels. We propose a novel online server capacity provisioning algorithm that proactively adjusts server capacities available to each of the concurrent channels, such that the supply of server bandwidth in each channel dynamically adapts to the forecasted demand, taking into account the number of peers, the streaming quality, and the channel priority. The algorithm is able to learn over time, has full Internet service provider (ISP) awareness to maximally constrain P2P traffic within ISP boundaries, and can provide differentiated streaming qualities to different channels by manipulating their priorities. To evaluate its effectiveness, our experiments are based on an implementation of the algorithm, which replays real-world traces.

Since the inception of network coding in information theory, we have witnessed a sharp increase of research interest in its applications in communications and networking, where the focus has been on more practical aspects. However, thus far, network coding has not been deployed in real-world commercial systems in operation at a large scale, and in a production setting. In this paper, we present the objectives, rationale, and design in the first production deployment of random network coding, where it has been used in the past year as the cornerstone of a large-scale production on-demand streaming system, operated by UUSee Inc., delivering thousands of on-demand video channels to millions of unique visitors each month. To achieve a thorough understanding of the performance of network coding, we have collected 200 Gigabytes worth of real-world traces throughout the 17-day Summer Olympic Games in August 2008, and present our lessons learned after an in-depth trace-driven analysis.

Quality control and resource optimization are challenging problems in peer-assisted video streaming systems, due to their large scales and unreliable peer behavior. Such systems are also prone to per- formance degradation in the event of drastic demand changes, such as flash crowds and large-scale simultaneous peer departures. In this paper, we demonstrate the deficiency of state-of-the-art video streaming systems by analyzing real-world traces from UUSee, a popular commercial P2P media streaming system based in China, during the 2008 Beijing Olympics. We show how simple machine learning techniques combined with periodic collection of statistics can be used for automated monitoring and diagnosis of peer-assisted video streaming systems. With such a framework, it is possible to es- timate performance given certain resource usage patterns, making resource utilization more efficient. It also enables the prediction of large-scale performance degradation due to irregular demand pat- terns. #e effectiveness of our proposed framework is validated with extensive trace-driven evaluations.

In large-scale peer-to-peer (P2P) live streaming systems with a limited supply of server bandwidth, increasing the amount of upload bandwidth supplied by peers becomes critically important to the "well being" of streaming sessions in live channels. Intuitively, two types of peers are preferred to be kept up in a live session: peers that contribute a higher percentage of their upload capacities, and peers that are stable for a long period of time. The fundamental challenge is to identify, and satisfy the needs of, these types of "superior" peers in a live session, and to achieve this goal with minimum disruption to the traditional pull-based protocols that real-world live streaming protocols use. In this paper, we conduct a comprehensive and in-depth statistical analysis based on more than 130 GB worth of runtime traces from hundreds of streaming channels in a large- scale real-world live streaming system, UUSee (among the top three commercial systems in popularity in mainland China). Our objective is to discover critical factors that may influence the longevity and bandwidth contribution ratio of peers, using survival analysis techniques such as the Cox proportional hazards model and the Mantel-Haenszel test. Once these influential factors are found, they can be used to form a superiority index to distill superior peers from the general peer population. The index can be used in any way to favor superior peers, and we simulate the use of a simple ranking mechanism in a natural selection algorithm to show the effectiveness of the index, based on a replay of real-world traces from UUSee.

Large-scale live peer-to-peer (P2P) streaming applications have been successfully deployed in today's Internet. While they can accommodate millions of users simultaneously with hundreds of channels of programming, there still commonly exist channels and times where and when the streaming quality is unsatisfactory. In this paper, based on more than two terabytes and one year worth of live traces from UUSee, a large-scale commercial P2P live streaming system, we show an in-depth network-wide diagnosis of streaming inefficiencies, commonly present in mesh-based P2P streaming systems. We first identify an evolutionary pattern of low streaming quality in the system and the distribution of streaming inefficiencies across various streaming channels. We then carry out an extensive investigation to explore the causes to such streaming inefficiencies over different times and across different channels at specific times. The original discoveries we have brought forward include the two-sided effects of peer population on the streaming quality in a channel, the significant impact of inter-peer bandwidth bottlenecks at peak times, and the inefficient utilization of server capacities across concurrent channels. We conclude with a number of suggestions to improve real-world large-scale P2P streaming.

Due to peer instability and time-varying peer upload bandwidth availability in live peer-to-peer (P2P) streaming channels, it is preferable to provision adequate levels of stable upload capacities at dedicated streaming servers, in order to guarantee the streaming quality in all channels. Most commercial P2P streaming systems have resorted to the practice of over-provisioning upload capacities on streaming servers. We have performed a detailed analysis on 400 GB and 7 months of run-time traces from UUSee, a commercial P2P streaming system, and observed that available capacities on streaming servers are not able to keep up with the increasing demand imposed by hundreds of channels. We propose a novel online server capacity provisioning algorithm that proactively adjusts the server capacities available to each of the concurrent channels, such that the supply of server bandwidth in each channel dynamically adapts to the forecasted demand, taking into account the number of peers, the streaming quality, and the priorities of channels. The algorithm is able to learn over time, and has full ISP awareness to maximally constrain P2P traffic within ISP boundaries. To evaluate the effectiveness of our solution, our experimental studies are based on an implementation of the algorithm with actual channels of P2P streaming traffic, with real-world traces replayed within a server cluster.

Real-world live peer-to-peer (P2P) streaming applications have been successfully deployed in the Internet, delivering live multimedia content to millions of users at any given time. With relative simplicity in design with respect to peer selection and topology construction protocols and without much algorithmic sophistication, current-generation live P2P streaming applications are able to provide users with adequately satisfying viewing experiences. That said, little existing research has provided sufficient insights on the time-varying internal characteristics of peer-to-peer topologies in live streaming. This article presents Magellan , our collaborative work with UUSee Inc., Beijing, China, for exploring and charting graph theoretical properties of practical P2P streaming topologies, gaining important insights in their topological dynamics over a long period of time. With more than 120 GB worth of traces starting September 2006 from a commercially deployed P2P live streaming system that represents UUSee's core product, we have completed a thorough and in-depth investigation of the topological properties in large-scale live P2P streaming, as well as their evolutionary behavior over time, for example, at different times of the day and in flash crowd scenarios. We seek to explore real-world P2P streaming topologies with respect to their graph theoretical metrics, such as the degree, clustering coefficient, and reciprocity. In addition, we compare our findings with results from existing studies on topological properties of P2P file sharing applications, and present new and unique observations specific to streaming. We have observed that live P2P streaming sessions demonstrate excellent scalability, a high level of reciprocity, a clustering phenomenon in each ISP, and a degree distribution that does not follow the power-law distribution.

Live peer-to-peer (P2P) streaming applications have been successfully deployed in the Internet. With relatively simple peer selection protocol design, modern live P2P streaming applications are able to provide millions of concurrent users adequately satisfying viewing experiences. That said, few existing research has provided sufficient insights on the time-varying internal characteristics of P2P topologies in live streaming. With 120 GB worth of traces in late 2006 from a commercial P2P live streaming system of UUSee Inc. in Beijing, this paper represents the first attempt in the research community to explore topological properties in practical P2P streaming, and how they behave over time. Starting from classical graph metrics, such as degree, clustering coefficient, and reciprocity, we explore and extend them in specific perspectives of streaming applications. We also compare our findings with existing insights from topological studies of P2P file sharing applications, which shed new and unique insights specific to streaming. Our characterization reveals the scalability of the commercial P2P streaming application even in case of large flash crowds, the clustering phenomenon of peers in each ISP, as well as the reciprocal behavior among peers, all of which play important roles in achieving its current success.

The fundamental advantage of peer-to-peer (P2P) multimedia streaming applications is to leverage peer upload capacities to minimize bandwidth costs on dedicated streaming servers. The available bandwidth among peers is of pivotal importance to P2P streaming applications, especially as the number of peers in the streaming session reaches a very large scale. In this paper, we utilize more than 230 GB of traces collected from a commercial P2P streaming system, UUSee, over a four-month period of time. With such traces, we seek to thoroughly understand and characterize the achievable bandwidth of streaming flows among peers in large-scale real-world P2P live streaming sessions, in order to derive useful insights towards the improvement of current-generation P2P streaming protocols, such as peer selection. Using continuous traces over a long period of time, we explore evolutionary properties of inter-peer bandwidth. Focusing on representative snapshots of the entire topology at specific times, we investigate distributions of inter-peer bandwidth in various peer ISP/area/type categories, and statistically test and model the deciding factors that cause the variance of such inter-peer bandwidth. Our original discoveries in this study include: (1) The ISPs that peers belong to are more correlated to inter-peer bandwidth than their geographic locations; (2) There exist excellent linear correlations between peer last-mile bandwidth availability and inter-peer bandwidth within the same ISP, and between a subset of ISPs as well; and (3) The evolution of inter-peer bandwidth between two ISPs exhibits daily variation patterns. Based on these insights, we design a throughput expectation index that facilitates high-bandwidth peer selection without performing any measurements.