No abstract

This paper presents an analytical (in contrast to commonlyused simulations) approach to program scheduling in near video-on-demand (NVoD) systems. NVoD servers batch customers' requests by sourcing the same mr$erial at certain intervals called phase offsets. The proposed approach to analytical modeling integrates both customers' and serviceprovider's views to account for the tradeoff between system throughput and customers' partial patience. We first determine the optimal scheduling of movies of different popularities for maximum throughput and the lowest average phase offset. Next, we deal with quasi video-on-demand (QVoD) systems, in which programs are scheduled based on a threshold on the number of pending requests. The throughput is found to be usually greater in QVoD than in NVoD, except for the extreme case of nonstationary request arrivals. This observation is then used to improve throughput without compromising customers' QoS in terms of average phase offset and the corresponding dispersion.Index Terms -Near video-on-demand (NVoD), quasi videoon-demand (QVoD), partially patient customers, batching, video server throughput.

No abstract

No abstract

This article reports on a set of projects to (i) design, implement, and evaluate software frameworks for providing performance assurances in emerging Internet services and real-time applications with a focus on multimedia; and (ii) design and evaluate video-on-demand (VoD) servers as an application. In the rst project we have taken a two-pronged approach to providing performance assurances. In the rst thrust, particular attention is given to new resource-management mechanisms at both OS and middleware layers for next-generation servers The second thrust deals with the problem of achieving reliable communication QoS guarantees. Together, the proposed techniques alleviate bottleneck resource congestion, exploit application-level semantics to adapt to load conditions, and reduce the cost and time of real-time software development by providing reusable multi-purpose real-time software components for achieving QoS guarantees. Section 2 describes the Adaptware project which investigates adaptive software for server platforms Section 3 presents a complementary project that addresses reliable transmission of QoS-sensitive data over packet-switched networks. Together, these two prongs compose an end-to-end approach to achieving exible QoS guarantees for future Internet applications. Finally, Section 4 presents VoD servers as a potential application of the above two-pronged approach.