دانلود رایگان مقاله الگوریتم های زمان بندی پیشرفت رزرو برای شبکه تولید رسانه ای

Abstract

In the media production process a substrate network can be shared by many users simultaneously when different media actors are geographically distributed. This allows sophisticated media productions involving numerous producers to be concurrently created and transferred. Due to the predictable nature of media transfers, the collaboration among different actors could be significantly improved by deploying an efficient advance reservation system. In this paper, we propose a model for the advance bandwidth reservation problem, which takes the specific characteristics of media production networks into account. Flexible and time variable bandwidth reservations, meeting delivery deadlines, supporting splittable flows and interdependent transfers and all types of advance reservation requests imposed by the media production transfers are incorporated into this model. In addition to the optimal scheduling algorithms, which are presented based on this model, near optimal alternatives are also proposed. The experimental results show that the proposed algorithms are scalable in terms of physical topology and granularity of time intervals and obtain a satisfactory performance, executing significantly faster than an optimal algorithm and within 8.78% of the optimal results.

7. Conclusion

In this article, an optimal model and a set of novel scheduling algorithms were presented for advance bandwidth reservation in media production networks. Specifically the SPB approach is proposed to resolve the computational complexity associated with the optimal solutions. The bandwidth scheduling algorithms take the specific characteristics of media production processes into account, for example time-variable bandwidth reservation, flexible start times, request dependencies and splittable flows. In our approaches all four types of advance reservation requests are supported. Furthermore, the proposed algorithms operate in both offline and online manners. A detailed performance analysis is conducted to assess the viability of ILP-based and SPB solutions. The influence of the available bandwidth, the percentage of requests known in advance, the network load, the time granularity and the execution time have been evaluated. Our evaluation showed that the SPB results at least within 8.78% of the optimal admittance rate. Also, when a significant portion of requests is known in advance, AR significantly increases bandwidth ef- ficiency and request admittance. Concretely, in case all requests are known beforehand, request admittance of the optimal and heuristic solutions can be increased up to 5.22% and 5.7%, respectively. In addition, the results showed that time granularity increases algorithm accuracy and optimality in terms of request admittance. SPB can achieve higher scalability in terms of the size of physical network as well as time slot sizes. The size of time intervals can be fine-grained up to 1 min. Comparing to the ILP-based approaches, the SPB algorithms offer lower operational overhead in terms of problem complexity and execution time. Future work includes determining the impact on quality and performance of variable time intervals, and adding resilience to improve the robustness of the schedules generated by the advance reservation system.