對於影片傳送服務而言，高度的服務需求使得系統生產力(system capacity)成為最重要的問題之一。有效率地服務或資源分配(resource allocation)扮演影響系統生產力的一個關鍵因素，協調使用者的需求以及服務供應是達成有效率的資源分配一個有效的方式。此篇論文提出了一個協調式資源分配方法(Coordinated Resource Allocation)，簡稱COCA，用來協調對系統造成較高工作負擔(workload)的使用者。COCA使得對系統造成較高工作負擔的請求(request)等待一段特定時間後能保證得到頻道(channel)的存取權，藉由延遲部分的請求讓排班者(scheduler)轉移工作負擔到非尖峰時段。此工作負擔的轉移減少了高工作負擔時請求的被違背頻率(renege rate)，而且在低工作負擔時增加了資源的利用率。本論文也介紹了基於COCA方法實做的一個協調式排班系統(Cooperated Scheduler)，簡稱CoS。CoS包含了四個主要的軟體元件：協調式的排班引擎(Coordinated Scheduling Engine)、資源需求評估者(Resource Need Evaluator)、服務截止時間指定人(Deadline Assigner)以及頻道分配預估者(Channel Allocation Predictor)。此篇論文評估四個排班演算法：憑藉需求(On-Demand)演算法、單純的頻率控制(Pure Rate Control)演算法、以及COCA方式應用於此兩種策略的演算法。實驗結果顯示COCA可以有效地減少需求的違背頻率而且不需要進行排班最佳化的工作。

For the video delivery services, system capacity is one of important issues because of high resource need, especially during heavier workload. Efficiency of service or resource allocation plays key factor of system's capacity. Coordinating user demands and service supplies is an effective method for efficient resource allocation. This thesis proposed a Coordinated Channel Allocation (COCA) strategy to negotiate with the users who bring higher workload. COCA makes the heavier workload requests wait for a specific duration with access promising after waiting. By delaying partial requests, COCA scheduler shifts the workload to non-peak period. The shift in workload reduces the renege rate during heavier workload,
and improves the utilization during low workload. The Cooperated Scheduler (CoS) comprises four major components: 1) Coordinated Scheduling Engine, 2) Resource Requirement Evaluator, 3) Deadline Assigner, 4) Channel Allocation Predictor. The experiments are provided to evaluate performance of following four algorithms: On-demand, PRC, enhanced On-Demand with COCA strategy, enhanced PRC with COCA strategy. The experiment results show that COCA is effective for decreasing the
renege rate without reducing scheduling optimization.

[1] K. Miyashita, K. Masuda, and F. Higashitani, "Coordinated service allocation through flexible reservation," IEEE Transactions on Services Computing, vol. 1, no. 2, pp. 117-128, April-June
2008.

[2] A. Dan, D. Sitaram, and P. Shahabuddin, "Scheduling policies for an on-demand video server with batching," Proceedings of the second ACM international conference on Multimedia, pp. 15-23, October 1994.

[3] T. D. C. Little and D. Venkatesh, "Prospects for interactive video-on-demand," IEEE Multimedia, vol. 1, no. 3, pp. 14-24, September 1994.

[4] G. K. Zipf, Human behavior and the principle of least effort: An introduction to human ecology. Hafner Pub. Co, 1972.

[5] A. Dan, D. Sitaram, and P. Shahabuddin, "Dynamic batching policies for an on-demand video server," Multimedia Systems, vol. 4, no. 3, pp. 112-121, June 1996.

[6] M.-Y. Wu, S.-J. Ma, and W. Shu, "Scheduled video delivery for scalable on-demand service," Proceedings of the 12th international workshop on Network and operating systems support for digital audio and video, pp. 167-175, May 2002.

[7] K. C. Almeroth, "Adaptive workload-dependent scheduling for large-scale content delivery systems,"
IEEE Transactions on Circuits and Systems for Video Technology, vol. 11, no. 3, pp. 426-439, March 2001.

[8] K. C. Almeroth, A. Dan, D. Sitaram, and W. H. Tetzlaff, "Long term resource allocation in video
delivery systems," INFOCOM 1997, pp. 1333-1340, April 1997.

[9] Y. Zhang, M.-Y. Wu, and W. Shu, "Adaptive channel allocation for large-scale streaming content delivery systems," Multimedia Tools and Applications, vol. 32, no. 3, pp. 253-273, March 2007.

10] J. Yan, R. Kowalczyk, J. Lin, M. B. Chhetri, S. K. Goh, and J. Zhang, "Autonomous service level agreement negotiation for service composition provision," Future Generation Computer Systems, vol. 23, no. 6, pp. 748-759, July 2007.