聯合雲上數據供應鏈的工作流部署機制

工作流技術起源於二十世紀七十年代中期辦公自動化領域的研究，雖然剛開始研究者普遍相信此技術可以帶來辦公效率的巨大改善，然而這種期望最終還是落空了。因為工作流技術的引入使得人們只能死板的遵守固定的流程，最終導致辦公效率低和人們對技術的反感。直到進入九十年代後，隨著個人電腦，網路技術和傳播的推廣，以及日益增長的信息技術提高，使得工作流技術的研發進入了新的繁榮期。在現今的企業裡，每個人都想要去提升企業內部的效率，比如說提高生產量，增加機器能同時處理的量以及降低所消耗的成本等等。在本文中我們考慮工作流遇到數據供應鏈限制時的情況，數據供應的佈局與工作流分配的問題。我們制定了一個數學優化問題，最大化可接受的需求量，並最大限度地降低服務部署的消耗成本。本論文所研究的是在遇到多種不一樣的需求時，並且不同的需求也都具有不同的數據供應鏈限制。該如何去分配現有的資源，使得資源成本不會有過多的浪費，且能達到客戶所提出的需求。透過運用啟發式演算法解出的結果，本研究得知如果放置的服務需求流量都相同的情況下，先放置所需成本較大的路徑在網路圖裡，其最後的建置總成本將會是最少的，而如果遇到放置的服務需求流量不同的情況，先放置成本較小的路徑在網路圖中，其最後的建置總成本也將會是最少的，並且考慮了開啟一段時間的情況下，將垂直鏈路中成本最少的鏈路持續開啟，最後所消耗的總成本為最少的。

關鍵字

數據供應鏈；服務品質；工作流部署；資源管理；數位經濟

並列摘要

Workflow technology originated from the field of office automation in the mid-1970s. Although researchers have generally believed that this technology can bring about tremendous improvements in office efficiency, this expectance finally falls. The introduction of workflow technology makes people rigidly follow the fixed process, which leads to low office efficiency and causes people dislike the technology. Until the 1990s, with the promotion of personal computers, network technology, transmission, and the increasing information technology, the development of workflow technology has entered a new period of prosperity. In current enterprise, everyone wants to improve the efficiency of the company, such as increasing production, promoting the amount of machine that can process at the same time and reducing the cost. In this paper, we consider the situation when the workflow encounters data supply chain constraints, the layout of the data supply, and the problem of workflow allocation. We develop a mathematical optimization problem that maximizes acceptable demand and minimizes the cost of service deployment. In this paper, we study when facing with a variety of different needs, and different needs also have different data supply chain constraints. How to allocate existing resources, so that the cost of resources will not be too wasteful, and can meet the needs of customers. Through the use of heuristic algorithm to solve the results, this study knows that if the service demand flow is the same, first place the path with the higher cost in the network diagram, and the final total cost of construction will be It will be the least, and if there is a situation where the service demand flow is different, first place the less cost path in the network diagram, and the total cost of the final construction will be the least, and consider opening a section. In the case of time, the least cost link in the vertical link is continuously turned on, and the total cost consumed is the least.

並列關鍵字

Data supply chain ； Quality of service ； Workflow deployment ； Resource management ； Digital economy

參考文獻

Buyya, R., Ranjan, R., & Calheiros, R. N. (2010, May). Intercloud: Utility-oriented federation of cloud computing environments for scaling of application services. In International Conference on Algorithms and Architectures for Parallel Processing (pp. 13-31). Springer, Berlin, Heidelberg.

Google Scholar

Cao, Z., Kodialam, M., & Lakshman, T. V. (2014, August). Traffic steering in software defined networks: planning and online routing. In ACM SIGCOMM Computer Communication Review (Vol. 44, No. 4, pp. 65-70). ACM.

Google Scholar

Celesti, A., Tusa, F., Villari, M., & Puliafito, A. (2010, July). How to enhance cloud architectures to enable cross-federation. In 2010 IEEE 3rd international conference on cloud computing (pp. 337-345). IEEE.

Google Scholar

Charikar, M., Naamad, Y., Rexford, J., & Zou, X. K. (2018, August). Multi-commodity flow with in-network processing. In International Symposium on Algorithmic Aspects of Cloud Computing (pp. 73-101). Springer, Cham.

Google Scholar

Chen, W., & Deelman, E. (2012, May). Integration of workflow partitioning and resource provisioning. In 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012) (pp. 764-768). IEEE.

Google Scholar

國際替代計量

聯合雲上數據供應鏈的工作流部署機制

不提供下載

主題瀏覽