工作流已廣泛應用於科學運算領域，衍生出大量探討排程策略之文獻。然而，現有研究多假設工作流中各任務的執行時間為固定值，未考慮實際運行環境中可能出現的變異性。實際上，任務執行時間可能受到硬碟 I/O、網路傳輸延遲等因素影響，產生不確定性，進而對排程結果造成影響。
本研究旨在設計並實作一套支援不確定性任務執行時間的工作流排程模擬器，提供研究者一個可重現、具彈性且可擴充的模擬環境，以分析各種排程演算法在面對執行時間變異時的效能與穩定性。與傳統模擬器多假設任務執行時間為固定值不同，本系統允許使用者為每個任務自訂其執行時間的期望值與標準差，進而模擬實際運行中可能出現的不確定行為。

Workflow applications are widely used in scientific computing, leading to extensive research on scheduling strategies. However, most existing studies assume that the execution time of each task within a workflow is fixed, without considering the variability that may occur in real execution environments. In reality, task execution times may be affected by factors such as disk I/O and network transmission delays, resulting in uncertainty that can impact scheduling outcomes.
This study aims to design and implement a workflow scheduling simulator that supports uncertain task execution times. The simulator provides researchers with a reproducible, flexible, and extensible environment for analyzing the performance and stability of various scheduling algorithms under execution time variability. Unlike traditional simulators, which often assume fixed execution times for tasks, the proposed system allows users to specify both the expected value and standard deviation for each task's execution time, thereby simulating the uncertainty that may arise in real-world execution.

[1] Alex Abramovici, William E Althouse, Ronald WP Drever, Yekta Gürsel, Seiji Kawamura, Frederick J Raab, David Shoemaker, Lisa Sievers, Robert E Spero, Kip S Thorne, et al. Ligo: The laser interferometer gravitational-wave observatory. science, 256(5055):325–333, 1992.
[2] Thomas L Adam, K. Mani Chandy, and JR Dickson. A comparison of list schedules for parallel processing systems. Communications of the ACM, 17(12):685–690, 1974.
[3] G Bruce Berriman, Ewa Deelman, John C Good, Joseph C Jacob, Daniel S Katz, Carl Kesselman, Anastasia C Laity, Thomas A Prince, Gurmeet Singh, and Mei-Hu Su. Montage: a grid-enabled engine for delivering custom science-grade mosaics on demand. In Optimizing scientific return for astronomy through information technologies, volume 5493, pages 221–232. SPIE, 2004.
[4] Shishir Bharathi, Ann Chervenak, Ewa Deelman, Gaurang Mehta, Mei-Hui Su, and Karan Vahi. Characterization of scientific workflows. In 2008 third workshop on workflows in support of large-scale science, pages 1–10. IEEE, 2008.
[5] Duncan A Brown, Patrick R Brady, Alexander Dietz, Junwei Cao, Ben Johnson, and John McNabb. A case study on the use of workflow technologies for scientific analysis: Gravitational wave data analysis. Workflows for e-Science: Scientific workflows for grids, pages 39–59, 2007.
[6] Marc Bux and Ulf Leser. Dynamiccloudsim: Simulating heterogeneity in computational clouds. In Proceedings of the 2nd acm sigmod workshop on scalable workflow execution engines and technologies, pages 1–12, 2013.
[7] Rodrigo N Calheiros, Rajiv Ranjan, Anton Beloglazov, César AF De Rose, and Rajkumar Buyya. Cloudsim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Software: Practice and experience, 41(1):23–50, 2011.
[8] Weiwei Chen and Ewa Deelman. Workflowsim: A toolkit for simulating scientific workflows in distributed environments. In 2012 IEEE 8th international conference on E-science, pages 1–8. IEEE, 2012.
[9] Robert P Goldberg. Architecture of virtual machines. In Proceedings of the workshop on virtual computer systems, pages 74–112, 1973.
[10] Robert P Goldberg. Survey of virtual machine research. Computer, 7(6):34–45, 1974.
[11] Trevor Grant, Holden Karau, Boris Lublinsky, Richard Liu, and Ilan Filonenko. Kubeflow for machine learning. ” O’Reilly Media, Inc.”, 2020.
[12] Harshit Gupta, Amir Vahid Dastjerdi, Soumya K Ghosh, and Rajkumar Buyya. ifogsim: A toolkit for modeling and simulation of resource management techniques in the inter33 net of things, edge and fog computing environments. Software: Practice and Experience, 47(9):1275–1296, 2017.
[13] Bas P Harenslak and Julian De Ruiter. Data pipelines with apache airflow. Simon and Schuster, 2021.
[14] Tsung-Wei Huang, Dian-Lun Lin, Chun-Xun Lin, and Yibo Lin. Taskflow: A lightweight parallel and heterogeneous task graph computing system. IEEE Transactions on Parallel and Distributed Systems, 33(6):1303–1320, 2021.
[15] Jing-Jang Hwang, Yuan-Chieh Chow, Frank D Anger, and Chung-Yee Lee. Scheduling precedence graphs in systems with interprocessor communication times. siam journal on computing, 18(2):244–257, 1989.
[16] Alexandru Iosup, Ozan Sonmez, and Dick Epema. Dgsim: Comparing grid resource management architectures through trace-based simulation. In Euro-Par 2008–Parallel Processing: 14th International Euro-Par Conference, Las Palmas de Gran Canaria, Spain, August 26-29, 2008. Proceedings 14, pages 13–25. Springer, 2008.
[17] Gideon Juve, Ann Chervenak, Ewa Deelman, Shishir Bharathi, Gaurang Mehta, and Karan Vahi. Characterizing and profiling scientific workflows. Future generation computer systems, 29(3):682–692, 2013.
[18] Yu-Kwong Kwok and Ishfaq Ahmad. Static scheduling algorithms for allocating directed task graphs to multiprocessors. ACM Computing Surveys (CSUR), 31(4):406– 471, 1999.
[19] Xiao Liu, Lingmin Fan, Jia Xu, Xuejun Li, Lina Gong, John Grundy, and Yun Yang. Fogworkflowsim: An automated simulation toolkit for workflow performance evaluation in fog computing. In 2019 34th IEEE/ACM International Conference on Automated Software Engineering (ASE), pages 1114–1117. IEEE, 2019.
[20] Jonathan Livny, Hidayat Teonadi, Miron Livny, and Matthew K Waldor. Highthroughput, kingdom-wide prediction and annotation of bacterial non-coding rnas. PloS one, 3(9):e3197, 2008.
[21] Philip Maechling, Ewa Deelman, Li Zhao, Robert Graves, Gaurang Mehta, Nitin Gupta, John Mehringer, Carl Kesselman, Scott Callaghan, David Okaya, et al. Scec cybershake workflows—automating probabilistic seismic hazard analysis calculations. Workflows for e-Science: scientific workflows for grids, pages 143–163, 2007.
[22] Peter Mell, Tim Grance, et al. The nist definition of cloud computing. 2011.
[23] Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, et al. Ray: A distributed framework for emerging {AI} applications. In 13th USENIX symposium on operating systems design and implementation (OSDI 18), pages 561–577, 2018.
[24] Hernan Picatto, Georg Heiler, and Peter Klimek. Cost-effective big data orchestration using dagster: A multi-platform approach. arXiv preprint arXiv:2408.11635, 2024.
[25] Rami Rosen. Resource management: Linux kernel namespaces and cgroups. Haifux, May, 186:70, 2013.
[26] Jacopo Tagliabue, Hugo Bowne-Anderson, Ville Tuulos, Savin Goyal, Romain Cledat, and David Berg. Reasonable scale machine learning with open-source metaflow. arXiv preprint arXiv:2303.11761, 2023.
[27] James Turnbull. The Docker Book: Containerization is the new virtualization. James Turnbull, 2014.
[28] Laurens Versluis, Roland Mathá, Sacheendra Talluri, Tim Hegeman, Radu Prodan, Ewa Deelman, and Alexandru Iosup. The workflow trace archive: Open-access data from public and private computing infrastructures. IEEE Transactions on Parallel and Distributed Systems, 31(9):2170–2184, 2020.