ABSTRACT
This paper presents a two-stage edge scheduling framework that maps the tasks of a real-time artificial intelligence (AI) application across a collection of edge computing resources. The first stage is global and it creates schedules with execution slots for tasks with real-time constraints. The second stage is local and it uses the schedules from the first stage and places non real-time tasks in the free slots. By creating global schedules for time-critical tasks, the two-stage design allows a group of such tasks to run in a coordinated manner across edge computers while providing the local autonomy to execute other tasks according to a local schedule. We implemented the framework over a heterogeneous collection of machines and measured its performance under different conditions. Results show that the two-stage architecture is better because the flexibility offered by the architecture can be used by the edge servers to obtain higher overall performance (i.e., increase the batch and interactive execution rates or deadline compliance rates).
- K. Dolui and S. K. Datta, "Comparison of edge computing implementations: Fog computing, cloudlet and mobile edge computing," in 2017 Global Internet of Things Summit (GIoTS), 2017, pp. 1--6.Google Scholar
- W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge computing: Vision and challenges," IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637--646, 2016.Google ScholarCross Ref
- S. Deng, H. Zhao, W. Fang, J. Yin, S. Dustdar, and A. Y. Zomaya, "Edge intelligence: The confluence of edge computing and artificial intelligence," IEEE Internet of Things Journal, vol. 7, no. 8, pp. 7457--7469, 2020.Google ScholarCross Ref
- Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, and J. Zhang, "Edge intelligence: Paving the last mile of artificial intelligence with edge computing," IEEE, vol. 107, no. 8, pp. 1738--1762, 2019.Google ScholarCross Ref
- E. Peltonen, M. Bennis, M. Capobianco, M. Debbah, A. Ding, F. Gil-Castiñeira, M. Jurmu, T. Karvonen, M. Kelanti, A. Kliks et al., "6g white paper on edge intelligence," arXiv preprint arXiv:2004.14850, 2020.Google Scholar
- A. H. Lodhi, B. Akgün, and Ö. Özkasap, "State-of-the-art techniques in deep edge intelligence," arXiv preprint arXiv:2008.00824, 2020.Google Scholar
- L. U. Khan, I. Yaqoob, M. Imran, Z. Han, and C. S. Hong, "6g wireless systems: A vision, architectural elements, and future directions," IEEE Access, vol. 8, pp. 147 029--147 044, 2020.Google Scholar
- R. Shafin, L. Liu, V. Chandrasekhar, H. Chen, J. Reed, and J. C. Zhang, "Artificial intelligence-enabled cellular networks: A critical path to beyond-5g and 6g," IEEE Wireless Communications, vol. 27, no. 2, pp. 212--217, 2020.Google ScholarCross Ref
- Y. Liu, M. Peng, G. Shou, Y. Chen, and S. Chen, "Toward edge intelligence: Multiaccess edge computing for 5g and internet of things," IEEE Internet of Things Journal, vol. 7, no. 8, pp. 6722--6747, 2020.Google ScholarCross Ref
- S. Raileanu, T. Borangiu, O. Morariu, and I. Iacob, "Edge computing in industrial iot framework for cloud-based manufacturing control," in 2018 22nd International Conference on System Theory, Control and Computing (ICSTCC), 2018, pp. 261--266.Google Scholar
- O. Fadahunsi and M. Maheswaran, "Locality sensitive request distribution for fog and cloud servers," Service Oriented Computing and Applications, pp. 1--14, 2019.Google Scholar
- D. Isovic and G. Fohler, "Handling mixed sets of tasks in combined offline and online scheduled real-time systems," Real-time systems, vol. 43, no. 3, pp. 296--325, 2009.Google ScholarDigital Library
- H. Tang, P. Ramanathan, and K. Morrow, "Inserting placeholder slack to improve run-time scheduling of non-preemptible real-time tasks in heterogeneous systems," in 2014 27th International Conference on VLSI Design and 2014 13th International Conference on Embedded Systems, 2014, pp. 168--173.Google Scholar
- H. Tang, P. Ramanathan, and K. Compton, "Combining hard periodic and soft aperiodic real-time task scheduling on heterogeneous compute resources," in 2011 International Conference on Parallel Processing, 2011, pp. 753--762.Google Scholar
- W. Jeon, W. Kim, H. Lee, and C. Lee, "Online slack-stealing scheduling with modified laedf in real-time systems," Electronics, vol. 8, no. 11, p. 1286, 2019.Google ScholarCross Ref
- H. Chu and K. Nahrstedt, "Cpu service classes for multimedia applications," in IEEE International Conference on Multimedia Computing and Systems, vol. 1. IEEE, 1999, pp. 296--301.Google Scholar
- B. Lin and P. Dinda, "Vsched: Mixing batch and interactive virtual machines using periodic real-time scheduling," in SC'05: 2005 ACM/IEEE conference on Supercomputing. IEEE, 2005, pp. 1--8.Google Scholar
- T. Yang, T. Liu, E. Berger, S. Kaplan, and J. Moss, "Redline: First class support for interactivity in commodity operating systems." in OSDI, vol. 8, 2008, pp. 73--86.Google Scholar
- W. Zhao, K. Ramamritham, and J. Stankovic, "Scheduling tasks with resource requirements in hard real-time systems," IEEE transactions on software engineering, no. 5, pp. 564--577, 1987.Google Scholar
- C. Shen, O. Gonzalez, K. Ramamritham, and I. Mizunuma, "User level scheduling of communicating real-time tasks." in IEEE Real Time Technology and Applications Symposium, 1999, pp. 164--175.Google Scholar
- S. El Zaatari, M. Marei, W. Li, and Z. Usman, "Cobot programming for collaborative industrial tasks: An overview," Robotics and Autonomous Systems, vol. 116, pp. 162--180, 2019.Google ScholarDigital Library
- K. Jeffay, D. F. Stanat, and C. U. Martel, "On non-preemptive scheduling of period and sporadic tasks," in [1991] Twelfth Real-Time Systems Symposium, 1991, pp. 129--139.Google ScholarCross Ref
- F. Cottet, J. Delacroix, Z. Mammeri, and C. Kaiser, Scheduling in real-time systems. Wiley Online Library, 2002.Google ScholarCross Ref
- M. Nasri, S. Baruah, G. Fohler, and M. Kargahi, "On the optimality of rm and edf for non-preemptive real-time harmonic tasks," in 22nd International Conference on Real-Time Networks and Systems, ser. RTNS '14. New York, NY, USA: Association for Computing Machinery, 2014, p. 331--340.Google ScholarDigital Library
Index Terms
- Edge scheduling framework for real-time and non real-time tasks
Recommendations
Real-time edge framework (RTEF): task scheduling and realisation
AbstractWith the big success of the Cloud Computing, or the Cloud, new research areas appeared. Edge Computing (EC) is one of the recent paradigms that is expected to overcome the Quality of Service (QoS) and latency issues caused by the best-effort ...
Preference-oriented fixed-priority scheduling for periodic real-time tasks
A preference priority assignment (PPA) scheme that explicitly incorporates the ASAP and ALAP execution preferences of periodic real-time tasks is proposed.An online dual-queue based preference-oriented fixed- priority (POFP) scheduler is proposed 4, ...
Dynamic Scheduling of Hard Real-Time Tasks and Real-Time Threads
The authors investigate the dynamic scheduling of tasks with well-defined timing constraints. They present a dynamic uniprocessor scheduling algorithm with an O(n log n) worst-case complexity. The preemptive scheduling performed by the algorithm is ...
Comments