1. Latest Techniques in Real Time Scheduling Srikanth Pathuri

2. Outline A quick recap Latest Techniques Applications Future Works

3. A Quick Recap …. What is Real Time scheduling? Hard Real Time Systems Soft Real Time Systems Firm Real Time Systems Real Time Tasks Periodic Tasks Aperiodic Tasks

4. A Quick Recap …. Real Time Scheduling algorithms Rate Monotonic Deadline Monotonic Earliest Deadline First Issues Encountered during Real Time Scheduling Priority Inversion Chain Blocking Priority Ceiling Protocol(PCP) Priority Inheritance Protocol(PIP)

5. Latest Techniques Self Adaptable & Self Healing Efficient schedulers over Wireless networks Energy Efficient schedulers Note : This list is not exhaustive.

6. Self-Healing Distributed Scheduling Platform Proposed recently @ CCGrid (2011) Distributed systems require effective mechanisms to manage the reliable provisioning of computational resources from different and distributed providers. The proposed self-adaptive distributed scheduling platform is composed of multiple agents implemented as intelligent feedback control loops to support policy-based scheduling and expose self-healing capabilities.

7. Self-Healing Distributed Scheduling Platform This platform leverages distributed scheduling processes by (i) allowing each provider to maintain its own internal scheduling process (ii) implementing self-healing capabilities based on agent modules recovery. Results of several tests on a real-life platform are simulated to evaluate recovery times and optimize platform parameters.

8. Adaptive Real time Distributed Scheduling This technique was again proposed recently this year as an IEEE paper. This is an adaptive real-time-service-based distributed scheduling scheme (RTDS) for wireless network system with the Non-Transparent RS architecture which is specified in the IEEE 802.16j standard. The main object of this technique is to utilize the RS to decrease the overhead of the BS and enhance the QoS of the real time service connections.

9. Adaptive Real time Distributed Scheduling We obtain the initial priority value for the order of scheduling through the quantification of each service type specified in IEEE 802.16 standard. The priority value varies according to the bandwidth request and the channel status of each connection, and it may be increased by a emergency packet event or decreased by taking fairness into consideration. The simulation results show that this proposed scheduling scheme performs better than other representative researches and also additionally guarantees the QoS of real time service connections.

10. Energy Efficient Real time Scheduling algorithms Energy Efficient Real-Time Scheduling Year – 2001 Introduced Variable Voltage Processing Based on the Earliest Deadline First algorithm Considered historical processor utilization in order to adjust voltage on processor to meet real-time deadlines Called Slacked EDF Energy Savings of 53%

11. Energy Efficient Real time Scheduling algorithms Dynamic Voltage and Frequency Scaling for RT Scheduling on Prioritized SMT Processor Year - 2011 Introduced Task Migration across processors Utilized system heuristics to determine voltage and frequency Algorithm: Reduces power consumption up to 30%

12. Energy Efficient Real time Scheduling algorithms 20 Global EDF-based Energy Efficient Real-Time Scheduling in Multicore Platforms Most Real-time algorithms assume Worst Case Execution Time (WCET) Proposed Average Case with “Slack Time” Algorithm: Uses slack time to adjust frequency of processor during off-peak usage Energy savings ~10%

13. Applications Applications of Real time scheduling: Air Traffic Controller Robotics Air craft Systems Turbulent Manufacturing Environments Note: This list is again not exhaustive.

14. Future Work NP – Complete But Some factors to be considered when designing a real time scheduling algorithm Performance Time Complexity Scalability Applicability

15. Thank You and…

16. References 1. Randy Chow, Theodore Johnson, “Distributed Operating Systems & Algorithms”, Addison Wesley, pp.156-163. 2. Yu-Kwong Kwok, Ishfaq Ahmad; Static scheduling algorithms for allocating directed task graphs to multiprocessors; ACM Computing Surveys; December 1999 3. Sachi Gupta, Gaurav Agarwal, Vikas Kumar “Task Scheduling in Multiprocessor System Using Genetic Algorithm”,10.1109/ICMLC.2010.50 4. Hongze Qiu, Wanli Zhou, Hailong Wang. “A Genetic Algorithm-based Approach to Flexible Job-shop Scheduling Problem”. DOI 10.1109/ICNC.2009.609 5. Xueyan Tang & Samuel T. Chanson. “ Optimizing Static Job Scheduling in a Network of Heterogeneous Computers”. pp 373- 382, icpp, IEEE 2000

17. References 1. L. Northrop, P. Feiler, R. Gabriel, J. Goodenough,T. Longstaff, R. Kazman, M. Klein, D. Schmidt, K. Sullivan, and K. Wallnau, “Ultra-large-scale systems—The softwarechallenge of the future,” Carnegie Mellon University Software Engineering Institute, Tech. Rep., 2006. [Online]. Available:http://www.sei.cmu.edu/uls 2. N. M. Villegas and H. A. M¨uller, “Managing dynamic contextto optimize smart interactions and services,” ser. LNCS, vol.6400. Springer, 2010, pp. 289–318. 3. D. Thain, T. Tannenbaum, and M. Livny, “Distributed computingin practice: the condor experience.” Concurrency -Practice and Experience, vol. 17, no. 2-4, pp. 323–356, 2005. 4. I. T. Foster, “Globus toolkit version 4: Software for serviceoriented systems.” in NPC, ser. LNCS, H. Jin, D. A. Reed,and W. Jiang, Eds., vol. 3779. Springer, 2005, pp. 2–13.

18. References 1. S. J. Chapin, D. Katramatos, J. Karpovich, and A. Grimshaw,“Resource management in legion,” Future Generation ComputerSystems, vol. 15, no. 5, pp. 583–594, 1999. 2. H. Casanova and J. Dongarra, “Netsolve: A network serverfor solving computational science problems,” Intl. Journal of Supercomputing Applications and High Performance Computing,vol. 11, no. 3, pp. 212–223, 1997. 3. M. Wooldridge, “Inteligent agents,” in Multiagent Systems:A modern Approach to Distributed Artificial Inteligence,G. Weiss, Ed. MIT Press, 1999, pp. 27–77. 4. W. Shen, Y. Li, H. Genniwa, and C. Wang, “Adaptive negotiationfor agent-based grid computing,” in Proceedings of the Agentcities/AAMAS’02, 2002, pp. 32–36.

19. References 1. D. Ouelhadj, J. M. Garibaldi, J. MacLaren, R. Sakellariou,and K. Krishnakumar, “A multi-agent infrastructure and a service level agreement negotiation protocol for robust scheduling in grid computing,” in EGC, 2005, pp. 651–660. 2. J. Sauer, T. Freese, and T. Teschke, “Towards agent-based multi-site scheduling,” in Proceedings of the ECAI 2000 Workshop on New Results in Planning, Scheduling, and Design, Berlin, 2000, pp. 123–130. [Online]. Available:citeseer.ist.psu.edu/sauer00towards.html