1. Congestion Control in Wireless Flow-Aware Networks Jerzy Dom˙zał, Member, IEEE Nirwan Ansari, Fellow, IEEE Andrzej Jajszczyk, Fellow, IEEE Dept. of Telecommun., AGH Univ. of Sci. & Technol., Krakow, Poland 2011 IEEE International Conference on Communications (ICC)

2. I. Introduction II. Flow-aware networks III. Wireless transmission in Fan IV. Congestion control in FAN V. Simulation analysis VI. Conclusion Outline

3. I. Introduction II. Flow-aware networks III. Wireless transmission in Fan IV. Congestion control in FAN V. Simulation analysis VI. Conclusion I. Introduction

4. I. Introduction(cont.) Existing solutionsRAMAF For wired networkFor wired-wireless network HomogeneityHeterogeneity In the congestion-less state : Real-time In the congestion-less state : Real-time In the congestion state : Not Real-time In the congestion state : Real-time

5. I. Introduction II. Flow-aware networks III. Wireless transmission in Fan IV. Congestion control in FAN V. Simulation analysis VI. Conclusion II. Flow-aware networks

6. II. Flow-aware networks(cont.) Goal: To achieve efficient packet transmission with the minimal knowledge of the network. Traffic Streamingusually used by real-time applications Elasticcarries best effort traffic

7. II. Flow-aware networks(cont.)

8. the cross-protect routers (also denoted as XP’s) composed of two blocks, the admission control (AC) and the scheduler.

9. II. Flow-aware networks(cont.) makes decisions of accepting or rejecting packets

10. II. Flow-aware networks(cont.)

11. In the congestion-less state ID 1

12. II. Flow-aware networks(cont.) In the congestion-less state ID 2 ID 1 ID 2 ID 1

13. II. Flow-aware networks(cont.) In the congestion-less state ID 3 ID 1 ID 2 ID 3 ID 1 ID 2

14. II. Flow-aware networks(cont.) In the congestion-less state ID 1 ID 2 ID 3 ID 4 … ID n ID 1 ID 2 ID 4 ID n Pfl_flow_timeout time

15. II. Flow-aware networks(cont.) In the congestion-less state ID 1 ID 2 ID 4 … ID n

16. II. Flow-aware networks(cont.) fair_rate || priority_load > certain threshold ID 1 ID 2 ID 4 … ID n

17. II. Flow-aware networks(cont.) In the congestion state ID 1 ID 2 ID 4 … ID n

18. II. Flow-aware networks(cont.) ID 1 ID 2 ID 4 … ID n In the congestion state

19. II. Flow-aware networks(cont.) ID 2 ID 1 ID 2 ID 4 … ID n In the congestion state

20. II. Flow-aware networks(cont.) ID 3 ID 1 ID 2 ID 4 … ID n In the congestion state

21. II. Flow-aware networks(cont.) scheduling algorithms were proposed for FAN –PFQ (Priority Fair Queuing) –PDRR (Priority Deficit Round Robin)

22. I. Introduction II. Flow-aware networks III. Wireless transmission in FAN IV. Congestion control in FAN V. Simulation analysis VI. Conclusion III. Wireless transmission in FAN

23. III. Wireless transmission in FAN(cont.) Wireline transmission in FAN has been reported in the literature. QoS aspects as well as reliability of transmission in FAN are analyzed. However, FAN with respect to wireless transmission has not been reported.

24. III. Wireless transmission in FAN(cont.) its inability to distinguish the cause of a packet loss. Thus, the implementation of a more effective fast recovery algorithm is not possible. TCP New Reno Based on this information, the sender may immediately send the lost packets again. TCP Sack has similar drawbacks as those of TCP NewReno. TCP Sack When Tahoe detects a congestion, it reduces congestion window to the maximum segment size, and activates the slow-start phase TCP Tahoe This version of TCP also does not consider what causes the packet losses. TCP Westwood TCP Vegas tries to use the available capacity without causing congestions. Unfortunately, the cause of the congestion is not analyzed, either. TCP Vegas the performance in the heterogeneous networks is improved by modifying the inaccurate bandwidth estimation caused by the ACK burstiness. TCP New Jersey

25. I. Introduction II. Flow-aware networks III. Wireless transmission in Fan IV. Congestion control in FAN V. Simulation analysis VI. Conclusion IV. Congestion control in FAN

26. IV. Congestion control in FAN(cont.) EFM (Enhanced Flushing Mechanism) The ids of all elastic flows are periodically removed from PFL if the outgoing link is congested. RAEF (Remove Active Elastic Flows) Removes the ids of flows which are active for time equal or greater than the value given by the active time parameter. RBAEF (Remove and Block Active Elastic Flows) The ids removed from PFL are added to the blocked flow list for a short time. RPAEF (Remove and Prioritize in access Active Elastic Flows) The ids removed from PFL are added to the priority in access flow list for a short time.

27. IV. Congestion control in FAN(cont.)

30. I. Introduction II. Flow-aware networks III. Wireless transmission in Fan IV. Congestion control in FAN V. Simulation analysis VI. Conclusion V. Simulation analysis

31. V. Simulation analysis(cont.)

32. 1 Gbit/s capacity FAN routers 100 Mbit/s capacity 1 Gbit/s capacity 5 Mbit/s capacity

33. V. Simulation analysis(cont.)

35. I. Introduction II. Flow-aware networks III. Wireless transmission in Fan IV. Congestion control in FAN V. Simulation analysis VI. Conclusion

36. VI. Conclusion(cont.) The paper presents the feasibility of realizing the wireless transmission in FAN, and proposes a new congestion control mechanism to improve the transmission of streaming flows. Goal –To analyze wireless transmission in FAN –To present the new congestion control mechanism for FAN, called RAMAF.

37. 縮寫英文說法拉丁原文 i.e.that isid est e.g.for exampleexempli gratia etc.and so forth/and the nextet cetera p.page pp.pages Weekly sentence Four congestion control mechanisms have been proposed for FAN [9], i.e., EFM (Enhanced Flushing Mechanism), RAEF (Remove Active Elastic Flows), RBAEF (Remove and Block Active Elastic Flows), and RPAEF (Remove and Prioritize in access Active Elastic Flows).