Top Banner
Multi-Channel Deficit Round Robin Scheduling for Hybrid TDM/WDM Optical Networks Master of Research Presentation by Mithileysh Sathiyanarayanan 611702 Supervisor : Dr. Kyeong Soo Kim College of Engineering, Swansea University October 2012
26

Multi_Channel Scheduling (MCDRR)

Dec 09, 2014

Download

Education

Master of Research Thesis Presentation.
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Multi_Channel Scheduling (MCDRR)

Multi-Channel Deficit Round Robin Scheduling for Hybrid TDM/WDM

Optical Networks

Master of Research Presentation by

Mithileysh Sathiyanarayanan 611702

Supervisor : Dr. Kyeong Soo KimCollege of Engineering, Swansea University

October 2012

Page 2: Multi_Channel Scheduling (MCDRR)

The main aim of the research is to propose a new multi-channel scheduling algorithm with tunable transmitters and fixed receivers which provide fairness and QoS guarantee in hybrid TDM/WDM Optical Networks (Next-Generation Networks).

Aim of the Research

Page 3: Multi_Channel Scheduling (MCDRR)

To extend the Fair Queuing (FQ) frame work to the case of multiple channels with tunable transmitters and fixed receivers.

To design a multi-channel scheduler using tunable transmitters and fixed receivers.

To avoid packet delay and improve throughput of the system.

To design and evaluate the performance of the scheduler for hybrid TDM/WDM PON’s providing fairness and QoS guarantee.

To implement detailed simulation model for the designed multi-channel scheduler.

Objectives of the Research

Page 4: Multi_Channel Scheduling (MCDRR)

Scheduling is a method of harmonizing the access to system resources among competing data flows.

The scheduling plays an important role in achieving high performance of the networking systems.

Well-designed scheduling algorithms could provide higher throughput, lower latency, and better fairness with lower complexity in serving the packets.

Introduction to scheduling

Page 5: Multi_Channel Scheduling (MCDRR)

The scheduling has been extensively studied mainly in the context of single-channel communication.

The advent of wavelength division multiplexing (WDM) technology, however, demands the extension of this packet scheduling problem to the case of multi-channel communication, especially with the tunable transmitters for hybrid time division multiplexing (TDM)/ wavelength division multiplexing (WDM) systems.

Purpose of multi-channel scheduling

Page 6: Multi_Channel Scheduling (MCDRR)

The major focus of existing work is mostly on the throughput and delay performance of the scheduling algorithm like in SUCCESS-HPON [1], but there is hardly any support for fairness and QoS guarantee.

The other focus is on the well-known DRR scheduling algorithm [2] for single-channel case which has advantages such as --it is simple and easy to implement, cost-effective, provides fairness and has a complexity of O(1).

Motivation

Page 7: Multi_Channel Scheduling (MCDRR)

The research is mainly based on the tunable transmitters and fixed receivers in the multi-channel system which requires investigation in the performance of a multi-channel deficit round-robin (MCDRR) scheduling algorithm, which can provide fairness (in terms of throughput) for flows with different size packets with O(1) processing per packet.

Problem Description

Page 8: Multi_Channel Scheduling (MCDRR)

MULTI-CHANNEL DEFICIT ROUND-ROBIN (MCDRR)

Fig 1 : Block diagram of a hybrid TDM/WDM link based on tunable transmitters and fixed receivers.

Page 9: Multi_Channel Scheduling (MCDRR)

The MCDRR is an extension of the DRR which takes into account the availability of channels and tunable transmitters and overlaps ‘rounds’ in scheduling to efficiently utilize channels and tunable transmitters.

The MCDRR allows multiple rounds to overlap and run in parallel, the scheduling and the transmission of packets are not necessarily sequential unlike the DRR.

MCDRR

Page 10: Multi_Channel Scheduling (MCDRR)

MCDRR Example

Start of Round 1

Page 11: Multi_Channel Scheduling (MCDRR)

MCDRR Example

End of Round 1

Page 12: Multi_Channel Scheduling (MCDRR)

MCDRR Example

Start of Round 2

Page 13: Multi_Channel Scheduling (MCDRR)

MCDRR Example

End of Round 2

Page 14: Multi_Channel Scheduling (MCDRR)

MCDRR Example

Start of Round 3

Page 15: Multi_Channel Scheduling (MCDRR)

MCDRR Example

End of Round 3

Page 16: Multi_Channel Scheduling (MCDRR)

MCDRR Example

End of Round1 showing in Tunable Transmitter

End of Round2 showing in Tunable Transmitter

Page 17: Multi_Channel Scheduling (MCDRR)

MCDRR Example

End of Round3 showing in Tunable Transmitter

Overlapping of all the three rounds in MCDRR Scheduling

Page 18: Multi_Channel Scheduling (MCDRR)

Simulation Results

Page 19: Multi_Channel Scheduling (MCDRR)

Simulation Results

Page 20: Multi_Channel Scheduling (MCDRR)

In Figure (2), the interframe times are exponentially distributed with the averages of 16 mus and 48 mus for the first flow and the rest of the flows respectively, while the frame sizes are uniformly distributed between 64 and 1518 bytes for all the flows.

In Figure (3), the interframe times are exponentially distributed with the averages of 16 mus and 32 mus for the first flow and the rest of the flows, while the frame sizes are fixed to 1000 bytes for the first flow and 500 bytes for the rest of the flows.

Simulation Results

Page 21: Multi_Channel Scheduling (MCDRR)

From the simulation results, we found that the proposed MCDRR scheduling algorithm provides nearly perfect fairness even with ill-behaved flows for different sets of conditions for interframe times and frame sizes.

Simulation Results

Page 22: Multi_Channel Scheduling (MCDRR)

We have proposed and investigated the performance of the MCDRR scheduling algorithm for a multichannel link with tunable transmitters and fixed receivers, which is based on the DRR.

In extending the DRR to the case of multi-channel scheduling, we try to efficiently utilize the network resources (i.e., channels and tunable transmitters) by overlapping rounds, while maintaining its low complexity (i.e.,O(1)). The nearly perfect fairness provided by the MCDRR has been demonstrated through simulation experiments.

Conclusion

Page 23: Multi_Channel Scheduling (MCDRR)

A detailed study must be carried out about the end-to-end performance of a network of MCDRR.

We can try to achieve 100% throughput by providing tight bounds.

Establishing mathematical bounds for the fairness and latency of the MCDRR is an important future work and also the comparison with other multi-channel scheduling algorithms can be carried out.

We can extend the present research to upstream scheduling and using tunable receivers.

Future Works

Page 24: Multi_Channel Scheduling (MCDRR)

[1] K. S. Kim, D. Gutierrez, F.-T. An, and L. G. Kazovsky, “Design and performance analysis of scheduling algorithms for WDM-PON under SUCCESS-HPON architecture,” J. Lightw. Technol., vol. 23, no. 11, pp.3716–3731, Nov. 2005.

[2] M. Shreedhar and G. Varghese, “Efficient fair queueing using deficit round robin,” SIGCOMM Comput. Commun. Rev., vol. 25, no. 4, pp.231–242, 1995.

References

Page 25: Multi_Channel Scheduling (MCDRR)

Multi-Channel Deficit Round-Robin Scheduling for Hybrid TDM/WDM Optical Networks

Presented at FOAN-2012 Russia http://iathnrl.swan.ac.uk/~kks/publications/

mcdrr_foan2012.pdf

My First Conference Paper

Page 26: Multi_Channel Scheduling (MCDRR)

THANK YOU FOR Listening !!!