Iterative resource pooling for bandwidth allocation in TDM-PON: algorithm, convergence and experimental evaluation

In this paper, we propose a new dynamic bandwidth allocation technique, SLIding Cycle Time (SLICT) for TDM-PON, specifically focused on ethernet passive optical network (EPON). Based on the sliding cycle time constraint, the proposed algorithm guarantees the maximum polling interval, an essential property for delay-sensitive applications and interactive services. We then introduce an iterative resource pooling that processes bursty best-effort traffic and achieves high throughput even under non-uniform upstream traffic distribution. We prove that greedy iterative resource pooling converges to equal resource allocation exponentially fast. Extensive numerical simulations show that SLICT outperforms existing techniques in all aspects: throughput, delay, packet loss and average queue size. Finally, SLICT has been implemented on an EPON FPGA board and the performance is confirmed under real traffic.

[1]  Maode Ma,et al.  A bandwidth guaranteed polling MAC protocol for Ethernet passive optical networks , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[2]  Anirban Mahanti,et al.  Traffic classification using clustering algorithms , 2006, MineNet '06.

[3]  Mung Chiang,et al.  An Axiomatic Theory of Fairness in Resource Allocation , 2010 .

[4]  Biswanath Mukherjee,et al.  IPACT: A dynamic protocol for an Ethernet PON (EPON) , 2002, IEEE Commun. Mag..

[5]  Walter Willinger,et al.  Self-similarity through high-variability: statistical analysis of Ethernet LAN traffic at the source level , 1997, TNET.

[6]  Biswanath Mukherjee,et al.  Ethernet PON (ePON): Design and Analysis of an Optical Access Network , 2001, Photonic Network Communications.

[7]  Jinwoo Park,et al.  Decentralized DBA scheme based on power detection in TDM-PON , 2007, Photonic Network Communications.

[8]  Ashutosh Sabharwal,et al.  An Axiomatic Theory of Fairness in Network Resource Allocation , 2009, 2010 Proceedings IEEE INFOCOM.

[9]  Biswanath Mukherjee,et al.  Interleaved Polling with Adaptive Cycle Time (IPACT): A Dynamic Bandwidth Distribution Scheme in an Optical Access Network , 2004, Photonic Network Communications.

[10]  Mirjana Radivojevic,et al.  Novel wavelength and bandwidth allocation algorithms for WDM EPON with QoS support , 2010, Photonic Network Communications.

[11]  Rubén M. Lorenzo,et al.  EPON bandwidth allocation algorithm based on automatic weight adaptation to provide client and service differentiation , 2008, Photonic Network Communications.

[12]  Hongseok Kim,et al.  Sliding cycle time-based MAC protocol for service level agreeable Ethernet passive optical networks , 2005, IEEE International Conference on Communications, 2005. ICC 2005. 2005.

[13]  Biswanath Mukherjee,et al.  Ethernet passive optical networks , 2005 .

[14]  Gee-Swee Poo,et al.  A hybrid cycle bandwidth allocation scheme with differentiated services support in Ethernet passive optical networks , 2008, Photonic Network Communications.

[15]  Kyoung-Rok Cho,et al.  Priority-based dynamic bandwidth allocation in Ethernet Passive Optical Networks , 2008, Photonic Network Communications.

[16]  Carey L. Williamson,et al.  Identifying and discriminating between web and peer-to-peer traffic in the network core , 2007, WWW '07.

[17]  Chadi Assi,et al.  On the fairness of dynamic bandwidth allocation schemes in Ethernet passive optical networks , 2006, Comput. Commun..

[18]  Walter Willinger,et al.  Self-similarity through high-variability: statistical analysis of Ethernet LAN traffic at the source level , 1997, TNET.

[19]  Chung-Ju Chang,et al.  PRNN/ERLS-based predictive QoS-promoted DBA scheme for upstream transmission in EPON , 2010, Photonic Network Communications.

[20]  Dynamic Bandwidth Allocation Schemes to Improve Utilization under Non-Uniform Traffic in Ethernet Passive Optical Networks , 2004 .

[21]  Carey L. Williamson,et al.  Offline/realtime traffic classification using semi-supervised learning , 2007, Perform. Evaluation.

[22]  Su-il Choi.  Cyclic Polling-Based Dynamic Bandwidth Allocation for Differentiated Classes of Service in Ethernet Passive Optical Networks , 2004, Photonic Network Communications.

[23]  Sudhir S. Dixit,et al.  Dynamic bandwidth allocation for quality-of-service over Ethernet PONs , 2003, IEEE J. Sel. Areas Commun..

[24]  Tomas Olovsson,et al.  Trends and Differences in Connection-Behavior within Classes of Internet Backbone Traffic , 2008, PAM.

[25]  Kyuho Son,et al.  Dynamic bandwidth allocation schemes to improve utilization under nonuniform traffic in Ethernet passive optical networks , 2004, 2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577).