Analysis of M-LWDF fairness and an enhanced M-LWDF packet scheduling mechanism

Abstract Modified largest weighted delay first (M-LWDF) is a typical packet scheduling algorithm for supporting hybrid real-time services over wireless networks. However, so far, there is little literature available regarding the theoretic analysis of M-LWDF fairness. This paper gives a theoretic analysis of M-LWDF fairness, which shows that M-LWDF fairness is related to channel condition, packet's arrival process and the ratio of quality of service (QoS) requirements of different service queues. Given service QoS requirements and other parameters related to channel model and packet's arrival process, the fairness is merely related to the ratio of the number of users in the service queues. Based on the analysis, an enhanced M-LWDF algorithm (EM-LWDF) is proposed and demonstrated in this paper. EM-LWDF is strictly designed in light of the fairness criteria of QoS requirements, so its fairness is almost not related to the ratio of the number of users in the service queues, and the theoretical value of fairness index is equal to 1. Simulation results validate the theoretic analysis and show the effectiveness of EM-LWDF in improving fairness.

[1]  Troels Emil Kolding.  Link and system performance aspects of proportional fair scheduling in WCDMA/HSDPA , 2003, 2003 IEEE 58th Vehicular Technology Conference. VTC 2003-Fall (IEEE Cat. No.03CH37484).

[2]  K. Sandrasegaran,et al.  Performance analysis of EXP/PF and M-LWDF in downlink 3GPP LTE system , 2009, 2009 First Asian Himalayas International Conference on Internet.

[3]  Jianhua Zhang,et al.  Channel and queue aware scheduling for real- time service in multiuser MIMO OFDM system , 2007, 2007 Asia-Pacific Conference on Communications.

[4]  Kumbesan Sandrasegaran,et al.  Performance of well known packet scheduling algorithms in the downlink 3GPP LTE system , 2009, 2009 IEEE 9th Malaysia International Conference on Communications (MICC).

[5]  Li,et al.  Scheduling Fairness of Real-Time Scheduling Algorithms in Wireless Multimedia Application , 2007 .

[6]  Matthew Andrews,et al.  Providing quality of service over a shared wireless link , 2001, IEEE Commun. Mag..

[7]  Jack M. Holtzman,et al.  Access Control of Data in Integrated Voice/Data CMDA Systems: Benefits and Tradeoffs , 1997, IEEE J. Sel. Areas Commun..

[8]  Jian Cai,et al.  Providing differentiated services in EGPRS through packet scheduling , 2000, Globecom '00 - IEEE. Global Telecommunications Conference. Conference Record (Cat. No.00CH37137).

[9]  A. Stolyar,et al.  LARGEST WEIGHTED DELAY FIRST SCHEDULING: LARGE DEVIATIONS AND OPTIMALITY , 2001 .

[10]  Kiseon Kim,et al.  Multiple QoS support using M-LWDF in OFDMA adaptive resource allocation , 2004, The 13th IEEE Workshop on Local and Metropolitan Area Networks, 2004. LANMAN 2004..

[11]  A. Jalali,et al.  Data throughput of CDMA-HDR a high efficiency-high data rate personal communication wireless system , 2000, VTC2000-Spring. 2000 IEEE 51st Vehicular Technology Conference Proceedings (Cat. No.00CH37026).

[12]  Preben E. Mogensen,et al.  Performance of the M-LWDF scheduling algorithm for streaming services in HSDPA , 2004, IEEE 60th Vehicular Technology Conference, 2004. VTC2004-Fall. 2004.

[13]  Rongqing Xu,et al.  A novel multi-radio packet scheduling algorithm for real-time traffic on generic link layer , 2009, 2009 15th Asia-Pacific Conference on Communications.

[14]  H. V. Poor,et al.  HOLPRO: a new rate scheduling algorithm for the downlink of CDMA networks , 2000, Vehicular Technology Conference Fall 2000. IEEE VTS Fall VTC2000. 52nd Vehicular Technology Conference (Cat. No.00CH37152).

[15]  Ion Stoica,et al.  Packet fair queueing algorithms for wireless networks with location-dependent errors , 1998, Proceedings. IEEE INFOCOM '98, the Conference on Computer Communications. Seventeenth Annual Joint Conference of the IEEE Computer and Communications Societies. Gateway to the 21st Century (Cat. No.98.