Although the performance degradation for TCP/IP over plain ATM during congestion can be reduced if switch buffer management techniques such as Early Packet Discarding (EPD) and Partial Packet Discarding (PPD) schemes are employed. However, we show via simulation that fairness among connections remains a problem. For example, the fairness among packets of different length is a well known unsolved issue for EPD. To improve fairness of TCP and UDP over an Internet backbone, we propose a new technique called the Age Priority Packet Discarding (APPD) scheme to be used along with EPD and PPD. We employ two simulation scenarios to examine the performance of APPD; the MPEG-I video over UDP protocol and the FTP over TCP protocol. The simulation shows that with APPD combined with EPD and PPD, fairness can be well maintained against different packet length, order of connections, as well as different propagation delays. In addition, packet loss probability can be reduced with APPD in all scenarios, and the improvement is especially significant for video over UDP protocol. Finally we discuss the hardware implementation technique of the APPD scheme.

We proposed an improved Hierarchical Packet Fair Queueing (H-PFQ) mechanism, using ACK Spacing, for efficient bandwidth management of TCP traffic over Internet. According to the pre-determined bandwidth sharing and the class hierarchy of all TCP sessions, we design an algorithm to calculate the required time intervals between consecutive ACK packets of each TCP session to avoid packet drops due to buffer overflow. We demonstrated via computer simulations that the proposed improvement techniques may result in much better performance than merely original H-PFQ mechanism used in the forward direction in the sense that not only effective throughput of the bottleneck link is improved but also the fairness among TCP sessions can be maintained.

Currently, the issues in Quality of Service, fairness and pricing strategies should have expedited the emergence of service differentiation in wireless access networks. In this paper, we propose a novel scheduling algorithm, called the Wireless Differentiated Fair Queueing (WDFQ) algorithm, to accommodate such need by providing delay/jitter controls, and fair residual bandwidth sharing for real-time and non-real-time traffic streams simultaneously. We show that the WDFQ scheme can achieve excellent performance, including timely delivery of real-time traffic, virtually error-free transmission of non-real-time traffic, and fair usage of channel bandwidth among remote stations. In addition, the location-dependent channel error property, as appeared in most wireless networks, are considered in the model and the temporary short error bursts are compensated by credits of bandwidth. The simulation results suggest that the length of retransmission period should be adapted to the error length to achieve good performance and maintain low implementation complexity.

In the current ATM AAL5 implementation, even a single cell loss event can lead to the corruption of one whole packet. Hence, it has been observed that the throughput of upper layer protocol may easily collapse on a congested ATM network. In this paper, we propose a buffer management method called Age Priority Packet Discarding (APPD) scheme to be used along with two other schemes: the Early Packet Discarding (EPD) and the Partial Packet Discarding (PPD) schemes. After describing the operations and the pseudo code of the proposed APPD scheme and how it operates with the EPD/PPD schemes, the packet level QoS of APPD and its extended versions are derived analytically under homogeneous ON-OFF source model. Numerical results obtained via analytical approach suggest that the proposed APPD scheme can more effectively and fairly reduce packet loss probability than other schemes.