In this paper we address the issue of cross-layer design in transport layer enhancement mechanisms, where the data-link and transport layer information is shared with each other, in order to provide improved system throughput of the wireless cellular network. We propose a Cross-layer Transport Layer Enhancement mechanism with name of XST (Cross-layer Snoop protocol for TCP), which is based on Snoop protocol combined with the forced duplicate acknowledgement congestion control strategy in wireless cellular networks. XST employs the cross-layer design, working at the data-link layer but using the transport layer information as operating criteria. We conduct a comparative study between the XST mechanism and Active Queue Management (AQM) mechanism in the literature, such as Random Early Detection (RED) in wireless environments with varying link characteristics. Simulation results demonstrate that the proposed XST significantly outperforms RED in wireless cellular network, especially under high-error-rate which is a major characteristic of wireless links.

TCP is a reliable transport protocol tuned to perform well in traditional networks made up of links with low bit-error rates. Networks with higher bit-error rates, such as those with wireless links and mobile hosts, violate many of the assumptions made by the transmission control protocol (TCP), causing degraded end-to-end performance. We propose a two-layer hierarchical cache architecture for enhancing TCP performance over heterogeneous networks with both wired and wireless links. A new network-layer protocol, called new snoop (NS), is designed. The main idea is to cache the unacknowledged packets at both the mobile switch center (MSC) and base station (BS), to form a two-layer cache hierarchy. If a packet is lost due to transmission errors in the wireless link, the BS takes the responsibility to recover the loss. When a handoff occurs, the packets cached at the MSC can help to minimize the latency of retransmissions due to temporal disconnection. NS can preserve the end-to-end TCP semantics and is compatible with existing TCP applications. Its implementation only requires code modification at the BS and MSC. Simulation results show that NS is significantly more robust in dealing with unreliable wireless links and handoffs as compared with the original snoop scheme, as well as some other existing TCP enhancements.

A novel router flow control scheme, called IRED, is proposed for supporting both guaranteed bandwidth (GB) and best-effort (BE) flows in the Internet. In IRED, network resources are reserved for each GB flow using resource reservation protocol (RSVP). At each router, packet scheduling behavior is established to meet the QoS requirements of each GB flow. For supporting BE flows, a router senses incipient congestion by monitoring the average buffer occupancy of BE packets with respect to the total buffer space available for BE traffic. When a pre-defined occupancy threshold is exceeded, IRED randomly drops BE packets to notify the selected senders to slow down their transmission rates. Our extensive simulation results reveal that IRED can provide QoS guarantee on delay and packet dropping probability for GB flows, and can achieve excellent throughput performance for BE flows. We also find that IRED can protect BE flows from the harassment of unfriendly greedy GB flows as well as non-adaptive BE flows.

A novel proactive base station flow control algorithm, called forced duplicate acknowledgement (FDA), is proposed for extending TCP over wireless networks. FDA is implemented at the base station (BS) of a wireless network. It works in conjunction with existing TCP enhancement schemes such as Snoop or New Snoop. In FDA, if the average occupied buffer size at a BS exceeds a pre-defined threshold, an incipient congestion is detected. Then three forced duplicate ACKs, functioning as a congestion notification, will be generated by the BS and forwarded to a set of selected TCP senders. Upon receiving the forced duplicate ACKs, a sender reduces its transfer rate as a result of performing the fast retransmit procedure. To prevent multiple packet dropping due to buffer overflow at the BS, a quality guaranteed cache release policy is designed. The idea is to make room for the on-the-fly packets by releasing some cached but not-yet-acknowledged packets at the BS in advance. The performance of the proposed FDA is evaluated by simulations. We found that under various traffic and system configurations, FDA can not only fairly allocate the available wireless bandwidth among all TCP connections, but also achieves the highest throughput as compared to other schemes we have investigated.

In this paper, we propose a two-layer hierarchical cache architecture for enhancing TCP performance over heterogeneous networks with both wired and wireless links. A new network-layer protocol, called New Snoop, is designed. The main idea is to cache the unacknowledged packets at both the mobile switch center (MSG) and base station (BS), thus forming a two-layer cache hierarchy. If a packet is lost due to transmission errors in the wireless link, the BS takes the responsibility to recover the loss. When a handoff occurs during a TCP connection session, the packets cached in MSC can help to minimize the latency of retransmissions due to temporal disconnection. Simulation results show that using New Snoop is significantly more robust in dealing with unreliable wireless inks and handoffs as compared with the Snoop scheme (Balakrishnan et al. 1995) as well as other existing TCP enhancements.

A new push-and-pull hybrid data broadcast scheme is proposed for providing wireless information services to three types of clients, general, pull and priority clients. Only pull and priority clients have the back channel for sending requests to the broadcast server. There is no scalability problem with the hybrid scheme because the amount of pull and priority clients is very small. Based on the requests collected from pull and priority clients, the server estimates the interest pattern changes of the whole client population. Then the broadcast schedule on the push channel for the next broadcast cycle is adjusted. Besides the push channel, a small amount of broadcast bandwidth is allocated to a pull channel. The data to be broadcast on the pull channel is decided by the server in real-time and priority is given to requests from priority clients. Simulations show that with a time-varying client interest pattern, the average data access time for all three types of clients can be minimized. Because of the priority in using the pull channel, priority clients can achieve the lowest access time and pull clients can achieve a lower access time than general clients. To further improve the performance, the hybrid scheme with local client cache is also investigated.

A novel LEO/MEO two-tier satellite communication system with inter-satellite links (ISLs) is proposed for providing multimedia services to global mobile users. This two-tier system architecture can reduce the transmission delay for long-distance users via MEO satellites while keeping the benefits of using LEO satellites as the service access nodes. The routing and re-routing during a handoff operation is simplified. Since the physical topology of the underlying network is time-dependent, routing is crucial for guaranteeing the delay and delay variation performance for interactive applications. We decompose the routing problem into two parts, routing in the access network and routing in the core MEO ISL network. For the access network, a new routing algorithm called the maximum holding access protocol (MHAP) is proposed for minimizing the number of LEO handoffs. For core MEO ISL network, both minimum transmission delay routing (MTDR) and minimum transmission time jitter routing (MTTJR) are investigated. Using computer simulations, we show that the proposed routing algorithms can reduce the probability of call re-routing and thus are very suitable for providing interactive multimedia services.