Packet-level wireless (802.11ax or 5G) network simulators face escalating system dimensionality resulting from dense deployment scenarios supporting wideband, Multi-Input Multi-Output (MIMO), Multi-User (MU) transmission. Managing the resulting network simulation complexity and achieving practical runtimes require continuing enhancements to physical (PHY) layer abstractions. This work improves the state-of-the-art PHY layer abstractions via a new computational workflow that maps extensive offline link simulation results for OFDM/OFDMA MIMO/MU-MIMO system performance over frequency-selective fading channels into Packet Error Ratio (PER) for network simulations. The proposed method is shown to require modest additional storage and the runtime is insensitive to the increase in PHY layer dimensionality. We describe the principles of this new method and provide details about its implementation, performance, and validation.

The explicit control protocol (XCP) has been proposed as a multi-level network feedback mechanism for congestion control of Internet transport protocols. Theoretical and simulation results have suggested that the protocol is stable and efficient over high bandwidth-delay product paths, while being more scalable to deploy than mechanisms that require per-flow state in routers. However, there is little operational experience with the approach. Since the deployment of XCP would require changes to both the end hosts and routers, it is important to study the implications of this new architecture before advocating such wide scale changes to Internets. This paper presents the results of an experimental study of XCP. We first implemented XCP in the Linux kernel and solved various systems issues. After validating previously reported simulation results, we studied the sensitivity of XCP's performance to various environmental factors, and discovered issues with TCP/IP configuration, capacity misestimation due to link sharing, handling of non-congestion losses, and the partial deployment of XCP queues in the network. These sensitivities can significantly reduce XCP's ability to control congestion and achieve fairness. Our contributions are twofold. First, through implementation we have revealed the challenges in platforms that lack large native data types or floating point arithmetic, and the need to keep fractions in the XCP protocol header. Second, through experiment and analysis we have identified several possibilities for XCP to enter into incorrect feedback control loops and adversely affect the performance. The challenges identified are deployment challenges intrinsic to the XCP design, and they suggest that the current proposal requires additional development and extension.

We study the performance of TCP over a satellite link, which is subject to intermittent blockages. Our simulation-based study characterizes the performance degradation of transferring messages ranging from small web objects to large files over satellite channels with widely varying blockage statistics. Using a split connection gateway, we investigate the impact of trying to preserve TCP end-to-end semantics upon connection close and find that such an approach significantly reduces the ability of small TCP transfers to survive a long duration blockage. We show that by tying the satellite gateway's offered window to the terrestrial TCP sender to the space in the send buffer on the satellite link becomes available, the split-connection gateway can essentially eliminate the delay incurred waiting for the TCP persist timer to expire. Finally, we illustrate how aspects of the gateway's design affect large and small TCP transfers differently.

The host identity protocol (HIP) is a recent protocol proposal for secure host mobility and multihoming using cryptographic-based name space for Internet hosts. This paper reports on our experience with implementing HIP and experimenting with it as a mobility management and host multihoming solution. After first introducing the HIP approach and contrasting it with other solutions, we describe our approach for implementing HIP as an extension to Linux and FreeS/WAN IPsec, including our use and extension of standard APIs. We then characterize the performance of HIP packet exchanges experimentally, and report that the computational overhead is dominated by the DSA signing of the HIP packets. Using 266 MHz Pentium II-based laptops, our HIP implementation took slightly under 1 second on average to complete connection setup, and less than 200 ms to process a mobility-initiated readdress. We also characterize the overhead due to the HIP "cookie challenge" used for stateless connection setup. We conclude by identifying areas for continued HIP development.

Advances in satellite technology are enabling the deployment of large constellations of low Earth Orbiting (LEO) satellites. Next-generation systems will be tailored for broadband, packet-switched services, and therefore require either distributed or centralized packet routing mechanisms. Some researchers have hypothesized that the semi-regular mesh topology of a polar-orbiting constellation admits a simple distributed routing protocol based on using geographic information embedded in the node address. We take a closer look at this hypothesis in the context of commercially-proposed constellation designs. Using simulation, we study a distributed routing protocol that selects the next hop based on a minimization of the remaining distance to the destination. Our numerical results indicate that this routing strategy usually yields good routes, with an average latency degradation of less than 10 ms when compared with the optimal route. However, there are locations in the topology, most notably around the counter-rotating seams, the polar regions, and close to the destination of a packet, where the assumption of a regular mesh topology breaks down and it is difficult to guarantee robustness without adding significant additional complexity to the protocol.

We address the question of how well end-to-end transport connections perform in a satellite environment composed of one or more satellites in geostationary orbit (GEO) or low-altitude Earth orbit (LEO), in which the connection may traverse a portion of the wired Internet. We first summarize the various ways in which latency and asymmetry can impair the performance of the Internet's transmission control protocol (TCP), and discuss extensions to standard TCP that alleviate some of these performance problems. Through analysis, simulation, and experiments, we quantify the performance of state-of-the-art TCP implementations in a satellite environment. A key part of the experimental method is the use of traffic models empirically derived from Internet traffic traces. We identify those TCP implementations that can be expected to perform reasonably well, and those that can suffer serious performance degradation. An important result is that, even with the best satellite-optimized TCP implementations, moderate levels of congestion in the wide-area Internet can seriously degrade performance for satellite connections. For scenarios in which TCP performance is poor, we investigate the potential improvement of using a satellite gateway, proxy, or Web cache to "split" transport connections in a manner transparent to end users. Finally, we describe a new transport protocol for use internally within a satellite network or as part of a split connection. This protocol, which we call the satellite transport protocol (STP), is optimized for challenging network impairments such as high latency, asymmetry, and high error rates. Among its chief benefits are up to an order of magnitude reduction in the bandwidth used in the reverse path, as compared to standard TCP, when conducting large file transfers. This is a particularly important attribute for the kind of asymmetric connectivity likely to dominate satellite-based Internet access.