Pei-chun Cheng

GeoDTN+Nav: Geographic DTN Routing with Navigator Prediction for Urban Vehicular Environments

Position-based routing has proven to be well suited for highly dynamic environment such as Vehicular Ad Hoc Networks (VANET) due to its simplicity. Greedy Perimeter Stateless Routing (GPSR) and Greedy Perimeter Coordinator Routing (GPCR) both use greedy algorithms to forward packets by selecting relays with the best progress towards the destination or use a recovery mode in case such solutions fail. These protocols could forward packets efficiently given that the underlying network is fully connected. However, the dynamic nature of vehicular network, such as vehicle density, traffic pattern, and radio obstacles could create unconnected networks partitions. To this end, we propose GeoDTN+Nav, a hybrid geographic routing solution enhancing the standard greedy and recovery modes exploiting the vehicular mobility and on-board vehicular navigation systems to efficiently deliver packets even in partitioned networks. GeoDTN+Nav outperforms standard geographic routing protocols such as GPSR and GPCR because it is able to estimate network partitions and then improves partitions reachability by using a store-carry-forward procedure when necessary. We propose a virtual navigation interface (VNI) to provide generalized route information to optimize such forwarding procedure. We finally evaluate the benefit of our approach first analytically and then with simulations. By using delay tolerant forwarding in sparse networks, GeoDTN+Nav greatly increases the packet delivery ratio of geographic routing protocols and provides comparable routing delay to benchmark DTN algorithms.

GeoCross: A geographic routing protocol in the presence of loops in urban scenarios

In this paper,we propose GeoCross, a simple, yet novel, event-driven geographic routing protocol that removes cross-links dynamically to avoid routing loops in urban Vehicular Ad Hoc Networks (VANETs). GeoCross exploits the natural planar feature of urban maps without resorting to cumbersome planarization. Its feature of dynamic loop detection makes GeoCross suitable for highly mobile VANET. We have shown that in pathologic cases, GeoCrosss packet delivery ratio (PDR) is consistently higher than Greedy Perimeter Stateless Routings (GPSRs) and Greedy Perimeter Coordinator Routings (GPCRs). We have also shown that caching (GeoCross+Cache) provides the same high PDR but uses fewer hops.

Understanding BGP next-hop diversity

The Internet topological connectivity becomes denser over time. However the de facto routing protocol of the global Internet, BGP, lets each BGP router select and propagate only a single best path to each destination network. This leads to a common concern that the rich connectivity is not fully utilized and the lack of alternative paths can reduce a networks robustness to failures as well as flexibility in traffic engineering, and can lead to slow adaptation to topological changes. Yet there have been few quantitative measurement studies on path diversity in todays operational Internet. In this paper we use iBGP routing data collected from a Tier1 ISP, ISPA, over a 2-year time period to quantify BGP next-hop diversity for all destinations. Our results show that ISPA reaches the majority of prefixes through multiple next-hop routers. We use several case studies of prefixes with different diversity degrees to identify two major factors that impact the number of observed next-hops: the ISPs path preference and the number of peering routers between large ISPs. This observation provides operational input to the current efforts on augmenting BGP to increase path diversity.

Longitudinal study of BGP monitor session failures

BGP routing data collected by RouteViews and RIPE RIS have become an essential asset to both the network research and operation communities. However, it has long been speculated that the BGP monitoring sessions between operational routers and the data collectors fail from time to time. Such session failures lead to missing update messages as well as duplicate updates during session re-establishment, making analysis results derived from such data inaccurate. Since there is no complete record of these monitoring session failures, data users either have to sanitize the data discretionarily with respect to their specific needs or, more commonly, assume that session failures are infrequent enough and simply ignore them. In this paper, we present the first systematic assessment and documentary on BGP session failures of RouteViews and RIPE data collectors over the past eight years. Our results show that monitoring session failures are rather frequent, more than 30% of BGP monitoring sessions experienced at least one failure every month. Furthermore, we observed failures that happen to multiple peer sessions on the same collector around the same time, suggesting that the collectors local problems are a major factor in the session instability. We also developed a web site as a community resource to publish all session failures detected for RouteViews and RIPE RIS data collectors to help users select and clean up BGP data before performing their analysis.

Route flap damping with assured reachability

It is well known that a relatively small percentage of unstable routes exists in the global routing system which contributes an out of proportion number of routing updates. The route flap damping (RFD) was once considered an effective means to curtail such instability. However, both measurement studies and operational observations show that BGP path exploration can trigger false route damping which leads to prolonged periods of lost network reachability. As a result, many networks turned off RFD. In this paper we propose a simple solution, RFD+RG, dubbed RFD with Reachability Guard, to address the reachability problem in the RFD deployment. RFD+RG performs route flap damping without losing reachability, and the +RG enhancement component works independently from specific damping algorithms and can be integrated into any existing RFD scheme. We use collected BGP data to evaluate RFD+RG performance and our results show that RFD+RG can suppress up to 27% of route instabilities while faithfully preserving reachability.

Explaining BGP Slow Table Transfers

Although there have been a plethora of studies on TCP performance in supporting of various applications, relatively little is known about the interaction between TCP and BGP, which is a specific application running on top of TCP. This paper investigates BGPs slow route propagation by analyzing packet traces collected from a large ISP and Route Views Oregon collector. In particular we focus on the prolonged periods of BGP routing table transfers and examine in detail the interplay between TCP and BGP. In addition to the problems reported in previous literature, this study reveals a number of new TCP transport problems, that collectively induce significant delays. Furthermore, we develop a tool, named T-DAT, that can be deployed together with BGP data collectors to infer various factors behind the observed delay, including BGPs sending and receiving behavior, TCPs parameter settings, TCPs flow and congestion control, and network path limitation. Identifying these delay contributing factors makes an important step for ISPs and router vendors to diagnose and improve the BGP performance.

A comparative study of architectural impact on BGP next-hop diversity

Large ISPs have been growing rapidly in both the size and global connectivity. To scale with the sheer number of routers, many providers have replaced the flat full-mesh iBGP connectivity with a hierarchical architecture, using either Route-Reflection (RR) or AS confederation. Given that each intermediate iBGP router in the hierarchy selects and propagates only one best path per destination network, there is a common perception that, compared to full-mesh, a hierarchical iBGP connectivity is likely to lose sight of alternative paths to external destinations. To gauge the path diversity reduction in the operational networks, we performed a comparative study by using iBGP data collected from two global-scale ISPs, with full-mesh core and RR architecture respectively. Our results show that both ISPs suffer a significant reduction (up to 42%) in the overall path diversity. However the specifics of different iBGP architectures only made a minor impact (less than 2.9%) on this reduction. Rather, in both ISPs the majority of the alternative paths are eliminated by the first two criteria in BGP best path selection, i.e., LOCAL PREF and AS PATH length.