Mohammad Zubair Ahmad

Survey Paper: Routing protocols in ad hoc networks: A survey

Ad hoc wireless networks perform the difficult task of multi-hop communication in an environment without a dedicated infrastructure, with mobile nodes and changing network topology. Different deployments exhibit various constraints, such as energy limitations, opportunities, such as the knowledge of the physical location of the nodes in certain scenarios, and requirements, such as real-time or multi-cast communication. In the last 15years, the wireless networking community designed hundreds of new routing protocols targeting the various scenarios of this design space. The objective of this paper is to create a taxonomy of the ad hoc routing protocols, and to survey and compare representative examples for each class of protocols. We strive to uncover the requirements considered by the different protocols, the resource limitations under which they operate, and the design decisions made by the authors.

Congestion Avoidance and Fairness in Wireless Sensor Networks

Designing a sensor network congestion avoidance algorithm is a challenging task due to the application specific nature of these networks. The frequency of event sensing is a deciding factor in the occurence of congestion. Numerous sensors, simultaneously transmitting data, increase the probability of packet drops due to congestion close to the base station(s). In this paper, we propose a novel distributed congestion avoidance algorithm which uses the ratio of the number of downstream and upstream nodes along with available queue sizes of the downstream nodes to detect incipient congestion. Monitoring queue sizes of candidate downstream nodes helps ensure effective load balancing and fairness in our avoidance algorithm. Through simulation studies we observe a greater packet delivery ratio and higher network lifetime in comparison with other prevalent mechanisms.

Circularity-Based medium access control in mobile ad hoc networks

The RTS/CTS access scheme, designed to reduce the number of collisions in a IEEE 802.11 network, is known to exhibit problems due to masked nodes, the imbalance between the interference range and the communication range of the nodes, and scenarios in which nodes are unnecessarily silenced, thus preventing parallel transmissions to take place. We present an approach for enhancing the performance of the IEEE 802.11 MAC protocol by selectively discarding or delaying specifically marked RTS and CTS packets. By dropping the circularity-satisfied RTS, we allow certain parallel transmissions to proceed, even if there is a non-zero risk of collision. By delaying the circularity-satisfied CTS, we allow a neighboring parallel transmission to continue. One important feature of the circularity approach is that it is fully compatible with the IEEE 802.11 standard. We implemented the circularity approach in ns-2 simulator. Through a series of experiments, we show that the circularity approach provides a significant improvement in the throughput and end-to-end delay of the network, and contributes to a reduction of the number of collisions in most scenarios.

Studying the effect of internet eXchange points on internet link delays

Internet exchange points (IXPs) are an increasingly important constituent of the Internet at the Autonomous System (AS) level. IXPs are set up with the goal of enabling greater efficiency in traffic exchange between ASes both from economical and technical perspectives. Little is however known about the effect that IXPs have in packet transmission between peering ASes, with a significant focus of the research community being in determining their effect on the topology evolution of the Internet. In this paper, we report on the increasing deployment of IXPs around the world over the past few years and carry out a set of experiments to try and establish the effectiveness of Internet routes traversing an IXP. We find that IXP links entail lesser delays than normal links on the Internet even though their presence does not decrease the length of a path. Our results present pointers towards developing more extensive experiments to verify the effectiveness of deploying IXPs worldwide.

Understanding the impact of internet exchange points on internet topology and routing performance

The growth of Internet eXchange Points (IXPs) as an important component in the Internet Autonomous System (AS) level topology has led to the need for a detailed evaluation of their effect on Internet topology evolution and inter-domain packet routing. In this work, we carry out initial measurements to analyze the effect of the additional peering links and observe path quality in terms of round-trip time and loss rates of routes going through an IXP between pairs of Internet hosts. We observe significant effects of IXP-links on Internet growth and topology evolution while the routing performance points to numerous cases of Triangle Inequality Violations (TIVs) due to the IXP switches.

Critical sections in networked games

This work introduces the concept of critical sections for online first person shooter games (FPS). A critical section is a section of game-play which demands higher precision or tighter deadlines. Critical section traffic is more sensitive to network degradations than sections immediately preceding or following it. Critical sections provide game developers and network programmers a notion of relative priority of game traffic, and can identify segments whose preservation can lead to superior user perceived quality of playing FPS games on a network. By analyzing video-recordings of over 5 hours of FPS gameplay by 10 volunteers, we identify sections of FPS game-play whose degradation would cause inconsistent game-state updates resulting in user frustration. We observe that critical sections exhibit a pattern of occurrence and can account for upto 17% of game-play time. We next quantify the expected network induced degradations on critical sections for online FPS games on the Internet. Using traces from a deployment of FPS workloads on 50+ nodes in the Internet, we study network dynamics and their ensuing effect on critical sections. Using traces from this experiment, we derive the lower bound on potentially degraded game-play session on todays Internet. We argue that critical sections of FPS games can be preserved. This can allow a variety of network architectures to better deliver higher perceptual experience when deployed on the Internet. Overall, our results have implications for FPS game-design, network provisioning, and game quality evaluation.

A tale of nine Internet exchange points: Studying path latencies through major regional IXPs

The Internet ecosystem comprising of thousands of Autonomous Systems (ASes) now include Internet eXchange Points (IXPs) as another critical component in the infrastructure. With the growth of peering worldwide, IXPs are playing an increasing role not only in the topology evolution of the Internet but also inter-domain path routing. In this work, we first motivate the need to monitor popular exchange points based on geographical locations. These major IXPs are responsible for transmitting 43% of the total IXP traffic and hence play a significant role in determining the effects of peering at IXPs on path latencies. Using the most important route performance metric of end to end latency we then propose and implement a measurement framework to carry out an in-depth comparison of paths traversing an IXP with other available alternate paths. We observe the presence of a significant percentage of alternate paths outperforming the default route through an IXP in all major regions. Even though IXPs are set up primarily with economic benefits in mind, we conclude that there is a huge potential for improvement with more efficient routing and better planning at the primary IXPs around the world.

Evaluating End-User Network Benefits of Peering with Path Latencies

Internet eXchange Points (IXPs) have been recently identified as critical components of the Internets AS level infrastructure. Recent studies have characterized the importance of IXPs in Internet topology evolution studies but the network benefits brought about by the increased peering has not garnered much attention. In this work, we propose and implement a measurement framework to compare paths traversing an IXP hop with a set of valid alternate paths which isolate the IXP effects. Our framework enables identification of these alternate paths and then carries out an in-depth comparison of the IXP path with its available alternates. Using the popular route performance metric of end- to-end latency we observe that most paths through peering ASes at exchanges generally have a better alternate through transit providers of the peering ASes. Traditional overlay routes such as detour paths also outperform the default BGP path through an IXP. While economic benefits are the primary driving forces behind public peering we conclude that obtaining network benefits (in terms of path latencies) require due consideration by peering ASes to ensure better end-user experience.

Analysis of large scale traceroute datasets in Internet routing overlays by parallel computation

The creation of a routing overlay network on the Internet requires the identification of shorter detour paths between end hosts in comparison to the default path available. These detour paths are typically the edges forming a Triangle Inequality Violation (TIV), an artifact of the Internet delay space where the sum of latencies across an intermediate hop is lesser than the direct latency between the pair of end hosts. These violations are caused mainly due to interdomain routing policies between Autonomous Systems (ASes) and AS peering through Internet eXchange Points (IXPs). Identifying detours for a global overlay network requires large amounts of computational capabilities due to the sheer number of possible paths linking source and destination ASes. In this work, we use parallel programming paradigms to exploit the massively parallel capabilities of analyzing the large network measurement datasets made available to the network research community by CAIDA. We study Internet routes traversing IXPs and measure potential TIVs created by these paths. Large scale analysis of the dataset is carried out by implementing an efficient parallel solution on the CPU and then the general purpose graphics processor unit (GPGPU) as well. Both multicore CPU and GPGPU implementations can be carried out with ease on desktop environments with readily available software. We find both parallel solutions yield high improvements in speedup (2-35x) in comparison to the serial methodologies thereby opening up the possibility of harnessing the power of parallel programming with readily available hardware. The large amount of data analyzed and studied helps draw various inferences for the networking research community in building future scalable Internet routing overlays with greater routing efficiencies.

Internet exchange points and Internet routing

The Internet is a network of Autonomous Systems (ASes) comprising of a complex and complicated ecosystem of networks used for a wide variety of applications. ASes exhibit varied functionality and communicate according to predefined rules to maintain distinct business objectives; termed intra-AS relations. These relations are one of two types: customer-provider (hierarchical) or peering (flat). Recent studies of intra-AS relations indicate the gradual transition of the Internet ecosystem from the hierarchical structure to a flatter peering architecture [1]. This infrastructure level flattening is characterized by the constant growth, rewiring and deaths of inter-AS links. Primary driving forces behind these changes are economic; especially the meteoric rise in popularity of organizations such as Facebook, Google, Yahoo and Microsoft, who have lately deployed large, private WAN infrastructures [1]. The transition from the hierarchical Internet has also accelerated with the deployment of multiple Internet eXchange Points (IXPs) worldwide, the facilitator of peering. Numerous peering links (between ASes) at these IXPs have recently been uncovered but their effects on Internet topology and inter-domain routing performance not yet examined.