Truc Anh N. Nguyen

ResTP: A Transport Protocol for FI Resilience

To support emerging application classes and network use paradigms for Future Internet resilience, we are designing a new transport protocol: ResTP. ResTP overcomes the limitations of TCP and UDP that evolved in the context of the fixed, wired, connected, relatively reliable, and low-to-moderate delay Internet. ResTP is developed to efficiently carry traffic from various application types across a wide variety of network types. By supporting cross-layering, ResTP allows service tuning by the upper application layer while promptly reacting to network condition changes by using the feedback from the lower network layer. ResTP supports a set of transport-layer services, and each service is comprised of many mechanisms and algorithms that can be combined based on the specific mission requirement, application type, and underlying network characteristics. In addition, ResTP can exploit multiple available paths for its data transmission to increase redundancy while better utilizing network resources. With the design based on our ResiliNets framework, we believe that ResTP is the first transport-layer protocol that considers all disciplines related to resilience.

An Implementation of Scalable, Vegas, Veno, and YeAH Congestion Control Algorithms in ns-3

Despite the modern advancements in networking, TCP congestion control is still one of the key mechanisms that ensure the stability of the Internet. Given its principal role, it is a popular research topic revisited every time TCP and its variants are studied. Open-source network simulators such as ns-3 are important tools used by the research community to gain valuable insight into existing TCP congestion control algorithms and to develop new variants. However, the current TCP infrastructure in ns-3 supports only a few congestion control algorithms. As part of the ongoing effort to extend TCP functionalities in the simulator, we implement Scalable, Vegas, Veno, and YeAH based on the original literature and their implementations in the Linux kernel; this paper presents our implementation details. The paper also discusses our validation of the added models against the theories to demonstrate their correctness. Through our evaluation, we highlight the key features of each algorithm that we study.

Opportunistic transport for disrupted airborne networks

Due to the challenging network conditions posed by a highly-dynamic airborne telemetry environment, it is essential for the transport protocol to provide automated mechanisms that dynamically adapt to changing end-to-end performance on any path. The AeroTP multi-mode transport protocol provides service tailored to the requirements of the telemetry mission control and data packets, achieving better performance compared to the traditional TCP and UDP. We use ns-3 to simulate the AeroTP protocols reliable and quasi-reliable modes and demonstrate the performance tradeoffs between the modes, as well as comparing their performance with TCP and UDP.

Performance Evaluation of TCP Congestion Control Algorithms in Data Center Networks

TCP congestion control has been known for its crucial role in stabilizing the Internet and preventing congestion collapses. However, with the rapid advancement in networking technologies, resulting in the emergence of challenging network environments such as data center networks (DCNs), the traditional TCP algorithm leads to several impairments. The shortcomings of TCP when deployed in DCNs have motivated the development of multiple new variants, including DCTCP, ICTCP, IA-TCP, and D2TCP, but all of these algorithms exhibit their advantages at the cost of a number of drawbacks in the Global Internet. Motivated by the belief that new innovations need to be established on top of a solid foundation with a thorough understanding of the existing, well-established algorithms, we have been working towards a comprehensive analysis of various conventional TCP algorithms in DCNs and other modern networks. This paper presents our first milestone towards the completion of our comparative study in which we present the results obtained by simulating multiple TCP variants: NewReno, Vegas, HighSpeed, Scalable, Westwood+, BIC, CUBIC, and YeAH using a fat tree architecture. Each protocol is evaluated in terms of queue length, number of dropped packets, average packet delay, and aggregate bandwidth as a percentage of the channel bandwidth.

An Implementation and Analysis of SCPS-TP in ns-3

Given the importance of TCP in transport-layer protocol studies and the numerous TCP modifications, yet the limited TCP models in ns-3, we extend the existing TCP framework in the network simulator by implementing SCPS-TP, a transport-layer protocol for space communications. The TCP backward-compatible SCPS-TP is constructed as a set of TCP enhancements through the utilization of TCP options to address the unique characteristics of space networks with error-prone, highly asymmetric, and bandwidth-constrained channels. In this paper, we present our implementation together with a set of simulations to validate our model against the original SCPS-TP paper. Through the verification, we also analyze the performance of SCPS-TP in comparison with the standard TCP.

Disruption-Tolerant Airborne Networks and Protocols

Introduction Traditional Internet protocols are not suitable for the aeronautical environment. The TCP/IP protocol stack has evolved for an Internet that is mostly wired (although that is changing at the edges) with stable topologies and connectivity to which disruptions require terminating of TCP connections, and reconvergence of routing algorithms. Civilian and commercial airborne networks require some modifications due to wireless links and moderate but often predicable mobility. However, these scenarios are not necessarily multi-hop, and traditionally rely on point-to-point links to ground stations for ATC (air traffic control) and satellites (for Internet access and entertainment distribution). Drone networks may be more challenging if multi-hop communication is desired with unpredictable movements. The most challenging scenario is for highly dynamic high-velocity multi-hop airborne networks, currently the domain of military communication. However, it is reasonable to expect future civilian, commercial, and government airborne networks to become more challenging as is becoming the case for ground-based vehicular networks, motivating VANETs (vehicular ad hoc networks) and VDTNs (vehicular disruption-tolerant networks). This chapter is organized as follows: Section 4.2 introduces the communication environment for aeronautical networks, which can vary significantly depending on the scenario (e.g., civilian vs. military networks). Section 4.3 relates airborne networks to the traditional Internet, as well as other mobile wireless environments, including WMNs (wireless mesh networks), MANETs (mobile ad hoc networks), and DTNs (disruption-tolerant networks). Section 4.4 then presents an architecture and protocol suite suitable for the most demanding aeronautical environment: highly dynamic, high-velocity multi-hop networks that require the greatest change to past networking architectures, with comparisons to traditional end-to-end transport and routing protocols. Section 4.5 presents selected performance evaluation of this aeronautical protocol suite, with references to further analysis. Finally, Section 4.6 summarizes this chapter. Airborne Network Environment Airborne networks are a class of mobile wireless networks: wireless due to the untethered communication links between aircraft, and mobile due to the movement of aircraft. Depending on the communication paradigm, they may or may not need to be ad hoc networks that self-organize. Table 4.1 shows the key characteristics of airborne network scenarios, ordered in increasing challenge to network protocols. The evolution from current to future network types, described for each scenario below, is depicted in italic font in the last column.

Cross-layer geodiverse protocol stack for resilient multipath transport and routing using OpenFlow

This work describes a cross-layer resilient protocol stack for survivable network communications during regional challenges. The GeoDivRP routing protocol collects network statistics and calculates multiple geodiverse paths; it provides these geodiverse paths upstack to the resilient transport protocol, ResTP, for resilient multipath communications. ResTP provides multiple resilience modes to cope with different network failure conditions. A profile-based challenge model is used to better represent different challenge scenarios. Furthermore, the resilient protocol stack is implemented in network simulator ns-3 and compared to Multipath TCP. Software-defined networking controller is proposed to implement the link failure detection module to increase the cross-layer protocol stack performance. By providing multiple d-distance separated paths, the protocol stack provides better path protection against regional challenges than MPTCP.

Geodiverse Routing Protocol with multipath forwarding compared to MPTCP.

This work presents a comprehensive performance comparison of our cross-layer resilient protocol stack, ResTP-GeoDivRP against Multipath TCP (MPTCP). A profile-based challenge model is used to better represent different failure scenarios. Furthermore, our resilient protocol stack is implemented in the network simulator ns-3 and emulated in the KanREN testbed. The GeoDivRP routing protocol collects network statistics and calculates multiple geodiverse paths; these paths are provided upstack to our resilient transport protocol, ResTP, for resilient multipath communications. By providing multiple geodiverse paths, our ResTP-GeoDivRP protocol stack provides better path protection against regional failures than MPTCP.