James P. G. Sterbenz

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.

Epidemic routing protocol implementation in ns-3

Routing protocols play a significant role in the overall performance of ad-hoc wireless networks. Several routing protocols have been proposed for ad hoc environments. Any new proposed protocol should be compared with other routing protocols to show its performance under several scenarios. Epidemic routing was one of the first routing schemes proposed for DTNs (delay-tolerant networks). In this paper, we present our implementation of the epidemic routing protocol in the ns-3 simulator. We analyse its performance and compare with the previous ns-2 implementation. Our analysis conforms the results of the previous ns-2 implementation. Moreover, we compare our epidemic implementation to other MANET routing protocols in a delay tolerant environment and we show that epidemic routing outperforms other MANET routing protocols in terms of packet delivery at the expense of overhead and delay.

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.

Evaluation and improvement of network resilience against attacks using graph spectral metrics

Measuring and improving communication network resilience against targeted attacks and random failures is an important aspect of network design. There are a plethora of proposed graph metrics to predict network resilience against such attacks. In this paper, we investigate a set of graph spectral-robustness metrics and evaluate their accuracy in predicating network resilience against node attacks. We use two datasets of graphs: baseline and random graphs to study these graph spectral robustness metrics. For each baseline graph, we apply several centrality-based attacks while we measuring the network resilience in terms of flow robustness. Using a large number of random graphs, we show the accuracy of each robustness metric to predict the graph resilience against such attacks. Furthermore, we improve the topology resilience of three real-world physical graphs via adding a set of links to maximize a given spectral metric. Among these studied metrics, we show that the network criticality robustness metric is the most accurate in predicting the behavior of a given network against centrality-based attacks. Moreover, we show that maximizing network criticality of a given graph yields the most resilient network against such attacks.

Multilevel IoT Model for Smart Cities Resilience

Currently, the Internet of Things (IoT) is in the center of attention as an emerging technology among researchers and stakeholders. It is assumed that it is a key enabler for other technologies such as smart cities, smart health, smart grids, and smart transportation. Although the concept of the IoT is generally understood among researchers, there is no standard model representing this technology, particularly with respect to network architecture, which will be necessary to apply existing and emerging resilience and survivability techniques. Additionally, security and privacy have not yet received the needed attention. In this paper we propose a new multilevel IoT network-centric model, and discuss its applicability to the application of resilience and survivability.

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.

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.