All analytical and simulation research on ad hoc wireless networks must necessarily model radio propagation using simplifying assumptions. A growing body of research, however, indicates that the behavior of the protocol stack may depend significantly on these underlying assumptions. The standard response to this problem is a call for more realism in designing radio models. But how much realism is enough? This study is the first to approach this question by validating simulator performance (both at the physical and application layers) with the results of real-world data. Referencing an eXtensive set of measurements from a large outdoor routing eXperiment, we start by evaluating the relative realism of common assumptions made in radio model design, identifying those which provide a reasonable approXimation of reality. Although several such investigations have been made for static sensor networks, radio behavior in mobile network deployments is a much less-studied topic. We then reproduce our eXperimental setup in our simulator, and generate the same application-layer metrics under progressively smaller sets of these assumptions. By comparing the simulated outcome to the outcome of our eXperiment, we are able to discern at what point our balance of simplification and realism captures the real behavior of our target environment.

Data centers consume significant amounts of energy. As severs become more energy efficient with various energy saving techniques, the data center network (DCN) has been accounting for 20% or more of the energy consumed by the entire data center. While DCNs are typically provisioned with full bisection bandwidth, DCN traffic demonstrates fluctuating patterns. The objective of this work is to improve the energy efficiency of DCNs during off-peak traffic time by powering off idle devices. Although there exist a number of energy optimization solutions for DCNs, they consider only either the hosts or network, but not both. In this paper, we propose a joint optimization scheme that simultaneously optimizes virtual machine (VM) placement and network flow routing to maximize energy savings, and we also build an OpenFlow based prototype to experimentally demonstrate the effectiveness of our design. First, we formulate the joint optimization problem as an integer linear program, but it is not a practical solution due to high complexity. To practically and effectively combine host and network based optimization, we present a unified representation method that converts the VM placement problem to a routing problem. In addition, to accelerate processing the large number of servers and an even larger number of VMs, we describe a parallelization approach that divides the DCN into clusters for parallel processing. Further, to quickly find efficient paths for flows, we propose a fast topology oriented multipath routing algorithm that uses depth-first search to quickly traverse between hierarchical switch layers and uses the best-fit criterion to maximize flow consolidation. Finally, we have conducted extensive simulations and experiments to compare our design with existing ones. The simulation and experiment results fully demonstrate that our design outperforms existing hostor network-only optimization solutions, and well approximates the ideal linear program.

The Real-Time Immersive Network Simulation Environment (RINSE) simulator is being developed to support large-scale network security preparedness and training exercises, involving hundreds of players and a modeled network composed of hundreds of local-area networks (LANs). The simulator must be able to present a realistic rendering of network behavior as attacks are launched and players diagnose events and try counter measures to keep network services operating. The authors describe the architecture and function of RINSE and outline how techniques such as multiresolution traffic modeling, multiresolution attack models, and new routing simulation methods are used to address the scalability challenges of this application. They also describe in more detail new work on CPU/memory models necessary for the exercise scenarios and a latency absorption technique that will help when extending the range of client tools usable by the players.

The fat tree topology with multipath capability has been used in many recent data center networks (DCNs) for increased bandwidth and fault tolerance. Traditional routing protocols have only limited support for multipath routing, and cannot fully utilize the available bandwidth in such networks. In this paper, we study multipath routing for fat tree networks. We formulate the problem as a linear program and prove its NP-completeness. We propose a practical solution, which takes advantage of the emerging software-defined networking paradigm. Our algorithm relies on a central controller to collect necessary network state information in order to make optimized routing decisions. We implemented the algorithm as an OpenFlow controller module and validated it with Mininet emulation. We also developed a fluid-based DCN simulator and conducted experiments, which show that our algorithm outperforms the traditional multipath algorithm based on random assignments, both in terms of increased throughput and in reduced end-to-end delay.