Testbed

About: Testbed is a research topic. Over the lifetime, 10858 publications have been published within this topic receiving 147147 citations. The topic is also known as: test bed.

Reinforcement Learning for Satellite Communications: From LEO to Deep Space Operations

Abstract: The National Aeronautics and Space Administration (NASA) is in the midst of defining and developing the future space and ground architecture for the coming decades to return science and exploration discovery data back to investigators on Earth. Optimizing the data return from these missions requires planning, design, standards, and operations coordinated from formulation and development throughout the mission. The use of automation enhanced by cognition and machine learning are potential methods for optimizing data return, reducing costs of operations, and helping manage the complexity of the automated systems. In this article, we discuss the potential role of machine learning in the linkto- link aspect of the communication systems. An experiment using NASA's Space Communication and Navigation Testbed onboard the International Space Station and the ground station located at NASA John H. Glenn Research Center demonstrates for the first time the benefits and challenges of applying machine learning to space links in the actual flight environment. The experiment used machine learning decisions to configure a space link from the ISS-based testbed to the ground station to achieve multiple objectives related to data throughput, bandwidth, and power. Aspects of the specific neural-network-based reinforcement learning algorithm formation and on-orbit testing are discussed.

Workload and Failure Characterization on a Large-Scale Federated Testbed

Abstract: Recently, a number of federated distributed computational and communication infrastructures have emerged, including the Grid, PlanetLab, and Content Distribution Networks. In these environments, mutually distrustful autonomous domains pool resources together for their mutual benefit, for instance to gain access to: unique computational resources, multiple vantage points on the network, or more computation than available locally. Key challenges for such federated infrastructures include resource allocation, scheduling, and constructing highly available services in the face of faulty end hosts and unpredictable network behavior. Developing such appropriate mechanisms and policies requires an understanding of the usage characteristics and operating environment of the target environment. In this paper, we present a detailed characterization of the actual use of the PlanetLab network testbed. PlanetLab consists of 240 nodes spread across 100 autonomous domains with over 500 active users. Using a variety of measurement tools, we present a three-month study on the network, CPU, memory and disk usage of individual PlanetLab nodes and sites. On the consumer side, we further characterize the consumption of individual users. Next, we present results on the availability and reliability of system nodes and the network interconnecting them. Finally, we discuss the implications of our measurements for emerging federated environments.

A Wireless Sensor Network Testbed

Abstract: Key design requirements for wireless sensor network (WSN) applications revolve around long battery life, low cost, small footprint and mesh-networking in supporting communication between large numbers of devices in an interoperable and multi-application environment. This paper presents a WSN testbed that aims to facilitate the developments and experiments of different routing algorithms. Numerous adaptive routing algorithms are implemented to offer self-healing capability for a wide range of WSN applications. Senor nodes in the network can connect together and to sensor gateways in star, mesh, and hybrid topologies. When any sensor node fails due to battery drain, physical destruction, hardware and/or software issues, etc, the network will dynamically route active connections around isolated network segments in order to minimize service interruption.

Network mobility and protocol interoperability in ad hoc networks

Abstract: The integration of various network-level functions, including routing, management, and security, is critical to the efficient operation of a mobile ad hoc network. In this article we focus on network mobility (rather than node mobility), implying the movement of entire subnetworks with respect to one another, while individual users initially associated with one such subnetwork may also move to other domains. One example is a battlefield network that includes ships, aircraft, and ground troops. In this "network of networks", subnets (e.g. shipboard networks) may be interconnected via a terrestrial mobile wireless network (e.g., between moving ships). We discuss the design and implementation of a new ad hoc routing protocol, a suite of solutions for policy-based network management, and approaches for key management and deployment of IPsec in a MANET. These solutions, in turn, are integrated with real-time middleware, a secure radio link, and a topology monitoring tool. We briefly describe each component of the solution, and focus on the challenges and approaches to integrating these components into a cohesive system to support network mobility. We evaluate the effectiveness of the system through experiments conducted in a wireless ad hoc testbed.

RAN Resource Usage Prediction for a 5G Slice Broker

Abstract: Network slicing will allow 5G network operators to offer a diverse set of services over a shared physical infrastructure. We focus on supporting the operation of the Radio Access Network (RAN) slice broker, which maps slice requirements into allocation of Physical Resource Blocks (PRBs). We first develop a new metric, REVA, based on the number of PRBs available to a single Very Active bearer. REVA is independent of channel conditions and allows easy derivation of an individual wireless link's throughput. In order for the slice broker to efficiently utilize the RAN, there is a need for reliable and short term prediction of resource usage by a slice. To support such prediction, we construct an LTE testbed and develop custom additions to the scheduler. Using data collected from the testbed, we compute REVA and develop a realistic time series prediction model for REVA. Specifically, we present the X-LSTM prediction model, based upon Long Short-Term Memory (LSTM) neural networks. Evaluated with data collected in the testbed, X-LSTM outperforms Autoregressive Integrated Moving Average Model (ARIMA) and LSTM neural networks by up to 31%. X-LSTM also achieves over 91% accuracy in predicting REVA. By using X-LSTM to predict future usage, a slice broker is more adept to provision a slice and reduce over-provisioning and SLA violation costs by more than 10% in comparison to LSTM and ARIMA.