Luiz Magalhaes

Transport level mechanisms for bandwidth aggregation on mobile hosts

Present mobile computing does not support the simultaneous use of multiple heterogeneous network interfaces for a single transport layer connection. We describe a solution for channel aggregation at the transport layer, which provides increased bandwidth to mobile nodes. We present R-MTP (reliable multiplexing transport protocol), a rate-based reliable transport protocol capable of multiplexing data from a single application data stream across multiple network interfaces. Due to the lossy nature of wireless links in mobile environments, R-MTP tracks packet interarrival time for discrimination between congestion-based and transmission-based losses as well as better bandwidth estimation. The challenges to such a reliable protocol lie in the coordination of packets across streams with varying channel characteristics. Our experimental results validate R-MTPs bandwidth estimation and loss characterization techniques. Successful bandwidth aggregation is demonstrated in ideal and lossy environments.

A cooperative approach to user mobility

We propose a networking model that treats a users set of personal devices as a MObile grouPEd Device, a MOPED, which appears as a single entity to the rest of the Internet. All communication for a user is directed to this point of presence. As the user moves through different environments, the devices cooperate to provide the user with access to all available communication resources. We present the basic networking functionality necessary to enable the operation of MOPEDs and their integration into the Internet. We introduce a middleware layer to extend IP routing to work with MOPEDs and a lightweight IP encapsulation protocol, Multipath Routing enCAPsulation (MRCAP), used to implement that middleware.

MMTP — multimedia multiplexing transport protocol

Multimedia data has special requirements that are hard to be met on mobile hosts due to potentially low bandwidth and disruptions due to host mobility. Such limited communication capabilities of mobile hosts can be offset by the simultaneous use of multiple link layer technologies. MMTP is a member of a suite of protocols that share the novel characteristic of aggregating bandwidth from multiple link-layer channels. The use of multiple channels to transport user data provides five key benefits: (1) a fatter pipe,(2) a fast feedback path, (3) the retransmission of selected lost messages, without delaying the playout of the data stream, (4) less sensitivity to minor bandwidth fluctuations on any one individual channel, and (5) smooth vertical handoffs for active data streams.MMTP is a rate-based protocol designed for transferring multimedia data on mobile systems, and makes simultaneous use of every communication channel available to send data at the required rate. Transmission in MMTP is governed by two mechanisms. The first is a set of rate control protocols associated with each outgoing channel. The second is a scheduling algorithm that places incoming packets on the appropriate channel. MMTP is link-layer aware protocol that uses bandwidth estimation for congestion control, and relays to the application information needed for rate adaptation. In this paper, we show that the quality of data transmission can be improved through the use of MMTP through experimental comparisons with data transmitted via UDP. We also demonstrate the economy of bandwidth: MMTP only sends packets that it estimates will arrive within the packet deadline, thus decreasing the number of late packets that will be discarded at the receiver.

End-to-end inverse multiplexing for mobile hosts

This paper presents a framework for the creation of transport protocols for mobile hosts that use multiple link layers simultaneously for the same connection. This abstraction provides an end-to-end transport layer channel between two applications that do not have to be aware of host mobility. The channel is composed of multiple network layer sub-channels. A sub-channel is an end-to-end network layer connection that is mapped to one physical interface. Inverse multiplexing is used at the transport level to divide application data into sub-channels, and a rate-based transmission mechanism provides congestion avoidance. The same mechanism is used to differentiate transmission losses from congestion losses, resulting in good throughput in lossy wireless links. Experimental results for two protocols created using this framework validate our design choices.

A comprehensive analysis on the use of schedule-based asynchronous duty cycling in wireless sensor networks

Duty cycling is a fundamental mechanism for battery-operated ad hoc networks, such as Wireless Sensor Networks, Delay Tolerant Networks, and solar-powered Wireless Mesh Networks. Because of its utter importance, it has been proposed in a wide variety of flavors, one of the most prominent being that of the asynchronous mechanisms. In particular, schedule-based duty cycling has earned attention due to its low requirements and simplicity of implementation. Despite its potential, a comprehensive and realistic study on the neighbor discovery latency that results from schedule-based asynchronous duty cycling is still missing. This paper fills in this gap, by providing accurate models for major schedule-based mechanisms: Block Designs, Quorum systems and Disco. The provided models consider message loss probability and yield more precise estimations than traditional models. Based on this improved accuracy, the relative latency, a new metric for studying the trade off between latency and power, is proposed as a substitute to the power-latency product. Finally, a practical mapping of which schedule is more adequate for given requirements of latency, energy savings and link reliability is presented.

Centralized channel allocation algorithm for IEEE 802.11 networks

The sharing of the wireless spectrum is a major concern of network administrators. Access points in the same network interfere with each other, degrading the aggregate performance of stations. Moreover, wireless networks usually coexist with others applications that share the same spectrum and negatively impact the packet transmission. To overcome these issues, we propose the channel allocation algorithm designed for central controllers of infra-structured IEEE 802.11 networks. Our algorithm reduces the interference in controlled access points through the dynamic choice of their operating channels and, unlike other proposals, was designed to operate in a network composed of low cost devices from different brands, and open source software. Furthermore, we also consider the interference caused by unmanaged networks, adjusting the settings of the managed access points according to the wireless environment. The proposal was implemented and evaluated in an open testbed, and the results show that our controller efficiently manages the spectrum with low cost equipment and a low complexity algorithm.

Nested block designs

In schedule-based asynchronous duty cycling, nodes activate and deactivate their radio interfaces according to a specially designed wakeup schedule, which guarantees overlapping active time between nodes, irrespective of their synchronization offsets. When compared to synchronous duty cycling, such an approach has the advantage of being simple to implement, eliminating the need for synchronization protocols, complex computations or extra hardware. However, among published proposals, there is no single schedule-based mechanism that provides the lowest latency in all scenarios, when considering duty cycling symmetry, frame delivery probability and duty cycling rate. This paper introduces nested block designs, a new schedule that extends the use of block designs to application scenarios for which they were previously not possible or not as efficient as other schedules. Nested block designs provide the lowest latency among known schedule-based asynchronous duty cycling mechanisms for a wide range of applications, as confirmed by analytical models and real implementations on WSN motes.

Designing a rate-based transport protocol for wired-wireless networks

A large majority of the Internet traffic relies on TCP as its transport protocol. In future, as the edge of the Internet continues to extend over the wireless medium, TCP (or its close variants) may not prove to be appropriate. The key reason is in TCP’s inability to discriminate congestion losses from transmission losses. Since transmission losses are frequent in wireless networks, the penalty from loss misclassification can become high, leading to performance degradation. This paper presents an eXtended Rate-based Transport Protocol (XRTP), designed to support communication over lossy wireless media. We depart from the ack-based rate control paradigm. Instead, we try to estimate the network conditions by injecting probe packets at the sender, and then observing the spacing between packets that arrive at the receiver. We show that these observations can be useful indicators of available bandwidth, network congestion, and even the cause of packet loss. The inferences from the observations are utilized to regulate the transmission rate at the sender, leading to desirable properties of congestion control and loss discrimination. Simulation results show the efficacy of our proposed rate-based protocol in lossy wireless environments.

FIT@BR - a Future Internet Testbed in Brazil

A major objective of the Brazil-EU FIBRE project is the deployment in Brazil of FIT@BR, a wide-area network testbed to support user experimentation in the design and validation of new network architectures and applications. In such a testbed, a high degree of automated resource sharing between experimenters is required, and the testbed itself must be instrumented so that precise measurements and accounting of both user and facility resources may be carried out. In this article, we describe the design and implementation of the Control and Monitoring Framework (CMF) for the FIT@BR testbed, which is based on three CMFs developed in existing testbed projects. In order to take best advantage of different testbed functionalities at different sites, FIT@BR is being created as a federated testbed, which will facilitate future interoperation with international initiatives.

Neighbor discovery time in schedule-based asynchronous duty cycling

In schedule-based asynchronous duty cycling, nodes alternate between active and inactive time slots in cycles that guarantee the occurrence of overlapping active time, therefore ensuring that neighbors will have opportunities to communicate. Among these schedules, Block Designs provide the minimal duty cycle for a given number of time slots [1]. However, there exists no precise estimation model for the resulting NDT when such schedules are employed. This paper provides an accurate model for nodes operating under Block Design schedules.