Roman Lim

FlockLab: a testbed for distributed, synchronized tracing and profiling of wireless embedded systems

Testbeds are indispensable for debugging and evaluating wireless embedded systems. While existing testbeds provide ample opportunities for realistic, large-scale experiments, they are limited in their ability to closely observe and control the distributed operation of resource-constrained nodes-access to the nodes is restricted to the serial port. This paper presents FlockLab, a testbed that overcomes this limitation by allowing multiple services to run simultaneously and synchronously against all nodes under test in addition to the traditional serial port service: tracing of GPIO pins to record logical events occurring on a node, actuation of GPIO pins to trigger actions on a node, and high-resolution power profiling. FlockLabs accurate timing information in the low microsecond range enables logical events to be correlated with power samples, thus providing a previously unattained level of visibility into the distributed behavior of wireless embedded systems. In this paper, we describe FlockLabs design, benchmark its performance, and demonstrate its capabilities through several real-world test cases.

Learning from sensor network data

Within the PermaSense project, two wireless sensor networks have been deployed for a long-term operation in the Swiss Alps. For enabling state-of-the-art permafrost research based on the collected data, highest possible data quality and yield have to be ensured. But, the operation of wireless sensors networks remains a hard research problem. Firstly, deployed wireless sensors networks are subject to continuous changes. Second, there are scenarios that can only be tested in the field as the capabilities of testbeds are too limited. Basically, it is not possible to test for many months before deploying in the field. In this poster, we present an analysis of our data that has been collected over nine months. In addition to describing our system design and methods, we also share our experiences from discovered severe incidences.

Comparative performance analysis of the PermaDozer protocol in diverse deployments

In this paper, we present a performance analysis of the communication stack of the PermaDozer application. Our offline analysis is based on long-term performance data from three diverse real-world wireless sensor network deployments. Two of the deployments considered are located in the Swiss mountains at 3.500 meters a.s.l., the third deployment is located along a river in the Swiss midlands. Apart from climatic differences, the three deployments also vary in network size, network density, node placement, and type and quantity of RF interference. From September 2008 to May 2011 more than 99.6 million WSN packets have been collected serving as the dataset. All three deployments are based on the same software and hardware. This allows us to comparatively study the performance of the PermaDozer protocol under different deployment settings and environmental conditions. For the period between June 2010 and May 2011, our networks achieved a data yield of ≥ 99.5%. But, we can also clearly notice that achieving this performance requires varying effort in terms of radio duty cycle resulting in different power consumption and network lifetime.

The FlockLab testbed architecture

A vital factor for a successful deployment of sensor nodes is testing of all system aspects in a realistic setup. This work presents a testbed architecture which allows for detailed monitoring and stimulation of a wireless sensor node. In particular, time-accurate state extraction and power measurements are provided in a distributed, yet synchronized context. The FlockLab testbed architecture provides a distributed lab instrument, where detailed observations of every sensor node enable thorough testing. Software services allow for formulating testcases and reliable test data collection.

Bolt: A Stateful Processor Interconnect

The wireless sensor network community is currently undergoing a platform paradigm shift, moving away from classical single-processor motes toward heterogeneous multi-processor architectures. These emerging platforms promise efficient concurrent processing with energy-proportional system performance. The use of shared interconnects and shared memory for inter-processor communication, however, causes interference in the time, power, and clock domains, which prevents designers from fully harnessing these benefits. We thus designed Bolt, the first ultra-low-power processor interconnect for the compositional construction of heterogeneous wireless embedded platforms. This paper presents the architectural blueprint for interconnecting two independent processors, while enabling asynchronous inter-processor communication with predictable run-time behavior. We detail a prototype implementation of Bolt, and apply formal methods to analytically derive bounds on the execution time of its message passing operations. Experiments with a custom-built dual-processor platform show that our Bolt prototype incurs a negligible power overhead relative to state-of-the-art platforms, offers predictable message passing with empirical bounds that match the analytical ones to within a few clock cycles, and achieves a high throughput of up to 3.3 Mbps.

Automated Wireless Sensor Network Testing

The design of distributed, wireless, and embedded system is a tedious and error-prone process. Experiences from previous real-world wireless sensor network (WSN) deployments strongly indicate that it is vital to follow a systematic design approach to satisfy all design requirements including robustness and reliability. Such a design methodology needs to include an end-to-end testing methodology. The proposed framework for WSN testing allows to apply distributed unit testing concepts in the development process. The tool flow decreases test time and allows for monitoring the correctness of the implementation throughout the development process.

EvAnT: Analysis and Checking of Event Traces for Wireless Sensor Networks

Testing and verification methodologies for wireless sensor networks (WSN) systems in pre-deployment are vital for a successful deployment. Increased visibility of the internal state of a WSN application is established by instrumenting the application for logging execution traces at runtime. While the interpretation of the event traces is application-specific, a common method for analysis can be devised. This method should allow for a concise formulation of explorative queries to determine the occurrence and the cause of functional or performance problems. The contribution of this paper is an event analysis methodology that is implemented in the EvAnT framework. EvAnT allows for specifying queries that are executed on the collected traces. EvAnT is specifically tailored to WSN testing and debugging. We demonstrate the applicability of EvAnT by a case study in a building monitoring project.

A testbed for fine-grained tracing of time sensitive behavior in wireless sensor networks

This paper introduces TRACELAB, a new testbed architecture that allows for fine-grained tracing of time sensitive behavior of low-power wireless embedded systems. Such traces help to systematically analyze code execution to find software errors, measure bounds for execution times, or to verify functional program properties. TRACELAB builds on the idea of GPIO tracing: by including short GPIO instructions into node applications, the program behavior can be traced in a minimally invasive manner, simultaneously on all observed nodes. TRACELAB enables fine-grained distributed tracing by overcoming the limits of existing testbed architectures with respect to timing accuracy and peak event rates. For that purpose, an existing testbed design is extended with a new data acquisition system that includes an FPGA chip for fast and deterministic data handling. To faithfully align distributed trace measurements, TRACELAB integrates a highly accurate wireless time distribution network. We build 31 TRACELAB observers and deploy them in an office environment and outdoors. Measurements using GPS precision timing show that TRACELAB (i) is able to trace events at rates of up to 108 events/s and (ii) aligns traces from different locations within 1 μs with an empirical probability of 99.9 %.

Distributed and synchronized measurements with FlockLab

Developing, testing, debugging, and evaluating communication protocols for low-power wireless networks is a long and cumbersome task. Simulators can be helpful in the early stages of development, but their models of hardware components and the wireless channel are often rather simplistic and hence cannot substitute experiments on real sensor node platforms. The resources available on common platforms are however very limited, and so are the possibilities for non-intrusive debugging and testing. With most existing testbeds it is only possible to collect information from the serial port, which requires adding highly intrusive logging statements that alter the timing behavior of the software running on the nodes. This is particularly detrimental to the operation of time-critical components, such as radio drivers, media access control (MAC) protocols, and certain flooding protocols [2], hindering their testbed-assisted development.

Measurement and validation of energy harvesting IoT devices

With the appearance of wearable devices and the IoT, energy harvesting nodes are becoming more and more important. The design and evaluation of these small standalone sensors and actuators, which harvest limited amounts of energy, requires novel tools and methods. Fast and accurate measurement systems are required to capture the rapidly changing harvesting scenarios and characterize leakage currents and energy efficiencies. The need for real-world experiments creates a demand for compact and portable equipment to perform in-situ power measurements and environmental logging. This work presents the RocketLogger, a hand-held measurement device that combines both properties: portability and accuracy. The custom analog front-end allows logging at sampling rates up to 64 kSPS. The fast range switching within 1.4 μ8 guarantees continuous power measurements starting from 4pW at 1 mV up to 2.75 W at 5.5 V. The software provides remote control and manages data acquisition of up to 13Mb/ sec in real-time. We extensively characterize the RocketLoggers performance, demonstrate the need for its properties in three use-cases at different stages of the system design flow, and show its advantages in measuring and validating new harvesting-driven devices for the IoT.