TU Darmstadt / ULB / TUbiblio

A Heterogeneous System Architecture for Low-Power Wireless Sensor Nodes in Compute-Intensive Distributed Applications

Engel, Andreas (2016)
A Heterogeneous System Architecture for Low-Power Wireless Sensor Nodes in Compute-Intensive Distributed Applications.
Technische Universität Darmstadt
Ph.D. Thesis, Primary publication

Abstract

Wireless Sensor Networks (WSNs) combine embedded sensing and processing capabilities with a wireless communication infrastructure, thus supporting distributed monitoring applications. WSNs have been investigated for more than three decades, and recent social and industrial developments such as home automation, or the Internet of Things, have increased the commercial relevance of this key technology. The communication bandwidth of the sensor nodes is limited by the transportation media and the restricted energy budget of the nodes. To still keep up with the ever increasing sensor count and sampling rates, the basic data acquisition and collection capabilities of WSNs have been extended with decentralized smart feature extraction and data aggregation algorithms. Energy-efficient processing elements are thus required to meet the ever-growing compute demands of the WSN motes within the available energy budget.

The Hardware-Accelerated Low Power Mote (HaLoMote) is proposed and evaluated in this thesis to address the requirements of compute-intensive WSN applications. It is a heterogeneous system architecture, that combines a Field Programmable Gate Array (FPGA) for hardware-accelerated data aggregation with an IEEE 802.15.4 based Radio Frequency System-on-Chip for the network management and the top-level control of the applications. To properly support Dynamic Power Management (DPM) on the HaLoMote, a Microsemi IGLOO FPGA with a non-volatile configuration storage was chosen for a prototype implementation, called Hardware-Accelerated Low Energy Wireless Embedded Sensor Node (HaLOEWEn). As for every multi-processor architecture, the inter-processor communication and coordination strongly influences the efficiency of the HaLoMote. Therefore, a generic communication framework is proposed in this thesis. It is tightly coupled with the DPM strategy of the HaLoMote, that supports fast transitions between active and idle modes. Low-power sleep periods can thus be scheduled within every sampling cycle, even for sampling rates of hundreds of hertz.

In addition to the development of the heterogeneous system architecture, this thesis focuses on the energy consumption trade-off between wireless data transmission and in-sensor data aggregation. The HaLOEWEn is compared with typical software processors in terms of runtime and energy efficiency in the context of three monitoring applications. The building blocks of these applications comprise hardware-accelerated digital signal processing primitives, lossless data compression, a precise wireless time synchronization protocol, and a transceiver scheduling for contention free information flooding from multiple sources to all network nodes. Most of these concepts are applicable to similar distributed monitoring applications with in-sensor data aggregation.

A Structural Health Monitoring (SHM) application is used for the system level evaluation of the HaLoMote concept. The Random Decrement Technique (RDT) is a particular SHM data aggregation algorithm, which determines the free-decay response of the monitored structure for subsequent modal identification. The hardware-accelerated RDT executed on a HaLOEWEn mote requires only 43 % of the energy that a recent ARM Cortex-M based microcontroller consumes for this algorithm. The functionality of the overall WSN-based SHM system is shown with a laboratory-scale demonstrator. Compared to reference data acquired by a wire-bound laboratory measurement system, the HaLOEWEn network can capture the structural information relevant for the SHM application with less than 1 % deviation.

Item Type: Ph.D. Thesis
Erschienen: 2016
Creators: Engel, Andreas
Type of entry: Primary publication
Title: A Heterogeneous System Architecture for Low-Power Wireless Sensor Nodes in Compute-Intensive Distributed Applications
Language: English
Referees: Koch, Prof. Andreas ; Hochberger, Prof. Christian
Date: 2016
Place of Publication: Darmstadt
Refereed: 17 December 2015
URL / URN: http://tuprints.ulb.tu-darmstadt.de/5778
Abstract:

Wireless Sensor Networks (WSNs) combine embedded sensing and processing capabilities with a wireless communication infrastructure, thus supporting distributed monitoring applications. WSNs have been investigated for more than three decades, and recent social and industrial developments such as home automation, or the Internet of Things, have increased the commercial relevance of this key technology. The communication bandwidth of the sensor nodes is limited by the transportation media and the restricted energy budget of the nodes. To still keep up with the ever increasing sensor count and sampling rates, the basic data acquisition and collection capabilities of WSNs have been extended with decentralized smart feature extraction and data aggregation algorithms. Energy-efficient processing elements are thus required to meet the ever-growing compute demands of the WSN motes within the available energy budget.

The Hardware-Accelerated Low Power Mote (HaLoMote) is proposed and evaluated in this thesis to address the requirements of compute-intensive WSN applications. It is a heterogeneous system architecture, that combines a Field Programmable Gate Array (FPGA) for hardware-accelerated data aggregation with an IEEE 802.15.4 based Radio Frequency System-on-Chip for the network management and the top-level control of the applications. To properly support Dynamic Power Management (DPM) on the HaLoMote, a Microsemi IGLOO FPGA with a non-volatile configuration storage was chosen for a prototype implementation, called Hardware-Accelerated Low Energy Wireless Embedded Sensor Node (HaLOEWEn). As for every multi-processor architecture, the inter-processor communication and coordination strongly influences the efficiency of the HaLoMote. Therefore, a generic communication framework is proposed in this thesis. It is tightly coupled with the DPM strategy of the HaLoMote, that supports fast transitions between active and idle modes. Low-power sleep periods can thus be scheduled within every sampling cycle, even for sampling rates of hundreds of hertz.

In addition to the development of the heterogeneous system architecture, this thesis focuses on the energy consumption trade-off between wireless data transmission and in-sensor data aggregation. The HaLOEWEn is compared with typical software processors in terms of runtime and energy efficiency in the context of three monitoring applications. The building blocks of these applications comprise hardware-accelerated digital signal processing primitives, lossless data compression, a precise wireless time synchronization protocol, and a transceiver scheduling for contention free information flooding from multiple sources to all network nodes. Most of these concepts are applicable to similar distributed monitoring applications with in-sensor data aggregation.

A Structural Health Monitoring (SHM) application is used for the system level evaluation of the HaLoMote concept. The Random Decrement Technique (RDT) is a particular SHM data aggregation algorithm, which determines the free-decay response of the monitored structure for subsequent modal identification. The hardware-accelerated RDT executed on a HaLOEWEn mote requires only 43 % of the energy that a recent ARM Cortex-M based microcontroller consumes for this algorithm. The functionality of the overall WSN-based SHM system is shown with a laboratory-scale demonstrator. Compared to reference data acquired by a wire-bound laboratory measurement system, the HaLOEWEn network can capture the structural information relevant for the SHM application with less than 1 % deviation.

Alternative Abstract:
Alternative abstract Language

Drahtlose Sensornetze (Wireless Sensor Networks, WSNs) kombinieren eingebettete Sensorik und Rechenleistung mit einer drahtlosen Kommunikationsinfrastruktur, wodurch räumlich verteilte Überwachungsanwendungen unterstützt werden. WSNs werden seit mehr als drei Jahrzehnten erforscht, aktuelle soziale und industrielle Trends wie intelligentes Wohnen oder das Internet der Dinge haben aber auch die kommerzielle Bedeutung dieser Schlüsseltechnologie verstärkt. Die übertragbaren Datenmengen sind durch das Transportmedium und die verfügbare Energie der Sensorknoten beschränkt. Um die wachsende Anzahl an Sensoren und die steigenden Abtastraten dennoch zu bewältigen, wurden die ursprünglich als einfache Datenerfassungssysteme ausgelegten WSNs um Fähigkeiten zur dezentralen Datenaggregation erweitert. Um den dadurch ständig wachsenden Bedarf an verteilter Rechenleistung mit den beschränkten Energieressourcen zu realisieren, werden energieeffiziente Recheneinheiten benötigt.

In der vorliegenden Arbeit wird die Hardware-Accelerated Low Power Mote (HaLoMote) Architektur vorgestellt und deren Effizienz für rechenintensive WSN-Anwendungen untersucht. Dabei handelt es sich um eine heterogene Architektur mit einem Field Programmable Gate Array (FPGA) für die Hardware-Beschleunigung von Datenaggregationsalgorithmen und einem Funksystem mit integriertem Mikrocontroller für das Netzwerkmanagement und die übergeordnete Steuerung der Anwendungen. Um eine effiziente Energieverwaltung für die HaLoMote zu ermöglichen, verwendet die prototypische Implementierung namens Hardware-Accelerated Low Energy Wireless Embedded Sensor Node (HaLOEWEn) ein FPGA mit persistentem Konfigurationsspeicher. Wie bei jeder Multiprozessorarchitektur beeinflusst die Interprozessorkommunikation und -koordination auch die Effizienz der HaLoMote. Daher wurde ein anwendungsunabhängiges Kommunikationsschema entwickelt, welches eng mit den Energiesparmechanismen der Plattform verknüpft und auf schnelle Wechsel zwischen Aktiv- und Ruhemodi ausgelegt ist. Dadurch können Schlafphasen innerhalb jedes Abtastzykluses selbst bei Abtastraten von mehreren Hundert Hertz genutzt werden.

Die vorliegende Arbeit untersucht darüber hinaus das Abwägen zwischen der drahtlosen Übertragung von Sensordaten und deren lokaler Aggregation. Dazu wird die HaLOEWEn Plattform mit herkömmlichen Software-Prozessoren bezüglich ihrer Laufzeit- und Energieeffizienz im Rahmen von drei Überwachungsanwendungen verglichen. Die verwendeten Algorithmen kombinieren Hardware-Beschleuniger für digitale Signalverarbeitungsprimitiven und verlustfreie Datenkompression mit einem präzisen Zeitsynchronisationsmechanismus sowie einem Verfahren zum kollisionsfreien Verteilen von Informationen im Netzwerk. Diese allgemeinen Komponenten können für ähnliche verteilte Überwachungsanwendungen mit aufwändiger dezentraler Datenaggregation wiederverwendet werden.

Eine Anwendung aus dem Bereich der Strukturüberwachung (Structural Health Monitoring, SHM) wird für die systemische Evaluation des HaLoMote Konzepts verwendet. Die Random Decrement Technique (RDT) ist ein spezieller Aggregationsalgorithmus, welcher das freie Ausschwingverhalten der überwachten Struktur ermittelt, selbst wenn die eigentliche Anregung der Struktur nicht bekannt ist. Dies ermöglicht eine operative Modalanalyse, welche die Voraussetzung für eine autonome Langzeitüberwachung ist. Die Berechnung der RDT auf der HaLOEWEn Plattform benötigt nur 43 % der Energie, welche ein aktueller ARM Cortex-M Mikrocontroller für den gleichen Algorithmus verbraucht. Um die Funktionsfähigkeit des gesamten WSN-basierten SHM Systems nachzuweisen, wurde ein Demonstrator im Labormaßstab aufgebaut. Im Vergleich zu einem drahtgebundenen Labormesssystem können die wesentlichen Strukturinformationen vom HaLOEWEn Netzwerk mit weniger als 1 % Abweichung erfasst werden.

German
Uncontrolled Keywords: Low-power design, Heterogeneous (hybrid) systems, Interprocessor communications, Dynamic Power Management, Reconfigurable hardware, Wireless sensor networks, Structural Health Monitoring, HaLoMote, HaLOEWEn
URN: urn:nbn:de:tuda-tuprints-57782
Classification DDC: 000 Generalities, computers, information > 004 Computer science
600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Embedded Systems and Applications
LOEWE > LOEWE-Zentren > AdRIA – Centre for Adaptronics – Research, Innovation, Application
LOEWE > LOEWE-Zentren
LOEWE
Date Deposited: 27 Nov 2016 20:55
Last Modified: 27 Nov 2016 20:55
PPN:
Referees: Koch, Prof. Andreas ; Hochberger, Prof. Christian
Refereed / Verteidigung / mdl. Prüfung: 17 December 2015
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details