4.6 Article

Using SRAM Based FPGAs for Power-Aware High Performance Wireless Sensor Networks

Journal

SENSORS
Volume 12, Issue 3, Pages 2667-2692

Publisher

MDPI
DOI: 10.3390/s120302667

Keywords

wireless sensor networks (WSNs); FPGA; dynamic and partial reconfiguration (DPR); energy efficiency

Ask authors/readers for more resources

While for years traditional wireless sensor nodes have been based on ultra-low power microcontrollers with sufficient but limited computing power, the complexity and number of tasks of today's applications are constantly increasing. Increasing the node duty cycle is not feasible in all cases, so in many cases more computing power is required. This extra computing power may be achieved by either more powerful microcontrollers, though more power consumption or, in general, any solution capable of accelerating task execution. At this point, the use of hardware based, and in particular FPGA solutions, might appear as a candidate technology, since though power use is higher compared with lower power devices, execution time is reduced, so energy could be reduced overall. In order to demonstrate this, an innovative WSN node architecture is proposed. This architecture is based on a high performance high capacity state-of-the-art FPGA, which combines the advantages of the intrinsic acceleration provided by the parallelism of hardware devices, the use of partial reconfiguration capabilities, as well as a careful power-aware management system, to show that energy savings for certain higher-end applications can be achieved. Finally, comprehensive tests have been done to validate the platform in terms of performance and power consumption, to proof that better energy efficiency compared to processor based solutions can be achieved, for instance, when encryption is imposed by the application requirements.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Computer Science, Information Systems

Lossy Hyperspectral Image Compression on a Reconfigurable and Fault-Tolerant FPGA-Based Adaptive Computing Platform

Yubal Barrios, Alfonso Rodriguez, Antonio Sanchez, Arturo Perez, Sebastian Lopez, Andres Otero, Eduardo de la Torre, Roberto Sarmiento

ELECTRONICS (2020)

Article Computer Science, Information Systems

A Machine-Learning-Based Distributed System for Fault Diagnosis With Scalable Detection Quality in Industrial IoT

Rodrigo Marino, Cristian Wisultschew, Andres Otero, Jose M. Lanza-Gutierrez, Jorge Portilla, Eduardo de la Torre

Summary: This article presents a machine learning-based methodology for fault detection in continuous processes, using a hybrid feature selection approach to select the most representative sensors and achieve high-quality fault identification. The proposed technique follows a distributed approach, overcoming limitations of centralized methods. Experimental results show that the methodology provides state-of-the-art detection quality for TEP fault-detection, with significantly lower latency and feature usage compared to other implementations. The scalability of the framework allows for optimal implementation selection based on application needs.

IEEE INTERNET OF THINGS JOURNAL (2021)

Article Engineering, Electrical & Electronic

A Machine Learning-Based Methodology for in-Process Fluid Characterization With Photonic Sensors

Rodrigo Marino, Sergio Quintero, Andres Otero, Jose M. Lanza-Gutierrez, Miguel Holgado

Summary: This research presents a new methodology for real-time fluid characterization using machine learning techniques, integrating multi-dimensional photonic sensors into chemical processes in line with the Industry 4.0 paradigm. The method also includes a novel feature selection strategy that significantly reduces energy consumption while maintaining detection accuracy.

IEEE SENSORS JOURNAL (2021)

Article Computer Science, Hardware & Architecture

Multi-grain reconfigurable and scalable overlays for hardware accelerator composition

Rafael Zamacola, Andres Otero, Eduardo de la Torre

Summary: In this study, a dynamically multi-grain reconfigurable and scalable overlay architecture is built using reconfigurable SRAM-based FPGAs, allowing for real-time reconfiguration of the overlay composition, adjustment of overlay size to free up resources, and adaptation to variable computation demands. The overlay utilizes two different dynamic partial reconfiguration granularities - medium grain for composing processing elements and fine grain for mapping applications onto the overlay. The overlay has been successfully integrated into an SoC and an automated toolchain is proposed for offloading computing-intensive parts to hardware.

JOURNAL OF SYSTEMS ARCHITECTURE (2021)

Article Engineering, Electrical & Electronic

Characterizing Deep Neural Networks on Edge Computing Systems for Object Classification in 3D Point Clouds

Cristian Wisultschew, Alejandro Perez, Andres Otero, Gabriel Mujica, Jorge Portilla

Summary: The shift of computing from the cloud to the edge of the Internet of Things is influencing deep learning applications. Moving intelligence closer to the point of need has advantages in terms of performance, power consumption, security, and privacy. However, dealing with massive data generated by data sources such as LIDAR sensors becomes challenging for edge devices, especially when heavy processing algorithms like deep neural networks are selected. This work demonstrates the feasibility of processing point cloud-based sensors at the edge using deep neural networks, thanks to new devices with high computing capacity and reduced power consumption. Evaluation of different edge processing architectures shows that neural accelerators with integrated host CPUs provide the best trade-off between power consumption and performance, making them an ideal solution for IoT applications at the edge level.

IEEE SENSORS JOURNAL (2022)

Article Computer Science, Hardware & Architecture

Exploiting Hardware-Based Data-Parallel and Multithreading Models for Smart Edge Computing in Reconfigurable FPGAs

Alfonso Rodriguez, Andres Otero, Marco Platzner, Eduardo de la Torre

Summary: Current edge computing systems in complex application scenarios require the use of heterogeneous hardware/software platforms to meet changing requirements. However, the lack of unified software-driven programming models limits the efficient deployment of multi-purpose hardware-accelerated solutions. Additionally, edge computing systems face challenges in operating under diverse conditions.

IEEE TRANSACTIONS ON COMPUTERS (2022)

Article Computer Science, Information Systems

Internet of Things in Sport Training: Application of a Rowing Propulsion Monitoring System

Remy Castro, Gabriel Mujica, Jorge Portilla

Summary: This research proposes a low-cost rowing propulsion monitoring system based on IoT technology, which can help analyze and optimize the performance of rowers. By integrating various sensing, communication, and data processing technologies, the system provides accurate real-time information and valuable technical support for rowers and coaches to define specific optimization profiles and improvement targets.

IEEE INTERNET OF THINGS JOURNAL (2022)

Article Computer Science, Information Systems

Analysis of the NTRU Post-Quantum Cryptographic Scheme in Constrained IoT Edge Devices

Jaime Senor, Jorge Portilla, Gabriel Mujica

Summary: The article discusses the significance of post-quantum cryptography in protecting modern public-key encryption from potential attacks by quantum computers. It evaluates the performance of NTRU in the context of IoT, showing its suitability for wireless sensor networks designed with modern microcontrollers.

IEEE INTERNET OF THINGS JOURNAL (2022)

Article Computer Science, Information Systems

Synthetic LiDAR-Labeled Data Set Generation to Train Deep Neural Networks for Object Classification in IoT at the Edge

Cristian Wisultschew, Rogelio Hernandez, Carlos Pastor, Jorge Portilla

Summary: LiDAR sensors are increasingly popular in IoT object detection due to their ability to provide precise distances, but manually generating data sets for deep learning is time-consuming and costly. This article proposes a method using a 3D simulator to automatically generate point cloud data sets for any LiDAR model, which can simulate custom scenarios for specific application requirements.

IEEE INTERNET OF THINGS JOURNAL (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Run-Time Monitoring and ML-Based Modeling in Reconfigurable Multi-Accelerator Systems

Juan Encinas, Alfonso Rodriguez, Andres Otero, Eduardo De la Torre

Summary: This paper applies machine learning techniques to extract predictive models of multiple hardware accelerators' performance, which are used to optimize system configuration under specific timing and power constraints. Additionally, a non-intrusive integrated instrumentation tool is proposed for measuring power consumption and execution performance in FPGA-based systems.

2021 XXXVI CONFERENCE ON DESIGN OF CIRCUITS AND INTEGRATED SYSTEMS (DCIS21) (2021)

Article Computer Science, Information Systems

Internet of Things in the Railway Domain: Edge Sensing System Based on Solid-State LIDAR and Fuzzy Clustering for Virtual Coupling

Gabriel Mujica, Javier Henche, Jorge Portilla

Summary: Recent advances in wireless communication, sensing, and processing technologies have enabled new research and innovation opportunities in areas such as Industry 4.0, Smart Cities, and Intelligent Transportation Systems. One particular area of focus is on the railway domain where the concept of Railway Virtual Coupling aims to improve capacity and efficiency through reducing the distance between trains and enhancing communication systems. The implementation of a Solid-State LIDAR based sensing system, coupled with IoT edge hardware and fuzzy clustering approach, has been tested in a real railway scenario to support accurate distance detection and virtual coupling maneuvers.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

3D-LIDAR Based Object Detection and Tracking on the Edge of IoT for Railway Level Crossing

Cristian Wisultschew, Gabriel Mujica, Jose Manuel Lanza-Gutierrez, Jorge Portilla

Summary: This paper proposes an edge IoT hardware platform implementation for detecting and tracking objects in a railway level crossing scenario, utilizing a low-resolution 3D 16-channel LIDAR as the sensor. The processing element of the system is located as close as possible to the sensor to improve latency, privacy, and avoid bandwidth limitations. A lightweight object detection and tracking algorithm is introduced to handle the large amount of information provided by the LIDAR, enabling real-time specifications to be met.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

An Integrated Approach and Tool Support for the Design of FPGA-Based Multi-Grain Reconfigurable Systems

Rafael Zamacola, Andres Otero, Alberto Garcia, Eduardo De La Torre

IEEE ACCESS (2020)

No Data Available