Sensor networks with battery-powered nodes can seldom simultaneously meet the design goals of lifetime, cost, sensing reliability and sensing and transmission coverage. Energy-harvesting, converting ambient energy to electrical energy, has emerged as an alternative to power sensor nodes. By exploiting recharge opportunities and tuning performance parameters based on current and expected energy levels, energy harvesting sensor nodes have the potential to address the conflicting design goals of lifetime and performance. This paper surveys various aspects of energy harvesting sensor systems- architecture, energy sources and storage technologies and examples of harvesting-based nodes and applications. The study also discusses the implications of recharge opportunities on sensor node operation and design of sensor network solutions.

Energy Harvesting Sensor Nodes: Survey and Implications

Low power wide area (LPWA) networks are attracting a lot of attention primarily because of their ability to offer affordable connectivity to the low-power devices distributed over very large geographical areas. In realizing the vision of the Internet of Things, LPWA technologies complement and sometimes supersede the conventional cellular and short range wireless technologies in performance for various emerging smart city and machine-to-machine applications. This review paper presents the design goals and the techniques, which different LPWA technologies exploit to offer wide-area coverage to low-power devices at the expense of low data rates. We survey several emerging LPWA technologies and the standardization activities carried out by different standards development organizations (e.g., IEEE, IETF, 3GPP, ETSI) as well as the industrial consortia built around individual LPWA technologies (e.g., LoRa Alliance, Weightless-SIG, and Dash7 alliance). We further note that LPWA technologies adopt similar approaches, thus sharing similar limitations and challenges. This paper expands on these research challenges and identifies potential directions to address them. While the proprietary LPWA technologies are already hitting the market with large nationwide roll-outs, this paper encourages an active engagement of the research community in solving problems that will shape the connectivity of tens of billions of devices in the next decade.

Low Power Wide Area Networks: An Overview

In this paper we discuss a selection of promising and interesting research areas in the design of protocols and systems for wireless industrial communications. We have selected topics that have either emerged as hot topics in the industrial communications community in the last few years (like wireless sensor networks), or which could be worthwhile research topics in the next few years (for example cooperative diversity techniques for error control, cognitive radio/opportunistic spectrum access for mitigation of external interferences).

/pdf/recent-and-emerging-topics-in-wireless-industrial-2rsgyci4x6.pdf

Recent and Emerging Topics in Wireless Industrial Communications: A Selection

Computer communications

Wireless sensor networks (WSNs) research has pre-dominantly assumed the use of a portable and limited energy source, viz. batteries, to power sensors. Without energy, a sensor is essentially useless and cannot contribute to the utility of the network as a whole. Consequently, substantial research efforts have been spent on designing energy-efficient networking protocols to maximize the lifetime of WSNs. However, there are emerging WSN applications where sensors are required to operate for much longer durations (like years or even decades) after they are deployed. Examples include in-situ environmental/habitat monitoring and structural health monitoring of critical infrastructures and buildings, where batteries are hard (or impossible) to replace/recharge. Lately, an alternative to powering WSNs is being actively studied, which is to convert the ambient energy from the environment into electricity to power the sensor nodes. While renewable energy technology is not new (e.g., solar and wind) the systems in use are far too large for WSNs. Those small enough for use in wireless sensors are most likely able to provide only enough energy to power sensors sporadically and not continuously. Sensor nodes need to exploit the sporadic availability of energy to quickly sense and transmit the data. This paper surveys related research and discusses the challenges of designing networking protocols for such WSNs powered by ambient energy harvesting.

/pdf/wireless-sensor-networks-powered-by-ambient-energy-190hpq37ui.pdf

Wireless sensor networks powered by ambient energy harvesting (WSN-HEAP) - Survey and challenges

Algorithmic approaches to the estimation of pairwise distances between the nodes of a wireless sensor network are highly attractive to provide information for routing and localization without requiring specific hardware to be added to cost/resource-constrained nodes. This paper exploits statistical geometry to derive robust estimators of the pairwise Euclidean distances from topological information typically available in any network. Extensive Monte Carlo experiments conducted on synthetic benchmarks demonstrate the improved quality of the proposed estimators with respect to the state of the art.

A statistical geometry approach to distance estimation in wireless sensor networks

The possibility of emulating renewable energy sources by means of portable, low-cost embedded devices is a key factor for the design and validation of ultra low-power networked embedded systems. Full characterisation of hardware-software platforms used for reliably and adaptively generating energy traces is therefore needed in order to clearly understand their adoption for testing energy harvesting devices or protocols. We investigate in this study a recently proposed embedded ultra-low power solution, which targets energy harvesting sources emulation with real-time responsiveness. The analyzed platform has been previously evaluated in terms of accuracy and reactiveness. However, given the presence of a positive feedback mechanism implemented by means of a compensation circuit, the possibility of unstable dynamics could hinder its applicability. It is therefore deemed interesting to delineate the conditions which guarantee the stability of the system. The aim of this article is to investigate the problem, to formally derive the electrical loads to be powered that allow for operate in a stable regime, and to experimentally assess properties in realistic scenarios. Theoretical and experimental results highlight the flexibility of the analyzed platform in terms of its capability to quickly adapt to changes in load conditions, while retaining bounded output dynamics.

https://www.mdpi.com/2073-431X/8/4/78/pdf

On the Stability of a Hardware Compensation Mechanism for Embedded Energy Harvesting Emulators

In the human activity recognition (HAR) application domain, the use of deep learning (DL) algorithms for feature extractions and training purposes delivers significant performance improvements with respect to the use of traditional machine learning (ML) algorithms. However, this comes at the expense of more complex and demanding models, making harder their deployment on constrained devices traditionally involved in the HAR process. The efficiency of DL deployment is thus yet to be explored. We thoroughly investigated the application of TensorFlow Lite simple conversion, dynamic, and full integer quantization compression techniques. We applied those techniques not only to convolutional neural networks (CNNs), but also to long short-term memory (LSTM) networks, and a combined version of CNN and LSTM. We also considered two use case scenarios, namely cascading compression and stand-alone compression mode. This paper reports the feasibility of deploying deep networks onto an ESP32 device, and how TensorFlow compression techniques impact classification accuracy, energy consumption, and inference latency. Results show that in the cascading case, it is not possible to carry out the performance characterization. Whereas in the stand-alone case, dynamic quantization is recommended because yields a negligible loss of accuracy. In terms of power efficiency, both dynamic and full integer quantization provide high energy saving with respect to the uncompressed models: between 31% and 37% for CNN networks, and up to 45% for LSTM networks. In terms of inference latency, dynamic and full integer quantization provide comparable performance.

A Study on the Application of TensorFlow Compression Techniques to Human Activity Recognition

Tiny wearable devices are nowadays one of the most popular and used devices in everyday life. At the same time, machine learning techniques have reached a level of maturity such that they can be used in the most varied fields. The union of these two technologies represents a valuable opportunity for the development of pervasive computing applications. On the other hand, pushing the machine learning inference on a wearable device can lead to nontrivial issues. In fact, devices with small size and low-energy availability, like those dedicated to wearable platforms, pose strict computational, memory, and power requirements which result in challenging issues to be addressed by designers. The main purpose of this study is to empirically explore the trade-off between energy consumption and classification accuracy of a machine learning-based hand-washing recognition task deployed on a real wearable device. Through extensive experimental results, obtained on a public human activity recognition dataset, we demonstrated that given an identical level of classification performance, a classic SVM classifier can save about 40% of energy with respect to a more complex LSTM network. Moreover, reducing the LSTM complexity, by lowering the number of its internal unit, can make the LSTM network energy cost-effective (with a savings of about 30%) at the cost of a reduction in accuracy of only 2%.

Energy-aware Tiny Machine Learning for Sensor-based Hand-washing Recognition

Current guidelines from the World Health Organization indicate that the SARSCoV-2 coronavirus, which results in the novel coronavirus disease (COVID-19), is transmitted through respiratory droplets or by contact. Contact transmission occurs when contaminated hands touch the mucous membrane of the mouth, nose, or eyes. Moreover, pathogens can also be transferred from one surface to another by contaminated hands, which facilitates transmission by indirect contact. Consequently, hands hygiene is extremely important to prevent the spread of the SARSCoV-2 virus. Additionally, hand washing and/or hand rubbing disrupts also the transmission of other viruses and bacteria that cause common colds, flu and pneumonia, thereby reducing the overall disease burden. The vast proliferation of wearable devices, such as smartwatches, containing acceleration, rotation, magnetic field sensors, etc., together with the modern technologies of artificial intelligence, such as machine learning and more recently deep-learning, allow the development of accurate applications for recognition and classification of human activities such as: walking, climbing stairs, running, clapping, sitting, sleeping, etc. In this work we evaluate the feasibility of an automatic system, based on current smartwatches, which is able to recognize when a subject is washing or rubbing its hands, in order to monitor parameters such as frequency and duration, and to evaluate the effectiveness of the gesture. Our preliminary results show a classification accuracy of about 95% and of about 94% for respectively deep and standard learning techniques.

Emanuele Lattanzi

Papers

A statistical geometry approach to distance estimation in wireless sensor networks

On the Stability of a Hardware Compensation Mechanism for Embedded Energy Harvesting Emulators

A Study on the Application of TensorFlow Compression Techniques to Human Activity Recognition

Energy-aware Tiny Machine Learning for Sensor-based Hand-washing Recognition

Automatic Unstructured Handwashing Recognition using Smartwatch to Reduce Contact Transmission of Pathogens