Lessons Learnt from Monitoring the Etna Volcano Using an IoT Sensor Network through a Period of Intense Eruptive Activity.

This paper describes the successes and failures after 4 years of continuous operation of a network of sensors, communicating nodes, and gateways deployed on the Etna Volcano in Sicily since 2019, including a period of Etna intense volcanic activity that occurred in 2021 and resulted in over 60 paroxysms. It documents how the installation of gateways at medium altitude allowed for data collection from sensors up to the summit craters. Most of the sensors left on the volcanic edifice during winters and during this period of intense volcanic activity were destroyed, but the whole gateway infrastructure remained fully operational, allowing for a very fruitful new field campaign two years later, in August 2023. Our experience has shown that the best strategy for IoT deployment on very active and/or high-altitude volcanoes like Etna is to permanently install gateways in areas where they are protected both from meteorological and volcanic hazards, that is mainly at the foot of the volcanic edifice, and to deploy temporary sensors and communicating nodes in the more exposed areas during field trips or in the summer season.

Piezoelectric Sensors as Energy Harvesters for Ultra Low-Power IoT Applications.

The aim of this paper is to discuss the usability of vibrations as energy sources, for the implementation of energy self-sufficient wireless sensing platforms within the Industrial Internet of Things (IIoT) framework. In this context, this paper proposes to equip vibrating assets like machinery with piezoelectric sensors, used to set up energy self-sufficient sensing platforms for hard-to-reach positions. Preliminary measurements as well as extended laboratory tests are proposed to understand the behavior of commercial piezoelectric sensors when employed as energy harvesters. First, a general architecture for a vibration-powered LoRaWAN-based sensor node is proposed. Final tests are then performed to identify an ideal trade-off between sensor sampling rates and energy availability. The target is to ensure continuous operation of the device while guaranteeing a charging trend of the storage component connected to the system. In this context, an Ultra-Low-Power Energy-Harvesting Integrated Circuit plays a crucial role by ensuring the correct regulation of the output with very high efficiency.

Adaptive Spatial Scheduling for Event Traffic in LoRaWAN Networks.

Low-Power Wide-Area Networks constitute a leading, emerging Internet-of-Things technology, with important applications in environmental and industrial monitoring and disaster prevention and management. In such sensor networks, external detectable events can trigger synchronized alarm report transmissions. In LoRaWANs, and more generally in networks with a random access-based medium access algorithm, this can lead to a cascade of frame collisions, temporarily resulting in degraded performance and diminished system operational capacity, despite LoRaWANs' physical layer interference and collision reduction techniques. In this paper, a novel scheduling algorithm is proposed that can increase system reliability in the case of such events. The new adaptive spatial scheduling algorithm is based on learning automata, as well as previous developments in scheduling over LoRaWANs, and it leverages network feedback information and traffic spatial correlation to increase network performance while maintaining high reliability. The proposed algorithm is investigated via an extensive simulation under a variety of network conditions and compared with a previously proposed scheduler for event-triggered traffic. The results show a decrease of up to 30% in average frame delay compared to the previous approach and an order of magnitude lower delay compared to the baseline algorithm. These findings highlight the importance of using spatial information in adaptive schemes for improving network performance, especially in location-sensitive applications.

LoRaWAN for Vehicular Networking: Field Tests for Vehicle-to-Roadside Communication.

Vehicular wireless networks are one of the most valuable tools for monitoring platforms in the automotive domain. At the same time, Internet of Things (IoT) solutions are playing a crucial role in the same framework, allowing users to connect to vehicles in order to gather data related to their working cycle. Such tasks can be accomplished by resorting to either cellular or non-cellular wireless technologies. While the former can ensure low latency but require high running costs, the latter can be employed in quasi-real-time applications but definitely reduce costs. To this end, this paper proposes the results of two measurement campaigns aimed at assessing the performance of the long-range wide-area network (LoRaWAN) protocol when it is exploited as an enabling technology to provide vehicles with connectivity. Performances are evaluated in terms of packet loss (PL) and received signal strength indicator (RSSI) in wireless links. The two testing scenarios consisted of a transmitter installed on a motorbike running on an elliptical track and a receiver placed in the centre of the track, and a transmitter installed on the roof of a car and a receiver placed next to a straight road. Several speeds were tested, and all the spreading factors (SFs) foreseen by the protocol were examined, showing that the Doppler effect has a marginal influence on the receiving performance of the technology, and that, on the whole, performance is not significantly affected by the speed. Such results prove the feasibility of LoRaWAN links for vehicular network purposes.

Towards Mass-Scale IoT with Energy-Autonomous LoRaWAN Sensor Nodes.

By 2030, it is expected that a trillion things will be connected. In such a scenario, the power required for the trillion nodes would necessitate using trillions of batteries, resulting in maintenance challenges and significant management costs. The objective of this research is to contribute to sustainable wireless sensor nodes through the introduction of an energy-autonomous wireless sensor node (EAWSN) designed to be an energy-autonomous, self-sufficient, and maintenance-free device, to be suitable for long-term mass-scale internet of things (IoT) applications in remote and inaccessible environments. The EAWSN utilizes Low-Power Wide Area Networks (LPWANs) via LoRaWAN connectivity, and it is powered by a commercial photovoltaic cell, which can also harvest ambient light in an indoor environment. Storage components include a capacitor of 2 mF, which allows EAWSN to successfully transmit 30-byte data packets up to 560 m, thanks to opportunistic LoRaWAN data rate selection that enables a significant trade-off between energy consumption and network coverage. The reliability of the designed platform is demonstrated through validation in an urban environment, showing exceptional performance over remarkable distances.

A Comprehensive Survey on Deep Learning-Based LoRa Radio Frequency Fingerprinting Identification.

LoRa enables long-range communication for Internet of Things (IoT) devices, especially those with limited resources and low power requirements. Consequently, LoRa has emerged as a popular choice for numerous IoT applications. However, the security of LoRa devices is one of the major concerns that requires attention. Existing device identification mechanisms use cryptography which has two major issues: (1) cryptography is hard on the device resources and (2) physical attacks might prevent them from being effective. Deep learning-based radio frequency fingerprinting identification (RFFI) is emerging as a key candidate for device identification using hardware-intrinsic features. In this paper, we present a comprehensive survey of the state of the art in the area of deep learning-based radio frequency fingerprinting identification for LoRa devices. We discuss various categories of radio frequency fingerprinting techniques along with hardware imperfections that can be exploited to identify an emitter. Furthermore, we describe different deep learning algorithms implemented for the task of LoRa device classification and summarize the main approaches and results. We discuss several representations of the LoRa signal used as input to deep learning models. Additionally, we provide a thorough review of all the LoRa RF signal datasets used in the literature and summarize details about the hardware used, the type of signals collected, the features provided, availability, and size. Finally, we conclude this paper by discussing the existing challenges in deep learning-based LoRa device identification and also envisage future research directions and opportunities.

A Nature-Inspired Approach to Energy-Efficient Relay Selection in Low-Power Wide-Area Networks (LPWAN).

Despite the ability of Low-Power Wide-Area Networks to offer extended range, they encounter challenges with coverage blind spots in the network. This article proposes an innovative energy-efficient and nature-inspired relay selection algorithm for LoRa-based LPWAN networks, serving as a solution for challenges related to poor signal range in areas with limited coverage. A swarm behavior-inspired approach is utilized to select the relays' localization in the network, providing network energy efficiency and radio signal extension. These relays help to bridge communication gaps, significantly reducing the impact of coverage blind spots by forwarding signals from devices with poor direct connectivity with the gateway. The proposed algorithm considers critical factors for the LoRa standard, such as the Spreading Factor and device energy budget analysis. Simulation experiments validate the proposed scheme's effectiveness in terms of energy efficiency under diverse multi-gateway (up to six gateways) network topology scenarios involving thousands of devices (1000-1500). Specifically, it is verified that the proposed approach outperforms a reference method in preventing battery depletion of the relays, which is vital for battery-powered IoT devices. Furthermore, the proposed heuristic method achieves over twice the speed of the exact method for some large-scale problems, with a negligible accuracy loss of less than 2%.

Recent Developments in AI and ML for IoT: A Systematic Literature Review on LoRaWAN Energy Efficiency and Performance Optimization.

The field of the Internet of Things (IoT) is dominating various areas of technology. As the number of devices has increased, there is a need for efficient communication with low resource consumption and energy efficiency. Low Power Wide Area Networks (LPWANs) have emerged as a transformative technology for the IoT as they provide long-range communication capabilities with low power consumption. Among the various LPWAN technologies, Long Range Wide Area Networks (LoRaWAN) are widely adopted due to their open standard architecture, which supports secure, bi-directional communication and is particularly effective in outdoor and complex urban environments. This technology is helpful in enabling a variety of IoT applications that require wide coverage and long battery life, such as smart cities, industrial IoT, and environmental monitoring. The integration of Machine Leaning (ML) and Artificial Intelligence (AI) into LoRaWAN operations has further enhanced its capability and particularly optimized resource allocation and energy efficiency. This systematic literature review provides a comprehensive examination of the integration of ML and AI technologies in the optimization of LPWANs, with a specific focus on LoRaWAN. This review follows the PRISMA model and systematically synthesizes current research to highlight how ML and AI enhance operational efficiency, particularly in terms of energy consumption, resource management, and network stability. The SLR aims to review the key methods and techniques that are used in state-of-the-art LoRaWAN to enhance the overall network performance. We identified 25 relevant primary studies. The study provides an analysis of key findings based on research questions on how various LoRaWAN parameters are optimized through advanced ML, DL, and RL techniques to achieve optimized performance.

Bat2Web: A Framework for Real-Time Classification of Bat Species Echolocation Signals Using Audio Sensor Data.

Bats play a pivotal role in maintaining ecological balance, and studying their behaviors offers vital insights into environmental health and aids in conservation efforts. Determining the presence of various bat species in an environment is essential for many bat studies. Specialized audio sensors can be used to record bat echolocation calls that can then be used to identify bat species. However, the complexity of bat calls presents a significant challenge, necessitating expert analysis and extensive time for accurate interpretation. Recent advances in neural networks can help identify bat species automatically from their echolocation calls. Such neural networks can be integrated into a complete end-to-end system that leverages recent internet of things (IoT) technologies with long-range, low-powered communication protocols to implement automated acoustical monitoring. This paper presents the design and implementation of such a system that uses a tiny neural network for interpreting sensor data derived from bat echolocation signals. A highly compact convolutional neural network (CNN) model was developed that demonstrated excellent performance in bat species identification, achieving an F1-score of 0.9578 and an accuracy rate of 97.5%. The neural network was deployed, and its performance was evaluated on various alternative edge devices, including the NVIDIA Jetson Nano and Google Coral.

Explainable Machine Learning for LoRaWAN Link Budget Analysis and Modeling.

This article explores the convergence of artificial intelligence and its challenges for precise planning of LoRa networks. It examines machine learning algorithms in conjunction with empirically collected data to develop an effective propagation model for LoRaWAN. We propose decoupling feature extraction and regression analysis, which facilitates training data requirements. In our comparative analysis, decision-tree-based gradient boosting achieved the lowest root-mean-squared error of 5.53 dBm. Another advantage of this model is its interpretability, which is exploited to qualitatively observe the governing propagation mechanisms. This approach provides a unique opportunity to practically understand the dependence of signal strength on other variables. The analysis revealed a 1.5 dBm sensitivity improvement as the LoR's spreading factor changed from 7 to 12. The impact of clutter was revealed to be highly non-linear, with high attenuations as clutter increased until a certain point, after which it became ineffective. The outcome of this work leads to a more accurate estimation and a better understanding of the LoRa's propagation. Consequently, mitigating the challenges associated with large-scale and dense LoRaWAN deployments, enabling improved link budget analysis, interference management, quality of service, scalability, and energy efficiency of Internet of Things networks.

Energy Performance of LR-FHSS: Analysis and Evaluation.

Long-range frequency hopping spread spectrum (LR-FHSS) is a pivotal advancement in the LoRaWAN protocol that is designed to enhance the network's capacity and robustness, particularly in densely populated environments. Although energy consumption is paramount in LoRaWAN-based end devices, this is the first study in the literature, to our knowledge, that models the impact of this novel mechanism on energy consumption. In this article, we provide a comprehensive energy consumption analytical model of LR-FHSS, focusing on three critical metrics: average current consumption, battery lifetime, and energy efficiency of data transmission. The model is based on measurements performed on real hardware in a fully operational LR-FHSS network. While in our evaluation, LR-FHSS can show worse consumption figures than LoRa, we find that with optimal configuration, the battery lifetime of LR-FHSS end devices can reach 2.5 years for a 50 min notification period. For the most energy-efficient payload size, this lifespan can be extended to a theoretical maximum of up to 16 years with a one-day notification interval using a cell-coin battery.

A Systematic Literature Review of LoRaWAN: Sensors and Applications.

LoRaWAN is a communication protocol designed especially for Internet of Things (IoT) applications that offers benefits such as long-distance connection and low power consumption. Due to the characteristics of LoRaWAN, this technology has gained great popularity in various IoT applications, such as environmental monitoring, smart agriculture, and applications in the areas of health and mobility, among others. Given this situation, the objective of this work is to provide an in-depth overview of LoRaWAN technology in terms of its applications, as well as the devices that have been used for the development of such applications. Additionally, this work reviews what other areas of LoRaWAN have been covered in different scientific articles, i.e., performance improvement and security. Among the main results of this study though analyzing previous works, we can say that most of them have been developed in the area of environmental monitoring and have used low-cost devices such as Arduinos, Raspberry Pis, and relatively low-cost commercial products such as those of the Semtech and STMicroelectronics brands. The analysis of the present work shows objectively and formally that LoRaWAN technology can be applied in various applications and that there are many studies that try to optimize its performance and security. This paper seeks to identify and describe the most relevant applications of LoRaWAN in different sectors, such as agriculture, health, and environmental monitoring, among others, and the challenges and solutions found in each area. This literature review will provide a valuable reference to understand the potential and opportunities offered by LoRaWAN technology.

Assessing a Methodology for Evaluating the Latency of IPv6 with SCHC Compression in LoRaWAN Deployments.

The Internet of Things (IoT) approach relies on the use of the Internet Protocol (IP) as a pervasive network protocol. IP acts as a "glue" for interconnecting end devices (on the field side) and end users, leveraging on very diverse lower-level and upper-level protocols. The need for scalability would suggest the adoption of IPv6, but the large overhead and payloads do not match with the constraints dictated by common wireless solutions. For this reason, compression strategies have been proposed to avoid redundant information in the IPv6 header and to provide fragmentation and reassembly of long messages. For example, the Static Context Header Compression (SCHC) protocol has been recently referenced by the LoRa Alliance as a standard IPv6 compression scheme for LoRaWAN-based applications. In this way, IoT end points can seamlessly share an end-to-end IP link. However, implementation details are out of the specifications' scope. For this reason, formal test procedures for comparing solutions from different providers are important. In this paper, a test method for assessing architectural delays of real-world deployments of SCHC-over-LoRaWAN implementations is presented. The original proposal includes a mapping phase, for identifying information flows, and a subsequent evaluation phase, in which flows are timestamped and time-related metrics are computed. The proposed strategy has been tested in different use cases involving LoRaWAN backends deployed all around the world. The feasibility of the proposed approach has been tested by measuring the end-to-end latency of IPv6 data in sample use cases, obtaining a delay of less than 1 s. However, the main result is the demonstration that the suggested methodology permits a comparison of the behavior of IPv6 with SCHC-over-LoRaWAN, allowing the optimization of choices and parameters during deployment and commissioning of both infrastructure components and software.

Mobility Classification of LoRaWAN Nodes Using Machine Learning at Network Level.

LoRaWAN networks rely heavily on the adaptive data rate algorithm to achieve good link reliability and to support the required density of end devices. However, to be effective the adaptive data rate algorithm needs to be tuned according to the level of mobility of each end device. For that purpose, different adaptive data rate algorithms have been developed for the different levels of mobility of end devices, e.g., for static or mobile end devices. In this paper, we describe and evaluate a new and effective method for determining the level of mobility of end devices based on machine learning techniques and specifically on the support vector machine supervised learning method. The proposed method does not rely on the location capability of LoRaWAN networks; instead, it relies only on data always available at the LoRaWAN network server. Moreover, the performance of this method in a real LoRaWAN network is assessed; the results give clear evidence of the effectiveness and reliability of the proposed machine learning approach.

Priority-Based Resource Allocation Optimization for Multi-Service LoRaWAN Harmonization in Compliance with IEEE 2668.

Given the advantage of LoRaWAN private networks, multiple types of services have been implemented by users in one LoRaWAN system to realize various smart applications. With an increasing number of applications, LoRaWAN suffers from multi-service coexistence challenges due to limited channel resources, uncoordinated network configuration, and scalability issues. The most effective solution is establishing a reasonable resource allocation scheme. However, existing approaches are not applicable for LoRaWAN with multiple services with different criticalities. Therefore, we propose a priority-based resource allocation (PB-RA) scheme to coordinate multi-service networks. In this paper, LoRaWAN application services are classified into three main categories, including safety, control, and monitoring. Considering the different criticalities of these services, the proposed PB-RA scheme assigns spreading factors (SFs) to end devices on the basis of the highest priority parameter, which decreases the average packet loss rate (PLR) and improves throughput. Moreover, a harmonization index, namely HDex, based on IEEE 2668 standard is first defined to comprehensively and quantitively evaluate the coordination ability in terms of key quality of service (QoS) performance (i.e., PLR, latency and throughput). Furthermore, Genetic Algorithm (GA)-based optimization is formulated to obtain the optimal service criticality parameters which maximize the average HDex of the network and contribute to a larger capacity of end devices while maintaining the HDex threshold for each service. Simulations and experimental results show that the proposed PB-RA scheme can achieve the HDex score of 3 for each service type at 150 end devices, which improves the capacity by 50% compared to the conventional adaptive data rate (ADR) scheme.

Leveraging Larger AES Keys in LoRaWAN: A Practical Evaluation of Energy and Time Costs.

Internet of Things (IoT) devices increasingly contribute to critical infrastructures, necessitating robust security measures. LoRaWAN, a low-power IoT network, employs the Advanced Encryption Standard (AES) with a 128-bit key for encryption and integrity, balancing efficiency and security. As computational capabilities of devices advance and recommendations for stronger encryption, such as AES-256, emerge, the implications of using longer AES keys (192 and 256 bits) on LoRaWAN devices' energy consumption and processing time become crucial. Despite the significance of the topic, there is a lack of research on the implications of using larger AES keys in real-world LoRaWAN settings. To address this gap, we perform extensive tests in a real-world LoRaWAN environment, modifying the source code of both a LoRaWAN end device and open-source server stack to incorporate larger AES keys. Our results show that, while larger AES keys increase both energy consumption and processing time, these increments are minimal compared to the time on air. Specifically, for the maximum payload size we used, when comparing AES-256 to AES-128, the additional computational time and energy are, respectively, 750 ms and 236 µJ. However, in terms of time on air costs, these increases represent just 0.2% and 0.13%, respectively. Our observations confirm our intuition that the increased costs correlate to the number of rounds of AES computation. Moreover, we formulate a mathematical model to predict the impact of longer AES keys on processing time, which further supports our empirical findings. These results suggest that implementing longer AES keys in LoRaWAN is a practical solution enhancing its security strength while not significantly impacting energy consumption or processing time.

Exploring LoRaWAN Traffic: In-Depth Analysis of IoT Network Communications.

In the past decade, Long-Range Wire-Area Network (LoRaWAN) has emerged as one of the most widely adopted Low Power Wide Area Network (LPWAN) standards. Significant efforts have been devoted to optimizing the operation of this network. However, research in this domain heavily relies on simulations and demands high-quality real-world traffic data. To address this need, we monitored and analyzed LoRaWAN traffic in four European cities, making the obtained data and post-processing scripts publicly available. For monitoring purposes, we developed an open-source sniffer capable of capturing all LoRaWAN communication within the EU868 band. Our analysis discovered significant issues in current LoRaWAN deployments, including violations of fundamental security principles, such as the use of default and exposed encryption keys, potential breaches of spectrum regulations including duty cycle violations, SyncWord issues, and misaligned Class-B beacons. This misalignment can render Class-B unusable, as the beacons cannot be validated. Furthermore, we enhanced Wireshark's LoRaWAN protocol dissector to accurately decode recorded traffic. Additionally, we proposed the passive reception of Class-B beacons as an alternative timebase source for devices operating within LoRaWAN coverage under the assumption that the issue of misaligned beacons can be addressed or mitigated in the future. The identified issues and the published dataset can serve as valuable resources for researchers simulating real-world traffic and for the LoRaWAN Alliance to enhance the standard to facilitate more reliable Class-B communication.

Rapid IoT Prototyping: A Visual Programming Tool and Hardware Solutions for LoRa-Based Devices.

LoRa technology has gained popularity as one of the most widely used standards for device interconnection due to its ability to cover long distances and energy efficiency, making it a suitable choice for various Internet of Things (IoT) monitoring and control applications. In this sense, this work presents the development of a visual support tool for creating IoT devices with LoRa and LoRaWAN connectivity. This work significantly advances the state of the art in LoRa technology by introducing a novel visual support tool tailored for creating IoT devices with LoRa and LoRaWAN connectivity. By simplifying the development process and offering compatibility with multiple hardware solutions, this research not only facilitates the integration of LoRaWAN technology within educational settings but also paves the way for rapid prototyping of IoT nodes. The incorporation of block programming for LoRa and LoRaWAN using the Arduinoblocks framework as a graphical environment enhances the capabilities of the tool, positioning it as a comprehensive solution for efficient firmware generation. In addition to the visual tool for firmware generation, multiple compatible hardware solutions enable easy, economical, and stable development, offering a comprehensive hardware and software solution. The hardware proposal is based on an ESP32 microcontroller, known for its power and low cost, in conjunction with an RFM9x module that is based on SX127x LoRa transceivers. Finally, three successfully tested use cases and a discussion are presented.

Fight Fire with Fire: Detecting Forest Fires with Embedded Machine Learning Models Dealing with Audio and Images on Low Power IoT Devices.

Forest fires are the main cause of desertification, and they have a disastrous impact on agricultural and forest ecosystems. Modern fire detection and warning systems rely on several techniques: satellite monitoring, sensor networks, image processing, data fusion, etc. Recently, Artificial Intelligence (AI) algorithms have been applied to fire recognition systems, enhancing their efficiency and reliability. However, these devices usually need constant data transmission along with a proper amount of computing power, entailing high costs and energy consumption. This paper presents the prototype of a Video Surveillance Unit (VSU) for recognising and signalling the presence of forest fires by exploiting two embedded Machine Learning (ML) algorithms running on a low power device. The ML models take audio samples and images as their respective inputs, allowing for timely fire detection. The main result is that while the performances of the two models are comparable when they work independently, their joint usage according to the proposed methodology provides a higher accuracy, precision, recall and F1 score (96.15%, 92.30%, 100.00%, and 96.00%, respectively). Eventually, each event is remotely signalled by making use of the Long Range Wide Area Network (LoRaWAN) protocol to ensure that the personnel in charge are able to operate promptly.

Data Acquisition Filtering Focused on Optimizing Transmission in a LoRaWAN Network Applied to the WSN Forest Monitoring System.

Developing innovative systems and operations to monitor forests and send alerts in dangerous situations, such as fires, has become, over the years, a necessary task to protect forests. In this work, a Wireless Sensor Network (WSN) is employed for forest data acquisition to identify abrupt anomalies when a fire ignition starts. Even though a low-power LoRaWAN network is used, each module still needs to save power as much as possible to avoid periodic maintenance since a current consumption peak happens while sending messages. Moreover, considering the LoRaWAN characteristics, each module should use the bandwidth only when essential. Therefore, four algorithms were tested and calibrated along real and monitored events of a wildfire. The first algorithm is based on the Exponential Smoothing method, Moving Averages techniques are used to define the other two algorithms, and the fourth uses the Least Mean Square. When properly combined, the algorithms can perform a pre-filtering data acquisition before each module uses the LoRaWAN network and, consequently, save energy if there is no necessity to send data. After the validations, using Wildfire Simulation Events (WSE), the developed filter achieves an accuracy rate of 0.73 with 0.5 possible false alerts. These rates do not represent a final warning to firefighters, and a possible improvement can be achieved through cloud-based server algorithms. By comparing the current consumption before and after the proposed implementation, the modules can save almost 53% of their batteries when is no demand to send data. At the same time, the modules can maintain the server informed with a minimum interval of 15 min and recognize abrupt changes in 60 s when fire ignition appears.