Electric infrastructures have been pushed forward to handle tasks they were not originally designed to perform. To improve reliability and efficiency, state-of-the-art power grids include improved security, reduced peak loads, increased integration of renewable sources, and lower operational costs. In this framework“, smart grids” are built around bidirectional communication technologies, where “smart meters” communicate with all other entities and collect data from the power grid, offering specific features to each actor playing in the energy marketplace. In this paper, to overcome some of the challenges raised by smart grids and smart meters, we propose a distributed metering infrastructure which provides bidirectional communication, self-configuration, and auto-update capabilities. Our 3-phase smart meters follow the basics Internet-of-Things principles and have the ability to run, either on-board or distributed on the network, multiple algorithms for smart grid management. These algorithms can be freely added, updated, or removed on-the-fly thanks to the auto-update feature of the system. Moreover, to reduce costs and improve scalability, we prove that it is possible to implement our smart meters using only off-the-shelf and inexpensive hardware devices. A digital real-time simulator (i.e., Opal-RT) has been used to assess the capabilities of both the infrastructure and the meter. Our experimental analysis shows that the latency introduced by the data transmission over the Internet is compliant with the limits imposed by the IEC 61850 standard. As a consequence, our architecture does not affect the operational status of the smart grid, making it a viable solution to support the deployment of novel services.

Hearth Rate (HR) monitoring is increasingly performed in wrist-worn devices using low-cost photoplethysmography (PPG) sensors. However, Motion Artifacts (MAs) caused by movements of the subject’s arm affect the performance of PPG-based HR tracking. This is typically addressed coupling the PPG signal with acceleration measurements from an inertial sensor. Unfortunately, most standard approaches of this kind rely on hand-tuned parameters, which impair their generalization capabilities and their applicability to real data in the field. In contrast, methods based on deep learning, despite their better generalization, are considered to be too complex to deploy on wearable devices. In this work, we tackle these limitations, proposing a design space exploration methodology to automatically generate a rich family of deep Temporal Convolutional Networks (TCNs) for HR monitoring, all derived from a single “seed” model. Our flow involves a cascade of two Neural Architecture Search (NAS) tools and a hardware-friendly quantizer, whose combination yields both highly accurate and extremely lightweight models. When tested on the PPG-Dalia dataset, our most accurate model sets a new state-of-the-art in Mean Absolute Error. Furthermore, we deploy our TCNs on an embedded platform featuring a STM32WB55 microcontroller, demonstrating their suitability for real-time execution. Our most accurate quantized network achieves 4.41 Beats Per Minute (BPM) of Mean Absolute Error (MAE), with an energy consumption of 47.65 mJ and a memory footprint of 412 kB. At the same time, the smallest network that obtains a MAE $< $ 8 BPM, among those generated by our flow, has a memory footprint of 1.9 kB and consumes just 1.79 mJ per inference.

The range of operations of electric vehicles (EVs) is a critical aspect that may affect the user's attitude toward them. For manned EVs, range anxiety is still perceived as a major issue and recent surveys have shown that one-third of potential European users are deterred by this problem when considering the move to an EV. A similar consideration applies to aerial EVs for commercial use, where a careful planning of the flying range is essential not only to guarantee the service but also to avoid the loss of the EVs due to charge depletion during the flight. Therefore, route planning for EVs for different purposes (range estimation, route optimization) and/or application scenarios (terrestrial, aerial EVs) is an essential element to foster the acceptance of EVs as a replacement of traditional vehicles. One essential element to enable such accurate planning is an accurate model of the actual power consumption. While very elaborate models for the electrical motors of EVs do exist, the motor power does not perfectly match the power drawn from the battery because of battery non-idealities. In this paper, we propose a general methodology that allows to predict and/or optimize the operation range of EVs, by allowing different accuracy/complexity tradeoffs for the models describing the route, the vehicle, and the battery, and taking into account the decoupling between motor and battery power. We demonstrate our method on two use cases. The first one is a traditional driving range prediction for a terrestrial EV; the second one concerns an unmanned aerial vehicle, for which the methodology will be used to determine the energy-optimal flying speed for a set of parcel delivery tasks.

Human Activity Recognition (HAR) based on inertial data is an increasingly diffused task on embedded devices, from smartphones to ultra low-power sensors. Due to the high computational complexity of deep learning models, most embedded HAR systems are based on simple and not-so-accurate classic machine learning algorithms. This work bridges the gap between on-device HAR and deep learning, proposing a set of efficient one-dimensional Convolutional Neural Networks (CNNs) that can be deployed on general purpose microcontrollers (MCUs). Our CNNs are obtained combining hyper-parameters optimization with sub-byte and mixed-precision quantization, to find good trade-offs between classification results and memory occupation. Moreover, we also leverage adaptive inference as an orthogonal optimization to tune the inference complexity at runtime based on the processed input, hence producing a more flexible HAR system. With experiments on four datasets, and targeting an ultra-low-power RISC-V MCU, we show that (i) we are able to obtain a rich set of Pareto-optimal CNNs for HAR, spanning more than 1 order of magnitude in terms of memory, latency, and energy consumption; (ii) thanks to adaptive inference, we can derive >20 runtime operating modes starting from a single CNN, differing by up to 10% in classification scores and by more than 3× in inference complexity, with a limited memory overhead; (iii) on three of the four benchmarks, we outperform all previous deep learning methods, while reducing the memory occupation by more than 100×. The few methods that obtain better performance (both shallow and deep) are not compatible with MCU deployment; (iv) all our CNNs are compatible with real-time on-device HAR, achieving an inference latency that ranges between 9 μs and 16 ms. Their memory occupation varies in 0.05–23.17 kB, and their energy consumption in 0.05 and 61.59 μJ, allowing years of continuous operation on a small battery supply.

In recent years, the introduction and exploitation of innovative information technologies in industrial contexts have led to the continuous growth of digital shop floor environments. The new Industry 4.0 model allows smart factories to become very advanced IT industries, generating an ever-increasing amount of valuable data. As a consequence, the necessity of powerful and reliable software architectures is becoming prominent along with data-driven methodologies to extract useful and hidden knowledge supporting the decision-making process. This article discusses the latest software technologies needed to collect, manage, and elaborate all data generated through innovative Internet-of-Things (IoT) architectures deployed over the production line, with the aim of extracting useful knowledge for the orchestration of high-level control services that can generate added business value. This survey covers the entire data life cycle in manufacturing environments, discussing key functional and methodological aspects along with a rich and properly classified set of technologies and tools, useful to add intelligence to data-driven services. Therefore, it serves both as a first guided step toward the rich landscape of the literature for readers approaching this field and as a global yet detailed overview of the current state of the art in the Industry 4.0 domain for experts. As a case study, we discuss, in detail, the deployment of the proposed solutions for two research project demonstrators, showing their ability to mitigate manufacturing line interruptions and reduce the corresponding impacts and costs.

The concept of Industry 4.0 originates from the will to introduce the benefits of digital computation into new and existing industrial plants to save time, materials and energy. The digital transformation requires that all machinery of the production line are connected together and with the enterprise applications, to capture and analyze data across all manufacturing stages. Then, such collected data can be exploited to take strategic decision on the production and to monitor it, reacting to unexpected behaviors and thus reducing downtime and maintenance costs. This article aims at supporting production engineers approaching digital transformation by exemplifying its key elements on a real life scenario, the Industrial Computer Engineering laboratory of the University of Verona. First of all, the article discusses network design, as communication is an enabler of the other technologies. Network is realized through automatic network synthesis from requirements and characteristics of the production line data flow. Then, the paper discusses data collection and the construction of a digital twin monitoring power consumption of the production line, with the goal of detecting any discrepancy between real time data and digital twin data. This allows to trigger an early intervention on the line, to guarantee an effective maintenance.