Developing a low-cost wireless energy meter with power quality measurements for smart grid applications represents a significant advance in efficient and accurate electric energy monitoring. In increasingly complex and interconnected electric systems, this device will be essential for a wide range of applications, such as smart grids, by introducing a real-time energy monitoring system. In light of this, smart meters can offer greater opportunities for sustainable and efficient energy use and improve the utilization of energy sources, especially those that are nonrenewable. According to the 2020 International Energy Agency (IEA) report, nonrenewable energy sources represent 65% of the global supply chain. The smart meter developed in this work is based on the ESP32 microcontroller and easily accessible components since it includes a user-friendly development platform that offers a cost-effective solution while ensuring reliable performance. The main objective of developing the smart meters was to enhance the software and simplify the hardware. Unlike traditional meters that calculate electrical parameters by means of complex circuits in hardware, this project performed the calculations directly on the microcontroller. This procedure reduced the complexity of the hardware by simplifying the meter design. Owing to the high-performance processing capability of the microcontroller, efficient and accurate calculations of electrical parameters could be achieved without the need for additional circuits. This software-driven approach with simplified hardware led to benefits, such as reduced production costs, lower energy consumption, and a meter with improved accuracy, as well as updates on flexibility. Furthermore, the integrated wireless connectivity in the microcontroller enables the collected data to be transmitted to remote monitoring systems for later analysis. The innovative feature of this smart meter lies in the fact that it has readily available components, along with the ESP32 chip, which results in a low-cost smart meter with performance that is comparable to other meters available on the market. Moreover, it is has the capacity to incorporate IoT and artificial intelligence applications. The developed smart meter is cost effective and energy efficient, and offers benefits with regard to flexibility, and thus represents an innovative, efficient, and versatile solution for smart grid applications.

Nucleic acid detection by electrophoresis is still a quick and accessible technique for many diagnosis methods, primarily at research laboratories or at the point of care units. Standard protocols detect DNA/RNA molecules through specific bound chemical dyes using a UV-transilluminator or UV-photo documentation system. However, the acquisition costs and availability of these devices, mainly the ones with photography and internet connection capabilities, can be prohibitive, especially in developing countries public health units. Also, ultraviolet radiation is a common additional risk factor to professionals that use electrophoresis-based nucleic acid detection. With that in mind, this work describes the development of a low-cost DNA/RNA detection smart system capable of obtaining qualitative and semi-quantitative data from gel analysis. The proposed device explores the visible light absorption range of commonly used DNA/RNA dyes using readily available parts, and simple manufacturing processes, such as light-emitting diodes (LEDs) and 3D impression. By applying IoT techniques, our system covers a wide range of color spectrum in order to detect bands from various commercially used dyes, using Bluetooth communication and a smartphone for hardware control, image capturing, and sharing. The project also enables process scalability and has low manufacturing and maintenance costs. The use of LEDs at the visible spectrum can achieve very reproducible images, providing a high potential for rapid and point-of-care diagnostics as well as applications in several fields such as healthcare, agriculture, and aquaculture.

This study investigates the implementation of artificial intelligence (AI) algorithms on resource-constrained edge devices, such as ESP32 and Raspberry Pi, within the context of smart grid (SG) applications. Specifically, it proposes a smart-meter-based system capable of classifying and detecting the Internet of Things (IoT) electronic devices at the extreme edge. The smart meter developed in this work acquires real-time voltage and current signals from connected devices, which are used to train and deploy lightweight machine learning models—Multi-Layer Perceptron (MLP) and K-Nearest Neighbor (KNN)—directly on edge hardware. The proposed system is integrated into the Artificial Intelligence in the Internet of Things for Smart Grids IAIoSGT architecture, which supports edge–cloud processing and real-time decision-making. A literature review highlights the key gaps in the existing approaches, particularly the lack of embedded intelligence for load identification at the edge. The experimental results emphasize the importance of data preprocessing—especially normalization—in optimizing model performance, revealing distinct behavior between MLP and KNN models depending on the platform. The findings confirm the feasibility of performing accurate low-latency classification directly on smart meters, reinforcing the potential of scalable AI-powered energy monitoring systems in SG.

This paper presents a study on the performance of Machine Learning techniques for the task of determining each of the electronics systems connected within the same electrical network, in the Internet of Smart Grid Things (IoSGT) architecture. This is regarded as an ecosystem which has cutting-edge technologies that work together to enable advanced SG applications, and run in core/edge cloud datacenters connected to an underlying IoT network infrastructure. This identification was carried out by analyzing traditional energy measures (i.e., voltage, current and power) through ML-based techniques. The analysis of regular energy measurements is required as a means of ensuring compatibility with legacy /smart meters, without the need to exchange them for new ones or make updates. The data was obtained by using a smart meter built by our group, and was processed and validated in the IoSGT edge-cloud.

Developing a low-cost wireless energy meter with power quality measurement for smart grid applications represents a significant advancement in efficient and accurate electrical energy monitoring.In increasingly complex and interconnected electrical systems, this device is essential in various applications, such as smart grids, enabling real-time energy usage monitoring. In such a context, smart meters expand the possibilities for sustainable and efficient energy use and promote better utilization of energy sources, especially non-renewable ones. According to the 2020 International Energy Agency (IEA) research, non-renewable energy sources represent 65% of the global total. The smart meter developed in this work is built based on the ESP32 microcontroller and easily accessible components, using a user-friendly development platform that offers a cost-effective solution while ensuring reliable performance. The main objective of the smart meter development was to enhance the software and simplify the hardware. Unlike traditional meters that perform electrical parameter calculations using complex hardware circuits, this project performed the calculations directly on the microcontroller. This approach reduced the complexity of the hardware, simplifying the meter’s design. With the high-performance processing capability of the microcontroller, efficient and accurate calculations of electrical parameters were achieved without the need for additional circuits. This software-driven approach with simplified hardware brought benefits such as reduced production costs, lower energy consumption, and increased meter development and updates flexibility. Furthermore, the integrated wireless connectivity in the microcontroller enables the transmission of collected data to remote monitoring systems for later analysis. The developed smart meter offers cost, energy efficiency, and flexibility benefits. It represents an innovative, efficient, and versatile solution for smart grid applications.

Today, grid resilience as a feature has become non-negotiable, significantly when power interruptions can impact the economy. The widespread popularity of Intelligent Electronic Devices (IED) operating as smart meters enables an immense amount of fine-grained electricity consumption data to be collected. However, risk can still exist in the Smart Grid (SG), as valuable data are exchanged among SG systems; theft or alteration of this data could violate consumer privacy. The Internet of Things for Smart Grid (IoSGT) is a promising ecosystem of different technologies that coordinate with each other to pave the way for new SG applications and services. As a use case of IoSGT for future SG applications and services, fraud detection, ıNon-technical losses (NTL), emerges as an important application for Smart Grid (SG) scenarios. A substantial amount of electrical energy is lost throughout the distribution system, and these losses are divided into two types: technical and non-technical. Non-technical losses (NTL) are any electrical energy consumed and not invoiced. They may occur due to illegal connections, issues with energy meters such as delay in the installation or reading errors, contaminated, defective, or non-adapted measuring equipment, very low valid consumption estimates, faulty connections, and disregarded customers. Non-technical losses are the primary cause of revenue loss in the SG. According to a recent study, electrical utilities lose $89.3 Billion per year due to non-technical losses. This article proposes ensemble predictor-based time series classifiers for NTL detection. The proposed predictor ministers the user’s energy consumption as a data input for classification, from splitting the data to executing the classifier.It encompasses the temporal aspects of energy consumption data during preprocessing, training, testing, and validation stages. The suggested predictor is Time Series (TS) oriented, from data splitting to the classifier’s performance. Overall, our best results have been recorded in the fraud detection-based time series classifiers (TSC) model scoring an improvement in the empirical performance metrics by 10% or more over the other developed models.