It is crucial to evaluate and anticipate stability under various conditions, as the ability to stabilize a smart grid (SG) is one of its key features for assessing the effectiveness of its design. Intelligent approaches to stability forecasting are necessary to mitigate inadvertent instability in SG design. This is particularly crucial with the expansion of residential and commercial infrastructures, along with the growing integration of renewable energies into these grids. Predicting the stability of SGs is currently a major challenge. The concept of an SG encompasses a broad range of emerging technologies in which artificial intelligence (AI) plays a crucial role and is increasingly being utilized in light of the limitations of conventional methods. It empowers informed decision-making and adaptable responses to fluctuations in customer energy needs, unexpected power outages, rapid changes in renewable energy generation, or any unforeseen crises within an SG system. In this paper, we propose a symmetric approach to enhance SG stability by integrating various machine learning (ML) and deep learning (DL) algorithms, where symmetry is observed in the balanced application of these diverse computational techniques to predict and ensure the grid’s stability. These algorithms utilized a dataset containing the simulation results of the SG stability. The learning phase of these algorithms is based on imprecise and unreliable data. To overcome this limitation, the fusion of classifiers can be a powerful approach to modeling inaccurate and uncertain data, providing more robust and reliable predictions than individual classifiers. Voting and Dempster–Shafer (DS) methods, two commonly used techniques in ensemble learning, were employed and compared. The results show that the use of the fusion of distinct classifiers with voting theory achieves an accuracy of 99.8% and outperforms several other methods including the DS method.

Distributed wireless sensor networks (WSNs) are widely used to enhance the quality and safety of various applications. These networks consist of numerous sensor nodes, often deployed in challenging terrains where maintenance is difficult. Efficient monitoring approaches are essential to maximize the functionality and lifespan of each sensor node, thereby improving the overall performance of the WSN. In this study, we propose a method to efficiently monitor radiofrequency electromagnetic fields (RF-EMF) exposure using WSNs. Our approach leverages sensor nodes to provide real-time measurements, ensuring accurate and timely data collection. With the increasing prevalence of wireless communication systems, assessing RF-EMF exposure has become crucial due to public health concerns. Since individuals spend over 70% of their time indoors, it is vital to evaluate indoor RF-EMF exposure. However, this task is complicated by the complex indoor environments, furniture arrangements, temporal variability of exposure, numerous obstructions with unknown dielectric properties, and uncontrolled factors such as people’s movements and the random positioning of furniture and doors. To address these challenges, we employ a sensor network to monitor RF-EMF exposure limits using embedded sensors. By integrating Internet of Things-embedded sensors with advanced modeling techniques, such as kriging, we characterize and model indoor RF-EMF downlink (DL) exposure effectively. Measurements taken in several buildings within a few hundred meters of base stations equipped with multiple cellular antennas (2G, 3G, 4G, and 5G) demonstrate that the kriging technique using the spherical model provides superior RF-EMF prediction compared with the exponential model. Using the spherical model, we constructed a high-resolution coverage map for the entire corridor, showcasing the effectiveness of our approach.

Modulation identification plays a crucial role in contemporary wireless communication systems, especially within 5G and future-generation networks that utilize a variety of multicarrier waveforms. This study introduces an innovative algorithm for automatic modulation classification (AMC) built on a deep residual network (DRN) architecture. The approach is tailored to accurately identify advanced 5G waveform types such as Orthogonal Frequency-Division Multiplexing (OFDM), Filtered OFDM (FOFDM), Filter Bank Multicarrier (FBMC), Universal Filtered Multicarrier (UFMC), and Weighted Overlap and Add OFDM (WOLA), using both 16-QAM and 64-QAM modulation schemes. To our knowledge, this is the first application of deep learning in the classification of such a diverse set of complex 5G waveforms. The proposed model combines the deep learning capabilities of DRNs for feature extraction with Principal Component Analysis (PCA) for dimensionality reduction and feature refinement. A detailed performance evaluation is conducted using metrics like classification recall, precision, accuracy, and F-measure. When compared with traditional machine learning approaches reported in recent studies, our DRN-based method shows significantly improved classification accuracy and robustness. These results highlight the effectiveness of deep residual networks in improving adaptive signal processing and enabling automatic modulation recognition in future wireless communication technologies.