This research explores the potential of Machine Learning (ML) to enhance wireless communication networks, specifically in the context of Wireless Smart Grid Networks (WSGNs). We integrated ML into the well-established Routing Protocol for Low-Power and Lossy Networks (RPL), resulting in an advanced version called ML-RPL. This novel protocol utilizes CatBoost, a Gradient Boosted Decision Trees (GBDT) algorithm, to optimize routing decisions. The ML model, trained on a dataset of routing metrics, predicts the probability of successfully reaching a destination node. Each node in the network uses the model to choose the route with the highest probability of effectively delivering packets. Our performance evaluation, carried out in a realistic scenario and under various traffic loads, reveals that ML-RPL significantly improves the packet delivery ratio and minimizes end-to-end delay, making it a promising solution for more efficient and responsive WSGNs.

Geomagnetically induced currents (GICs) flow through grounding circuits into power systems, when triggered by geomagnetic disturbances. Power transformers (with grounding connections) are the primary path for GIC flows into power systems. The flow of GICs through a power transformer can create adverse impacts on its operation, including large increases in its reactive power demands and significant harmonic distortions in the primary side currents. This paper presents case studies and analyses of the adverse impacts of GIC flows on power transformers. Presented case studies are conducted on two power transformers with different core types, power ratings, and voltage ratings. Each of these power transformers is tested for various levels of GIC flows with its loading being kept unchanged. Results of conducted case studies conclude that the $2^{\text{nd}}$ harmonic is the dominant in primary and side currents at all levels of GIC flows. Other harmonic components such as the $3^{\text{rd}}$ , $4^{\text{th}}$ , $ 5^{\text{th}},\ 6^{\text{th}},\ 7^{\text{th}}\ \text{and}\ 8^{\text{th}}$ harmonic components, can be observed with lower magnitudes than the $2^{\text{nd}}$ harmonic component.

Wind energy is an important cornerstone of a non-polluting and sustainable electricity supply. In practice, the integration of significant wind energy into the existing electricity supply system is a challenge due to the stochastic nature of wind power. To be able to effectively integrate wind power into existing grid systems, accurate short-term wind speed forecasting is essential. Statistical and soft computing models are mainly used for short-term forecasting and a physical fluid model is used for long-term forecasting. Soft computing models are commonly suggested for wind forecasting due to data independency and handling of non-linear nature systems. Fuzzy ARTMAP, which is a combination of fuzzy logic and adaptive resonance theory, has been shown to be superior to basic neural network models in terms of the stability–plasticity dilemma. This paper presents a novel approach to short-term wind forecasting (i.e., 12- and 24-hr forecasting) using a Fuzzy ARTMAP technique, and the results are compared to a recently proposed linear prediction technique and a conventional neural network backpropagation algorithm.

In this article, experimental performance assessment and comparison are presented for solid, low impedance, high impedance, frequency-selective, and isolated grounding (IG) systems. The typical design of a grounding system (for low and medium voltage generation, transmission, and distribution systems) is based on selecting an impedance ( $\bar{Z}_{G}$ ), which is used to connect the neutral point and the ground. The impedance $\bar{Z}_{G}$ is typically composed from a combination of $R$ , $L$ , and $C$ elements. The combination type (series or parallel), along with the values of $R$ , $L$ , $C$ elements, allow estimating the possible effects of $\bar{Z}_{G}$ on ground currents and potentials during ground faults. In this article, solid, low impedance, high impedance, frequency-selective, and IG systems are designed for a 35-kVA $3\phi$ transformer and a 5-kVA $3\phi$ synchronous generator, for purposes of assessing and comparing their effects on ground currents and potentials during ground faults. The laboratory transformer and generator are tested for line-to-ground and double line-to-ground faults with all designed grounding systems under different loading levels. Experimental results show that some grounding systems can effectively reduce ground currents, and other grounding systems can effectively reduce ground potentials. These capabilities and features can be used to achieve certain system and operation mandates, including ground capacity, maximum allowed overvoltage, and service continuity.

This paper presents performance assessment of ground fault protection for systems supplied by a transformer, which has frequency-selective grounding. Frequency-selective grounding is a new grounding system that is designed to act as a solid-grounding for high frequency currents, and as a low resistance-grounding for low frequency currents. This grounding system is composed from a parallel $R-C$ circuit with an equivalent impedance able to affect system zero-sequence currents and ground potentials. Such effects on zero-sequence currents and ground potentials can directly impact the accuracy and response speed of ground fault protection. Effects of frequency-selective grounding on ground fault protection are experimentally assessed for different fault and non-fault events, when the transformer supplies linear and non-liner loads. Experimental results demonstrate responses of various implementations of ground fault protection to fault and non-fault events, when the protected system has frequency selective grounding. Moreover, presented results and discussions aim to demonstrate the ability of frequency-selective grounding to support the operation of ground fault protection during different loading conditions and fault events.

This paper experimentally evaluates responses of ground fault protection for synchronous generators, which are grounded using frequency-selective grounding. Frequency-selective grounding is designed to provide a low ground impedance path (similar to solid grounding) for high frequency zero-sequence current components. This grounding system also provides an impedance similar to a low-resistance grounding for low frequency zero-sequence current components. The frequency-dependent equivalent impedance of frequency-selective grounding can affect ground potential and current, which are typically used as inputs for ground fault protective relays. Effects of frequency-selective grounding on ground fault protection are experimentally evaluated using a 7.5 kVA synchronous generator. Experimental tests are conducted for different implementations of ground fault protection, when responding to fault and non-fault events. Evaluation results detailed in this paper demonstrate the negligible effects of frequency-selective grounding on responses of different ground fault protective relays.