Increasing urbanization and the global transition toward sustainable, eco-friendly energy systems require efficient and robust energy predictions for smart grids. The inherently unpredictable, volatile, and intermittent nature of energy demand necessitates an accurate short-term load forecasting model to ensure reliable consumer applications. However, conventional deep learning models often struggle to address complex and dynamic load patterns. To address these challenges, this research presents a novel trustworthy GAI-assisted model comprising i) a variational autoencoder that maps raw energy consumption data to extract meaningful and compact features and ii) a deep learning model utilizing a dual attention mechanism with convolutional long short-term memory (DAConvLSTM), that effectively captures the temporal dependencies of the complex load pattern and optimizes forecasting accuracy. The effectiveness and robustness of the proposed model are extensively evaluated using publicly available comprehensive datasets. The results demonstrate the performance of the proposed model, with an overall improvement of 1.45%81.54% in the mean absolute error, 1.92%78.61% in the root mean square error, and 1.55%81.85% in the mean absolute percentage error compared with other baseline methods. The results validate the effectiveness of the proposed model in predicting peak load demand and have practical implications, thereby enhancing the existing knowledge for creating robust energy management in smart grid applications.

Ever-increasing dynamic surges in renewable-based electric power systems, notably wind and photovoltaic farms bring adverse impacts and challenges in terms of reliability and stability. The intermittency of renewable sources imposes significant deviations in frequency due to variations in demand. Wind power induces instability in the grid due to its vulnerable nature, and reduction in system inertia. To mitigate these dynamics issues, an optimal control technique based on flatness-based Active disturbance rejection control (FADRC) and utilizing an enhanced Beluga Whale optimization algorithm (EBWO) for a multi-area interconnected power system with photovoltaic generation. The proposed LFC model addresses the load perturbation and the deviation of tie-line power, with system uncertainties considered as lumped disturbances that are approximated by extended state observers. To achieve optimal performance, the Enhanced Beluga Whale optimization algorithm is adopted and integrated with the suggested controller to fine-tune the controller. To validate the formidable performance of the suggested scheme, different cases have been studied with the existing approaches. The simulation results reveal the supremacy and robustness of the dynamic response of the Flatness-based active disturbance rejection control as compared to other approaches under load variations and parameter uncertainty.

Rapid advancements in urbanization and industrialization have increased consumer-end applications in smart grids, where advanced data-driven methods have significantly improved consumer-level energy management using smart meters. However, these systems are highly vulnerable to cyberattacks, notably false data injection attacks (FDIA), which can compromise grid reliability and stability. Existing detection techniques often rely on centralized data collection and processing, which raises substantial privacy concerns and leads to overfitting due to limited data diversity. To address these issues, this paper presents a novel framework that integrates federated learning with an autoencoder-based 1D deep convolutional neural network (AE-1DdeepCNN) for FDIA in consumer applications. The proposed framework enables collaborative model training based on the IEEE-14 bus system dataset for anomaly detection while ensuring data privacy. Extensive experimental results with row-accuracy of 93.35%~99.40% in different smart meters demonstrate the effectiveness and robustness of the proposed method for FDIA detection in smart grid systems and consumer smart metering applications.

A major problem in the photovoltaic (PV) system is to determine the maximum power point (MPP) and to overcome the limitations of environmental change. To resolve the limitation of different techniques with high convergence rate and less fluctuations, a hybrid model of fractional open circuit voltage is proposed. For partial shading, incremental conductance is used. The proposed technique is extremely useful, provides high efficiency, and takes less time to achieve the MPP. The tenacity of the proposed method has been checked using MATLAB/Simulink, which clearly shows that the proposed technique has high efficiency compared to other MPP tracking methods.