Energy hubs (EHs) are considered a promising solution for multi-energy resources, providing advanced system efficiency and resilience. However, their operation is often challenged by the need for techno-economic trade-offs and the uncertainties related to supply and demand. This research presents a multi-objective optimizing framework for EH operations tackling these techno-economic aspects under uncertainty. Utilizing artificial neural networks (ANN)-based active learning (AL), the proposed approach dynamically enhances the model’s capability to achieve optimal scheduling and planning while considering complex, fluctuating energy demands and system constraints. The optimization approach under uncertainty provides robust predictive abilities across various scenarios, allowing the system to optimize energy management effectively, enhancing operational efficiency while minimizing overall energy losses, costs, and emissions. Results demonstrate significant improvements in system reliability, cost efficiency, and flexible operation, validating the effectiveness of ANN-based AL to optimize EHs management and ensure sustainable operation complexities. The AL algorithm enhances the ANN model’s predictive ability, resulting in a 57.9% decrease in operating costs and a 0.010682 loss of energy supply probability (LESP) value. It ensures energy efficiency while sustaining system flexibility, adapting to frequent load dynamics and intermittent renewable energy supply. The algorithm minimizes electrical and thermal deviations, achieving a balance of flexible operation with efficient energy management. Despite uncertainties and intermittent renewable energy supply, the AL optimizes renewables utilization and demand adjustments, reducing energy losses, costs, and emissions by 80.3The optimized system achieves an output of 13,687.8 kW per day. The system’s implementation is performed using MATLAB R2023b software, ensuring precision and efficiency.

A multi-energy resource aims to maintain a balance between energy output and load consumption and to ensure power continuity during different operating conditions. The harmonic distortions can be estimated from the output current of a harmonic source, which may not fully reflect its true harmonic distortions due to the interactions between the state changes at the power network level and the harmonic sources. System operators monitor each system's harmonic performance under different conditions of operation to find the actual contribution of grid-connected systems to harmonic-related issues. Development of machine learning algorithms leads to effective progress in the harmonic prediction and computation. In this paper, the combined data sequencing, and Bidirectional Long-Short Term Memory (Bi-LSTM) network has been exploited for the real-time harmonic prediction of future events in multi-energy sources. The validity of the proposed Model including the applications of ANFIS, ANNs, MLRA and LSTM is conducted on the two standard systems as IEEE 9-bus and IEEE 34-bus multi energy resources system that is associated with PV systems. The simulation results, based on climate changes of solar irradiance and ambient temperature in PV systems, demonstrate that the proposed methods can accurately forecast changes in total harmonic distortion (THD) as well as the voltage profile at the point of common coupling. The performance of Bi-LSTM, original LSTM, Machine Linear Regression (MLR), and Artificial Neural Networks (ANNs) techniques were assessed. These findings provide valuable insights. Four performance validation indices, RMSE, R-squared and MSE are considered to assess the performance of the competitive learning algorithms. The results showed that in the model IEEE 9-bus, Bi-LSTM outperformed all the applied methods as its RMSE value was 0.000019 while its MSE value was 3.61e-10 and finally, the Bi-LSTM had a higher value squared error (R²) was equal 1 which indicates the effectiveness of Bi-LSTM for predicting sequential total harmonic distortion. On the other hand, in case study of IEEE 34-bus, the RMSE, MSE and R² are 0, 3.276e-30 and 1 using Bi-LSTM which means that the Bi-LSTM leads to the best performance validation indices compared to other competitive algorithms for the tested multi-energy systems.

Electric Vehicles (EVs) play a pivotal role in advancing environmental sustainability and accelerating the transition toward clean energy systems. However, large-scale EV adoption poses significant operational challenges, particularly when charging and discharging activities are uncoordinated, potentially leading to elevated peak demand and increased grid stress. Effective scheduling techniques are therefore essential to ensure reliable integration of EVs into modern power systems. This study provides a rigorous comparative evaluation of two metaheuristic optimization paradigms for EV charging and discharging scheduling: the traditional Particle Swarm Optimization (PSO) algorithm and the more recent Transit Search Optimization (TSO) algorithm. Using an identical system configuration and EV dataset, the study assesses the performance of both approaches based on peak power reduction, cost minimization, and overall system efficiency. Results demonstrate that while enhanced PSO scenarios exhibit noticeable improvements over earlier literature, TSO consistently achieves superior outcomes due to its stronger exploration-exploitation balance. In particular, TSO attains a 46.23 % reduction in average EV charging cost and achieves the lowest power-loss levels across all tested scenarios. Relative to the best previously published benchmarks, TSO further improves peak power consumption by 1.6 % and total charging cost by 6.1 %. These findings highlight TSO’s strong potential as a high-efficiency scheduling tool for large-scale EV integration in future smart grid environments.