This study presents a weighted-sum multi-criteria optimization framework using PSO for the optimal siting, sizing, and scenario-based operation of energy storage systems (ESSs) in renewable-integrated distribution networks. The proposed model concurrently addresses technical, economic, and reliability objectives—minimizing active power losses (PL), voltage deviation (VD), expected energy not supplied (EENS), and short-circuit level (SCL), while maximizing voltage sensitivity index (VSI) and power-loss sensitivity factor (PLSF). A Particle Swarm Optimization (PSO) algorithm with weighted-sum scalarization is employed to solve this complex, nonlinear optimization problem and effectively balance the conflicting operational goals. The framework is validated using IEEE 69-bus and IEEE 118-bus test systems under varying load conditions (20%, 50%, 100%, and 150%) with time-dependent photovoltaic (PV) and wind turbine (WT) generation profiles. Results demonstrate that the proposed approach achieves significant performance enhancements, reducing power losses by up to 54%, EENS by 88%, and operational cost by 22% while maintaining SCL values within protection limits. Furthermore, the inclusion of ESS units improves system reliability and voltage stability, ensuring smooth operation during load fluctuations and fault conditions. The findings confirm that the proposed weighted-sum multi-criteria optimization framework using PSO provides a scalable and protection-aware solution for integrating ESSs into renewable-rich distribution networks. It offers a robust planning and operational tool for next-generation smart grids, enabling a more efficient, resilient, and sustainable energy ecosystem.

Accurate electricity load forecasting is crucial for optimizing power distribution networks, especially in rapidly growing cities like Tabriz (annual consumption growth of 7.2%). This study presents a hybrid AI framework integrating the Temporal Fusion Transformer (TFT) and XGBoost for residual error correction. The model is trained and evaluated using actual consumption data from Tabriz’s distribution network (2021–2023). Compared to a baseline TFT model, the proposed framework demonstrates a 11.2% reduction in RMSE (from 0.1249 to 0.1109) and a 10.7% decrease in MAE (from 0.0998 to 0.0891). Attention mechanism analysis reveals temperature (importance coefficient = 0.32), weekly patterns (0.18), and industrial activity (0.21) as key factors influencing electricity consumption in Tabriz. Achieving a MAPE of 4.2%, the framework provides actionable insights into consumption drivers. This research demonstrates the effectiveness of the proposed model in managing load fluctuations characteristic of medium-sized cities and offers potential for adaptation to similar urban contexts. The dual capability for accurate prediction and interpretable feature analysis establishes a new benchmark for smart grid analytics in emerging smart city environments.