<p>Short-term electrical load forecasting (STELF) is one of the crucial aspects of energy management systems, which helps in proper resource allocation and grid stability. In this paper, a novel approach has been proposed which leverages the advanced capabilities of the GRU model. This model is well known for its strength in capturing temporal dependencies of sequential data. Further, this approach is incorporated with the Class Topper Optimization Algorithm, which is a nature inspired meta-heuristic optimization process. The predictive capability of CTO-GRU model is enhanced by their integration through minimizing validation error via a time-ordered evaluation procedure to reach global optimal weight matrices. Further, the validity of the proposed framework is tested on real-time data sets through comprehensive experimentation. The resulting values demonstrate a significant gain in the accuracy, which justifies the better predictive capability achieved by the proposed approach. Through a proper analysis of the results, it can be assured that the proposed approach is suitable for enhancing the performance of the STELF. This research also provides opportunities for further improvement in the load forecasting methods by showing the advantages of combining state-of-the-art machine learning (ML) models with creative optimization algorithms to solve difficult real-world problems.</p>