A Novel Hybrid TLBO-RAT Algorithm for Optimal and Cost-Effective Power Generation Scheduling

This research addresses the Economic Load Dispatch (ELD) problem in power systems by proposing an innovative hybrid approach, integrating the Teaching-Learning-Based Optimization (TLBO) and Rat-in-aTube (RAT) algorithm. Applied to the IEEE 14-bus and IEEE 30-bus systems, the methodology optimizes generator output levels while considering constraints like capacity limits and transmission line losses. Leveraging TLBO’s teaching and learning phases and RAT’s exploration-exploitation trade-off enhancement, the hybrid algorithm demonstrates superior performance in achieving optimal or near-optimal ELD solutions. Using realistic parameters, results showcase faster convergence and higher solution quality compared to traditional optimization methods. This study contributes a powerful hybrid algorithm for ELD, offering valuable insights for efficient and sustainable economic load dispatch in intricate power networks. To differentiate from conventional optimization approaches, the proposed algorithm’s performance is evaluated through comparative analyses. These evaluations emphasize the algorithm’s advantageous characteristics concerning the speed of convergence and the quality of solutions, showcasing its effectiveness in comparison to established methods in the field. This research contributes to the field of power system optimization by introducing a hybrid algorithm that integrates the strengths of TLBO and RAT to address the ELD problem.