Computational Intelligence-based Economic Load Dispatch Solutions for IEEE-30 BUS Microgrid

This Fuel is a major source of power generating. However, fluctuating crude oil prices will significantly impact the cost of energy generation. A pre-offline analysis is a viable option for power system planners to prevent unwanted events. To get the desired outcome, an optimization method is necessary to identify the best parameters. This paper presents a novel method for optimizing economic load dispatch (ELD) in a 30-bus microgrid by combining Deep Neural Networks (DNN) with Non-dominated Sorting Genetic Algorithm II (NSGAII) and Particle Swarm optimization (PSO). The suggested approach seeks to reduce total operating expenses as well as CO2 emissions. In order to classify and feed the optimal generation levels into a DNN for categorization into Good, Moderate, and Bad load dispatch situations, the NSGAII algorithm effectively finds optimal generation levels. These findings demonstrate how well the suggested approach performs in improving microgrid operations' economic viability and environmental sustainability, making it a viable option for upcoming smart grid applications.