Constrained Multi-Objective Optimal Combined Economic Emission Dispatch

In this paper, researchers adopt multi-objective particle swarm optimization to tackle the issue of multi-objective combined economic emission dispatch (CEED). The equality and inequality restrictions in this optimization process make it non-linear. In most cases, it divides up the total amount of power generated by all the units in a given system. Primary goals include lowering fuel costs and minimizing environmental impact within prescribed constraints. Economic dispatch is often formulated as a nonlinear system, and the resulting solutions often fall behind expectations. However, these methods are not suitable for solving the economic dispatch issue because of their non-convex character. Several AI methods are used for the economic dispatch issue due to its complexity and the fact that it is neither linear nor smooth. The conventional form of the meta-heuristic approach, particle swarm optimization (PSO), has difficulty dealing with such difficulties, yet it is still widely utilized. In order to solve this issue, this work presents an updated form of particle swarm optimization. The efficiency of the customized version of specific swarm optimization (PSO) is verified in the MATLAB Simulink environment. Finding a Pareto-optimal, industrially, the multi-objective solution to the emission dispatch issue using multi-objective particle swarm optimization is shown to be a viable option.