Multi-objective optimization problem-solving based on evolutionary algorithms and chaotic systems

Dynamical systems that exhibit a high degree of sensitivity to the parameters of their initial states are referred to as chaotic. Natural selection and the process of evolution are the models that inspire a group of optimization algorithms collectively referred to as evolutionary algorithms (EA). EA is quite beneficial when handling difficult optimization difficulties, especially in situations where traditional procedures are either not practical or insufficient. The resolution of goal conflicts is accomplished through multi-objective optimization (MOO). The study proposed using chaotic systems and evolutionary algorithms to address the issue of multi-objective optimization.An initially chaotic time series of wind speed predictions was gathered from three locations in Penglai, China. The preprocessing of these data was carried out using Z-score normalization. We suggested using multi-objective particle swarm optimization (MOPSO) to gather information. Before the suggested design can be applied to the MOPSO of the chaotic system itself, it is required to evaluate the architecture of the proposed that will be utilized, the functioning of the chaotic systems, and the problems in the design of the system. Studies using currently available methods demonstrate that the proposed method outperforms all parameter measurements in terms of 15bits of throughput, active power loss 6.4812 MVA, 0.6495 voltages, 6.8% of RMSE, 0.8% of MAPE, and 0.1 sec of time. The finding of combining evolutionary algorithms with chaotic systems yields a powerful and effective framework for addressing multi-objective optimization problems, which bodes well for practical implementations in fields like building design, economics, and time management.