Population-Based Meta-Heuristic Optimization Algorithm Booster: An Evolutionary and Learning Competition Scheme

<p dir="ltr">In a Population-Based Meta-Heuristic Optimization Algorithm (PMOA), individuals in the population<br>will constantly generate new promising individuals, to form new populations. Although the population<br>continuously changes, the variations in each individual are traceable in most algorithms. An individual<br>in the population comes from the individual in the previous population. The direction of the evolution<br>of populations can be identified on top of this historical inheritance relationship, which improves<br>the efficiency of PMOAs and solves optimization problems more effectively. Since Recurrent Neural<br>Networks (RNNs) are able to capture the temporal dependencies in sequences, we are motivated to<br>propose a novel but simple Evolutionary and Learning Competition Scheme (ELCS), also referred<br>to as the PMOA Booster, in which individuals keep changing for the better fitness based on the<br>heuristic rules of the PMOA while an RNN is used to learn the process that each individual changes<br>in order to guide the generation of promising individuals. The ELCS automatically selects the RNN<br>or PMOA which generates more individuals with the better fitness. We test the proposed scheme<br>using the benchmark of IEEE Congress on Evolutionary Computation 2022 competition (CEC 2022).<br>The results show that this scheme is able to boost the performance of both the classical and state-of-<br>the-art PMOAs and outperforms its counterparts. Also, the ELCS produces promising results in two<br>real-world industrial scenarios. We believe that the effectiveness of the proposed ELCS is due to the<br>adaptive competition between the RNN and the PMOA.</p>