Real power loss reduction by extreme learning machine based Panthera leo, chaotic based Jungle search and Quantum based Chipmunk search optimization algorithms

In this paper Extreme Learning Machine based Panthera leo Optimization Algorithm (ELMPO), Chaotic based Jungle search optimization (CJSO) algorithm and Quantum based Chipmunk Search (QCS) Optimization algorithm are applied to solve the power loss lessening problem. Extreme learning machine (ELM) is applied and learning speed of feed-forward neural networks is composed of input, hidden and output layer. Regular performances of Panthera leo are imitated to model the Panthera leo Optimization (PO) Algorithm. Panthera leo certainly lives as cluster. Panthera leos act as Executioners to quest the Victim. Full-fledged male Panthera leo will bout with other males to attain the room of dominance. The beaten Panthera leo will be as Refugee Panthera leo. Principally several times there will be modification between inhabitant and refugee Panthera leos. Together male and female Panthera leo shifts their places with orientation to the environments. In the preliminary population dominance and Refugee sorting are completed. For every Panthera leo fitness rate will be calculated. In Panthera leo population poise in conclusion of iterations, the quantity of prevailing Panthera leo will be meticulous. With orientation to the extreme permitted number of every gender in $$\mathrm{Refugee Panthera leo}$$ Refugee Panthera leo ; the minimum sum fitness rate obsessed by $$\mathrm{Refugee Panthera leo}$$ Refugee Panthera leo will be impassive. Extreme Learning Machine (ELM) is integrated with Panthera leo Optimization (PO) Algorithm and it entitled as ELMPO. Jungle search optimization algorithm is modelled based on the systematized performance of search squads viewing for lost entities in a jungle. Rendering to Jungle search optimization algorithm, as squads each comprising numerous professionals in the pursuit arena banquet out transversely in the jungle and progressively progress in the identical route by discovering the traces from the mark up until they discover the lost entity. This search organization is modelled in a scientific method in the arrangement of Inter-cooperative pursuit operatives and transporting the skilful associate to the first of the squad. Double procedures are smeared to shape the squads to do active search processes in all jungles and highland zones. The primary procedure is a local examination done by every squad; the leader of every squad assigns zones to every associate and provides them the accountability of examining that portion. The leader is informed of any trace discovered by squad associates and they will direct extra squad associate to that zone for additional effective examination to expand the search. Consequently, all squad associates effort to conduct an active search in the zones allotted to them. In the subsequent procedure, the squad that discovers maximum traces is obligatory by other squads. In detail, leaders of squads direct one of their squad associates to the squad with the maximum traces for assisting and do an active search in the jungles and highland. In the interim, certain associates continue in the squads that discover the minimum traces in order to endure the examination in the jungles and highland in the circumstances of any error made by the upper squad. Quantum based Chipmunk Search (QCS) Optimization Algorithm is based on the deeds of chipmunk and Quantum mechanism has been incorporated in the algorithm. Chipmunk spirited searching scheme and sashaying along procedure are simulated systematically to model the algorithm. When Chipmunk instigates the searching then examining procedure activates. In the segment of autumn period Chipmunk pursue for nutrition resources by sashaying in various trees and they alter the locations and regulate dissimilar area of the tropical forest. Quantum mechanism has been incorporated in the procedure.Through incorporation Quantum computing, algorithm performance has been advanced. Repositioning of Chipmunk at the conclusion of wintertime season is hypothesized. Gene collection, both breadth reductions in addition to upholding the accurateness of the designated genes is significant. As a replacement for of working for a repositioning of Chipmunk, the quantity of genes is abridged by in view of all the genes in the amalgamation of the trees in jungle; uppermost three Chipmunks is considered in the work. Subsequently to decrease, the Chipmunk is allocated haphazard locations in the abridged exploration zone. The wintertime is taken as to conclude when all trees in jungles possess fitness value superior than vibrant bound factor. Proposed Extreme Learning Machine based Panthera leo Optimization Algorithm (ELMPO), Chaotic based Jungle search optimization (CJSO) algorithm and Quantum based Chipmunk Search (QCS) Optimization algorithm are corroborated in IEEE 30, 57, 118, 300 and 354 bus test systems. True power loss lessening, power divergence curtailing, and power constancy augmentation has been achieved.