A Firefly Algorithm and Elite Ant System-Trained Elman Neural Network for MPPT Algorithm of PV Array

This article proposes a novel MPPT algorithm based on the firefly and elite ant system-trained Elman neural network (FA-EAS-ElmanNN). First, position of fireflies is randomly initialized by (FA), meanwhile individuals with higher attractiveness degree value are selected as optimal solution. Second, extra pheromones artificially released to boost positive feedback effect convergence rate system (EAS). Third, weight threshold (ElmanNN) updated FA EAS. Also, trained ElamnNN employed acquire maximum voltage photovoltaic (PV) array. At last, PID controller PWM technology adapted regulate switch time converter. Furthermore, MATLAB/Simulink adopted datasets irradiance, temperature, validate reliability superiority proposed under complex atmospheric conditions. The tracking characteristic, response speed, efficiency contrasted particle swarm optimization (PSO), colony (ACO), ACO-artificial (ACO-ANN), PSO-RBF (PSO-RBNFNN) via simulation. FA-EAS-ElmanNN 99.73%, compared ACO-ANN, PSO-RBFNN, PSO, ACO algorithm, which increased 0.49%, 0.58%, 1.2% %, 1.5%, respectively. Additionally, experimental setup built demonstrate characteristic algorithm.