Introduction: In the energy crisis, the technologically equipped micro-grid is a boon to the electrical power generation system. Whereas the popular solar photo-voltaic (PV) micro-grids have self-sustained capabilities with minimum transmission line loss es, no pollution, and power cuts. Moreover, yielding maximum power from the plant is a challenging task under different plant conditions and the use of an appropriate algorithm will support tracking the maximum PowerPoint. Aim and Methodology: The objective is to yield the maximum power from the solar PV micro-grid. Therefore a more realistic three diode model of a solar photovoltaic cell is developed using basic equations to study the effectiveness of the proposed nature-inspired Flower Pollination Algorithm (FPA). The algorithm is applied to analyze the parameter variations of the model in comparison to Perturb and Observation (P__ampersandsignamp;O), Ant Colony Optimization (ACO), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) algorithms to achieve the peak power. The simulations are performed on the Matlab version 2020a. Results and Conclusion: The supremacy of the proposed method is judged from the power yield capability of the plant and significant improvement in fill factor from 0.75 to 0.81 has been observed with the proposed algorithm and the proposed algorithm achieved the maximum peak within 0.2 seconds compared to the other algorithms. The variations in the nine parameters of the cell are analyzed with the proposed algorithm in comparison with the P__ampersandsignamp;O, ACO, GA, and PSO proves the effectiveness of the proposed algorithm. The developed model trained using FPA for power peak tracking is verified for different shading patterns. The fill factor and power yield capacity of the micro-grid also improved along with the fast convergence.