Correct parametric extraction is vital for efficient photovoltaic cell designing and study of concerned system attributes, but the considerable nonlinearity of the results from the current–voltage curve makes this a difficult task. Consequently, in recent years, various interesting meta-heuristic techniques have been proposed to further expedite this development due to rapid advances in computer technology and swarm intelligence. In this work, two meta-heuristic methods, i.e., Genetic Algorithm and the Particle Swarm Optimisation method are used to identify the photovoltaic parameters of Zinc Oxide and Carbon Quantum Dots based hybrid cells. The values of optimised parameters, i.e., photo generated current, saturation current, series resistance, shunt resistance, using Genetic Algorithm are 0.567 mA, 0.077 mA, 61.282 Ω, 1.203 Ω respectively, and using Particle Swarm Optimization are 0.636 mA, 0.079 mA, 58.367 Ω, 0.975 Ω respectively. These results were validated using a highly potent optimization method, i.e., Artificial Neural Network using the firefly algorithm, the predicted photovoltaic characteristics aided in superior energy management and the proper operation of the photovoltaic system. The optimised results are deployed in a solar trigeneration model which is used in a commercial building. To substantiate the application area, a simulation tool, Polysun 12.0.8, is utilised to simulate and analyse the performance of hybrid cells. It is understood that the cell optimised using Particle Swarm Optimization obtains 7.85 % higher efficacy than the one optimised using Genetic Algorithm. The ultimate aim is to improve the efficiency of the solar systems and cope with the energy requirements by providing sufficient power, cooling and heating energy.