This paper deals with the application of gray wolf optimiser (GWO) based on an artificial neural network (ANN) to optimise the coupling of the Kerman combined cycle power plant (KCCPP) with multi-effect distillation desalination (MED) unit. Thermodynamic simulation of the initial power plant has been performed in the GT Pro simulator, and an extracted steam from the steam turbine was used to supply the required energy for the desalination plant. A desalination economic evaluation program called DEEP has been applied to calculate the cost of power and freshwater production. To optimise the system, a multi-objective fitness function has been defined to reach the minimum production cost and maximum performance in the dual-purpose plant. The optimisation procedure has been performed by combining an artificial neural network along with gray wolf optimiser, and the multi-objective fitness function has been predicted by a neural network at each stage of optimisation. In this analysis, the best value of 2.286 has been found for the fitness function by the gray wolf optimiser based on an artificial neural network. This fitness value has been obtained from 89.69 US$/MWh for electric power cost, 40.78% for net electric efficiency, 1.22 US$/m3 for freshwater cost, and 14 for gain output ratio. Highlight Kerman combined cycle power plant with 1912 MWe nominal power has been modelled. A multi-effect distillation desalination plant has been coupled to the power plant to supply 50,000 m3/day of freshwater. To find the optimal design of the dual-purpose plant, an artificial neural network was connected to the gray wolf optimiser algorithm. Multi-objective optimisation has been applied to increase efficiency and reduce costs in the dual-purpose plant.