Optimization of cold water temperature in forced draft cooling tower with various operating parameters has been considered in the present work. In this study, response surface method (RSM) and an artificial neural network (ANN) were developed to predict cold water temperature in forced draft cooling tower. In the development of predictive models, water flow, air flow, water temperature and packing height were considered as model variables. For this propose, an experiment based on statistical five-level four factorial design of experiments method was carried out in the forced draft cooling tower. Based on statistical analysis, packing height, air flow and water flow were high significant effects on cold water temperature, with very low probability values (< 0.0001). The optimum operating parameters were predicted using RSM, ANN model and confirmed through experiments. The result demonstrated that minimum cold water temperature was optioned from the ANN model compared with RSM.