Smart grid deployment is a global trend, creating endless possibilities for the use of data generated by dynamic networks. The challenge is the transformation of this large volume of data into useful information for the electrical system. An example of this is the application of demand side management (DSM) techniques for the optimization of power system management in real time. This project discusses the use of DSM in this new environment of electrical system and it presents a simulation that uses data acquired from digital meters, it creates patterns of load curves, uses these patterns load data to train and validate Artificial intelligence and uses this to classify new data using these defined patters. The results obtained in this study show that the implementation of DSM presented a satisfactory performance for the classification of load curves.