In Electric power system operations forecasting is an integral part, as it is the primary prerequisite for achieving the goal of optimal planning and operation of power systems. Short term load forecasting is necessary for the control and scheduling operations of a power system and also acts as input to the power analysis functions such as load flow and contingency analysis. This paper deals in short term load forecasting using adaptive neuro-fuzzy inference system (ANFIS). The set of inputs utilized to perform STLF is non- linear, therefore an adaptive decision-making system is attempted for the purpose of accurately mapping the inputs to the output. An ANFIS based system has the merits of fuzzy logic capable of mimicking the way human beings reason, and artificial neural networks with the adaptive learning ability. Such a hybrid system is composed of fuzzy if-then rules. For this workload and temperature data of March month is used and load is forecast for working day. For this work consider Holiday is Sunday, Preholiday is Saturday, Post-holiday is Monday and Working day is Tuesday, Wednesday, Thursday and Friday. The Training and Testing of ANFIS is done using MATLAB version7, R2013a.