A new approach using Neural Based Fuzzy (NBF) is proposed for the unit commitment of a power system. The objective of the paper is to find the generator scheduling such that the total operating cost can be minimized, when subject to a variety of constraints. This method allows a qualitative description of the behavior of a system, the system's characteristics, and response without the need for exact mathematical formulations. It is demonstrated through numerical example that a Neural based fuzzy approach achieves a logical and feasible economical cost of operation of the power system, which is the major objective of Unit Commitment (UC). The Neural- Network is a powerful tool for optimization problems that has been successfully applied to a number of combinatorial optimization problems. It has the ability to avoid entrapment in local minima by employing a f l exible memory system. Fuzzy logic is having the capability of qualitative representative of results in terms of input variables. The solution of Unit Commitment is a two stage process and it uses the advantage of both approaches. In the first stage the generator schedule is produced using Neural Network and in the second stage the production cost is calculated using fuzzy logic model. By doing so, it gives the optimum solution rapidly and efficiently. The Neyveli Thermal Power Station (NTPS) unit II in India has been considered as a case study and extensive studies have also been performed for different power systems consisting of 10, 20, and 26 generating units. Numerical results obtained by NBF are compared with conventional methods like DP and Lagrangian Relaxation (LR) to reach proper unit commitment.