This paper presents a new approach to solve short-term unit commitment problem (UCP) using neural based tabu search (NBTS). The solution of the unit commitment problem is a complex optimization problem. The exact solution of the UCP can be obtained by a complete enumeration of all feasible combinations of generating units, which could be very huge number. The unit commitment has commonly been formulated as a nonlinear, large scale, mixed-integer combinational optimization problem. The objective of this paper is to find the generation scheduling such that the total operating cost can be minimized, when subjected to a variety of constraints. This also means that it is desirable to find the optimal generating unit commitment in the power system for next H hours. Neyveli thermal power station - II in India, demonstrates the effectiveness of the proposed approach. Numerical results are shown to compare the superiority of the cost solutions obtained using the tabu search (TS) method in reaching proper unit commitment.