This paper presents a new solution to Unit Commitment (UC) problem based on a Modified Shuffled Frog Leaping Algorithm (MSFLA). The objective of this paper is to find the generation scheduling such that the total operating cost of thermal power plant 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 systems for the next 'H' hours. In addition minimum up/down time constraints have been directly coded, thus avoiding the use of many penalty functions that usually distort the search space. The test results for the systems of up to 100 units and comparisons with results obtained using Lagrangian relaxation, Genetic algorithm, Shuffled frog leaping algorithm, and Bacterial foraging methods are also reported. © 2012 Praise Worthy Prize S.r.l. - All Rigthts Reserved. © 2022 Elsevier B.V., All rights reserved.