Modified Ant Colony Optimization Technique for Solving Unit Commitment Problem

Ant colony optimization (ACO) which is inspired by the natural behavior of ants in finding the shortest path to food is appropriate for solving the combinatorial optimization problems. Therefore, it is used to solve the unit commitment problem (UCP) and attain the minimum cost for scheduling thermal units in order to produce the demand load. In this paper modified ACO (MACO) is used to solve the UCP in which particle swarm optimization (PSO) is used to find the ACO parameters and genetic algorithm (GA) is used to solve economic dispatch and to minimize the generation cost in order to select the committed units appropriately. At first, all possible combinations that satisfy the demanded load and spinning reserve are calculated by means of genetic algorithm and the minimum economic generation cost of each state is calculated to make the ants search space (ASS). Then the artificial ants are allowed to search in this space. Problem formulation takes into consideration the minimum up and down time constraints, startup cost, shutdown cost, spinning reserve, and generation limit constraints. The feasibility of the proposed method in two systems is explained and the results are compared with the other methods. The results reveal that the suggested algorithm is more encouraging than the other ones.