A closed-loop particle swarm optimization（CLPSO） algorithm is proposed by mapping PSO elements into the closed-loop system based on control theories. At each step， a PID controller is used to calculate an updated inertia weight for each particle in the swarm from its last fitness. With this modification， the limitations caused by a uniform inertia weight for the whole population are avoided， and the particles have sufficient diversity. In solving unit commitment（UC） problems with the CLPSO algorithm proposed， novel strategies are adopted to reduce the problem dimensions and guarantee particle feasibility. Simulation results demonstrate the superiority of the method proposed in solving UC problems.