In this paper, a computationally efficient frequencylimited model reduction algorithm is presented for large-scale interconnected power systems. The algorithm generates a reduced order model which not only preserves the electromechanical modes of the original power system but also satisfies a subset of the first-order optimality conditions for H2,ω model reduction problem within the desired frequency interval. The reduced order model accurately captures the oscillatory behavior of the original power system and provides a good time-and frequency-domain accuracy. The proposed algorithm enables fast simulation, analysis, and damping controller design for the original large-scale power system. The efficacy of the proposed algorithm is validated on benchmark power system examples.