The reduction of power consumption in wireless access networks is a challenging and important issue. In this paper, we apply Opposition-Based Learning (OBL) concepts for reducing the power consumption of LTE base stations. More specifically, we present a new Modified Biogeography Based Optimization (BBO) algorithm enhanced with OBL techniques. We apply both the original BBO and the new Modified Opposition BBO (MOBBO) to network design cases to the city of Ghent, Belgium, with 75 possible LTE base station locations. We optimize the network towards two objectives: coverage maximization and power consumption minimization. Preliminary results indicate the advantages and applicability of our approach.