Plastic solar cells are attractive candidates for providing cheap, clean, and renewable energy. However, such devices are critically dependent on the internal structure, or morphology, of the polymer constituents. We have developed a model that enables us to predict photovoltaic behavior for arbitrary morphologies, which we also generate from numerical simulations. We illustrate the model by showing how diblock copolymer morphologies can be manipulated to optimize the photovoltaic effect in plastic solar cells. In this manner, we can correlate photovoltaic properties with device structure and hence guide experiments to optimize polymer morphologies to meet photovoltaic needs.