The power consumption foreseen for 5G networks is expected to be substantially greater than that of 4G systems, mainly because of the ultra-dense deployments required to meet the upcoming traffic demands. This paper deals with a multi- objective formulation of the Cell Switch-Off (CSO) problem, a well-known and effective approach to save energy in such dense scenarios, which is addressed with an accurate, yet rather unknown multi-objective metaheuristic called MOCell (multi- objective cellular genetic algorithm). It has been evaluated over a different set of networks of increasing densification levels. The results have shown that MOCell is able to reach major energy savings when compared to a widely used multi-objective algorithm.