Open Radio Access Network (O-RAN) is the most promising solution for future RAN deployments. This attractive and efficient solution presents complex and new challenges w.r.t to cost, energy consumption and other performance indicators. In this work, we study function placement in the Open Radio Access Network (O-RAN) architecture. Our objective it to minimize the operating costs, while respecting other network constraints. We consider a RAN load that varies over the day and we study the ORAN-DUs (ORAN-Distributed Units) placement for different frequency bands. We use data obtained from real topology. First, we analyze the percentage of utilization, throughput and Modulation and Coding Scheme (MCS) selections of each frequency band for each hour of the day. Based on our analysis, we propose an Integer Linear Programming (ILP) model whose objective is to minimize computing and routing cost while respecting the delay and capacity constraints of ORAN interfaces. Our results analyse the cost savings of the proposed model w.r.t the DRAN (Distributed RAN), the solution prevailing before ORAN, during off-peak and peak hours.