In the context of ultra‐dense heterogeneous networks in 5G, we focus on the load balancing problem of elastic traffic in a single macrocell that is supported by a number of small cells. Each small cell is modeled by a single‐class processor sharing queue, whereas the macrocell is modelled by a multiclass processor sharing queue. We assume that the macrocell is always consuming energy, while a small cell can be switched off when it is idle with the setup delay penalty. As the main contribution, aimed at minimizing the weighted sum of the mean delay and the mean power consumption in the system, we develop static and dynamic load balancing policies that take into account the setup delay. All the obtained results are analytically founded. The performance of the static policy is evaluated using the achieved analytical expressions, which include the static optimal probabilities achieved before, whereas for the dynamic policy we need to perform simulations using previously obtained numerical results from the first policy iteration procedure. As concluded, numerical results indicate that the dynamic policy outperforms the static policy under realistic settings.