Due to high nonlinearity with features of large time constants, delays, and interaction among variables, control of the wastewater treatment plants (WWTPs) is a very challenging task. Modern control strategies such as model predictive controllers or artificial neural networks can be used to deal with the non-linearity. Another characteristic of this system should be considered is that it works repetitively. Iterative learning control (ILC) is a potential candidate for such a demanding task. This paper proposes a method using ILC for WWTPs to achieve new results. By exploiting data from the previous iterations, the learning control algorithm can improve gradually tracking control performance for the next runs, and hence outperforms conventional control approaches such as feedback controller and model predictive control (MPC). The benchmark simulation model No.1-BSM1 has been used as a standard for performance assessment and evaluation of the control strategy. Control of the dissolved oxygen in the aerated reactors has been performed using the PD-type ILC algorithms. The obtained results show the advantages of ILC over a classical PI control concerning the control quality indexes, IEA and ISE, of the system. Besides, the conventional feedback regulator is designed in a combination with the iterative learning control to deal with uncertainty. Simulation results demonstrate the potential benefits of the proposed method.