This article presents the concept of boundary-based predictive controller (BBPC) as an effective tool to control industrial processes with on--off actuator, for which the control goal is defined to keep the process output within the desired range. An example use of BBPC is shown in application to control of dissolved oxygen (DO) concentration in the laboratory activated sludge setup with biological reactor. It is suggested how to identify dynamical parameters of the proposed DO concentration model and how to provide adaptability required to ensure desired control performance in the presence of significant changes of process load disturbance. Practical implementation in programmable logic controller in the form of a general purpose library function block is also presented. Experimental comparison with conventional on–off controller shows robustness and superiority of the proposed BBPC.