Feedback control of event rate in online advertising campaigns

An actuation and feedback control algorithm is proposed for the specific objective of scalable event rate control in online advertising systems. The actuator employs the beta actuation mechanism to address discontinuity in the plant under control with adjustable plant gain, while the feedback controller implements a PI mechanism to regulate the event rate to stay at or above a user-specified reference. Effectiveness of the proposed scheme is demonstrated via simulations and validated with the in-view rate control and the video completion rate control of real advertising campaigns on the AdLearnTM advertising optimization system, developed at AOL.