Institute of Electrical & Electronic Engineers
Model Predictive Control (MPC) is an optimization-based scheme that imposes a real-time constraint on computing the solution of a Quadratic Programming (QP) problem. The implementation of MPC in fast embedded systems presents new technological challenges. In this paper, the authors present a parameterized Field-Programmable Gate Array (FPGA) implementation of a customized QP solver for optimal control of linear processes with constraints, which can achieve substantial acceleration over a general purpose microprocessor, especially as the size of the optimization problem grows. The focus is on exploiting the structure and accelerating the computational bottleneck in an existing primal-dual interior-point method.