On the use of supervised clustering in stochastic NMPC design
For control engineers implementing stochastic NMPC, this heuristic offers a potential computational speedup, but the lack of quantitative results makes its significance unclear.
The paper proposes a supervised clustering heuristic for real-time stochastic nonlinear model predictive control, reducing computational burden by updating a low-cardinality set of uncertainty vectors online. The method is illustrated with an example, but no concrete performance numbers are provided.
In this paper, a supervised clustering based-heuristic is proposed for the real-time implementation of approximate solutions to stochastic nonlinear model predictive control frameworks. The key idea is to update on-line a low cardinality set of uncertainty vectors to be used in the expression of the stochastic cost and constraints. These vectors are the centers of uncertainty clusters that are built using the optimal control sequences, cost and constraints indicators as supervision labels. The use of a moving clustering data buffer which accumulates recent past computations enables to reduce the computational burden per sampling period while making available at each period a relevant amount of samples for the clustering task. A relevant example is given to illustrate the contribution and the associated algorithms.