Incremental Proximal Multi-Forecast Model Predictive Control

TL;DR

This paper introduces an incremental proximal approach to multi-forecast model predictive control, enabling efficient computation of coupled plans across multiple scenarios with comparable performance to full multi-forecast methods.

Contribution

It proposes a novel incremental proximal method for solving coupled multi-forecast MPC problems efficiently, even without full convergence.

Findings

IP-MPC achieves significant improvements over single-forecast MPC.

Partial iterations of IP-MPC still retain most benefits of full multi-forecast control.

The method simplifies solving complex multi-scenario control problems.

Abstract

Multi-forecast model predictive control (MF-MPC) is a control policy that creates a plan of actions over a horizon for each of a given set of forecasted scenarios or contingencies, with the constraint that the first action in all plans be the same. In this note we show how these coupled plans can be found by solving a sequence of single plans, using an incremental proximal method. We refer to this policy as incremental proximal model predictive control (IP-MPC). We have observed that even when the iterations in IP-MPC are not carried out to convergence, we obtain a policy that achieves much of the improvement of MF-MPC over single-forecast model predictive control (MPC).