LiFT-MPC: Language-in-the-Loop Feedback Tuning of Cost Previews for MPC

2026-07-26

AI Summary

This work addresses the challenge in model predictive control (MPC) of accurately forecasting time-varying targets—such as electricity prices—that are heavily influenced by external events and thus difficult to predict from historical data alone. To this end, the paper introduces LiFT-MPC, a novel framework that, for the first time, incorporates linguistic contextual information into the MPC prediction-correction loop. By dynamically parsing online textual sources such as news articles, the method adjusts forecast signals in real time and uses control performance loss as a feedback signal to drive online updates of the prediction model. This approach enables performance-oriented closed-loop learning, demonstrably enhancing economic efficiency in real-world energy storage systems while providing formal guarantees of closed-loop stability.

Abstract

In model predictive control (MPC) with time-varying objectives, predicted signals need to be often incorporated in the cost function, such as prices in energy system operation. These are, however, often difficult to predict from the historical trajectory of these signals alone, as they may depend on other contextual events. We propose LiFT-MPC, an MPC framework that integrates a LiFT (Language-in-the-Loop Feedback Tuning) correction scheme to refine such predictions within the MPC loop. The prediction mechanism is updated online via a control-performance loss function, and we establish a performance guarantee for the resulting closed loop system. Numerical experiments using a realistic example of energy-storage management with real prices and news context to improve predictions, demonstrate an improved economic performance

Problem

• model predictive control
• time-varying objectives
• cost function
• signal prediction
• contextual events

Innovation

• Language-in-the-Loop
• Model Predictive Control
• Online Feedback Tuning
• Context-Aware Prediction
• Control Performance Guarantee