What price to pay? Auto-tuning a building MPC controller for optimal economic cost

TL;DR

This paper presents an automated hyperparameter tuning method using Constrained Bayesian Optimization for building MPC controllers, significantly reducing electricity costs in demand-side management.

Contribution

It introduces a novel automated tuning approach for MPC in DSM, achieving substantial cost savings over manual and rule-based controllers.

Findings

Optimized MPC reduced costs by 26.90% compared to rule-based control.

Cost savings of 17.46% over manually tuned MPC.

Optimal DSM program selection can lower bills by up to 20.18%.

Abstract

Demand-side management (DSM) programs introduce complex pricing, requiring advanced control for cost minimization. Model Predictive Control (MPC) offers a solution but its performance hinges on appropriate hyperparameter tuning. We propose using Constrained Bayesian Optimization (CONFIG) to automate this process. In a case study, our optimized MPC reduced electricity costs by 26.90% compared to a rule-based controller and by 17.46% versus an manually tuned MPC. Analysis of real contracts further showed that optimal DSM program selection can lower monthly bills by up to 20.18%, demonstrating a data-driven path to significant consumer savings.