MILP-based Imitation Learning for HVAC control

TL;DR

This paper introduces a MILP-based imitation learning approach for HVAC control that avoids forecast errors, leading to better energy efficiency and thermal comfort compared to forecast-based methods, with near-optimal performance.

Contribution

The study presents a novel MILP-based imitation learning method for HVAC control that does not rely on forecast data, improving performance over forecast-dependent approaches.

Findings

MILP-based imitation learning outperforms forecast-based MILP in energy and comfort metrics.

The learned controller's performance is nearly optimal compared to full-information solutions.

The method effectively uses historical data to train a neural network for real-time HVAC control.

Abstract

To optimize the operation of a HVAC system with advanced techniques such as artificial neural network, previous studies usually need forecast information in their method. However, the forecast information inevitably contains errors all the time, which degrade the performance of the HVAC operation. Hence, in this study, we propose MILP-based imitation learning method to control a HVAC system without using the forecast information in order to reduce energy cost and maintain thermal comfort at a given level. Our proposed controller is a deep neural network (DNN) trained by using data labeled by a MILP solver with historical data. After training, our controller is used to control the HVAC system with real-time data. For comparison, we also develop a second method named forecast-based MILP which control the HVAC system using the forecast information. The performance of the two methods is verified by using real outdoor temperatures and real day-ahead prices in Detroit city, Michigan, United States. Numerical results clearly show that the performance of the MILP-based imitation learning is better than that of the forecast-based MILP method in terms of hourly power consumption, daily energy cost, and thermal comfort. Moreover, the difference between results of the MILP-based imitation learning method and optimal results is almost negligible. These optimal results are achieved only by using the MILP solver at the end of a day when we have full information on the weather and prices for the day.