Multi-zone HVAC Control with Model-Based Deep Reinforcement Learning

TL;DR

This paper introduces MB2C, a model-based deep reinforcement learning system for multi-zone HVAC control that improves energy efficiency and sample efficiency using ensemble neural networks and a novel control algorithm.

Contribution

The paper develops MB2C, combining ensemble neural networks with Model Predictive Path Integral control for improved HVAC management in multi-zone buildings.

Findings

Achieves 8.23% more energy savings than existing MBRL methods.

Reduces training data requirements by over tenfold.

Maintains thermal comfort while improving efficiency.

Abstract

In this paper, we conduct a set of experiments to analyze the limitations of current MBRL-based HVAC control methods, in terms of model uncertainty and controller effectiveness. Using the lessons learned, we develop MB2C, a novel MBRL-based HVAC control system that can achieve high control performance with excellent sample efficiency. MB2C learns the building dynamics by employing an ensemble of environment-conditioned neural networks. It then applies a new control method, Model Predictive Path Integral (MPPI), for HVAC control. It produces candidate action sequences by using an importance sampling weighted algorithm that scales better to high state and action dimensions of multi-zone buildings. We evaluate MB2C using EnergyPlus simulations in a five-zone office building. The results show that MB2C can achieve 8.23% more energy savings compared to the state-of-the-art MBRL solution while maintaining similar thermal comfort. MB2C can reduce the training data set by an order of magnitude (10.52x) while achieving comparable performance to MFRL approaches.