Generalized Reinforcement Learning for Building Control using Behavioral Cloning

TL;DR

This paper introduces a generalized reinforcement learning approach called Behavioral Cloning that efficiently replicates model predictive control policies for building management, enabling low-cost, adaptable, and privacy-preserving control solutions across multiple buildings.

Contribution

The paper presents a novel, generalized RL-based control method using Behavioral Cloning with innovative techniques like CIPG, MPC-Guided data generation, and RT-RNNs, reducing training effort and enhancing adaptability.

Findings

Controller can generalize across multiple buildings and schedules.

Requires minimal building-specific tuning and low-cost hardware.

Achieves effective control with reduced computational requirements.

Abstract

Advanced building control methods such as model predictive control (MPC) offer significant potential benefits to both consumers and grid operators, but the high computational requirements have acted as barriers to more widespread adoption. Local control computation requires installation of expensive computational hardware, while cloud computing introduces data security and privacy concerns. In this paper, we drastically reduce the local computational requirements of advanced building control through a reinforcement learning (RL)-based approach called Behavioral Cloning, which represents the MPC policy as a neural network that can be locally implemented and quickly computed on a low-cost programmable logic controller. While previous RL and approximate MPC methods must be specifically trained for each building, our key improvement is that our controller can generalize to many buildings, electricity rates, and thermostat setpoint schedules without additional, effort-intensive retraining. To provide this versatility, we have adapted the traditional Behavioral Cloning approach through (1) a constraint-informed parameter grouping (CIPG) method that provides a more efficient representation of the training data; (2) an MPC-Guided training data generation method using the DAgger algorithm that improves stability and constraint satisfaction; and (3) a new deep learning model-structure called reverse-time recurrent neural networks (RT-RNN) that allows future information to flow backward in time to more effectively interpret the temporal information in disturbance predictions. The result is an easy-to-deploy, generalized behavioral clone of MPC that can be implemented on a programmable logic controller and requires little building-specific controller tuning, reducing the effort and costs associated with implementing smart residential heat pump control.