Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control

TL;DR

This paper introduces a convolutional neural network-based method to extract hidden state-time features for improved control of residential demand flexibility, effectively reducing electricity costs under partial observability.

Contribution

It presents a novel CNN-based approach for estimating Q-functions in reinforcement learning to handle partial observability in residential load control.

Findings

Successfully captures hidden features in simulation

Reduces electricity costs in cluster control

Demonstrates effectiveness of CNN in RL for demand management

Abstract

Direct load control of a heterogeneous cluster of residential demand flexibility sources is a high-dimensional control problem with partial observability. This work proposes a novel approach that uses a convolutional neural network to extract hidden state-time features to mitigate the curse of partial observability. More specific, a convolutional neural network is used as a function approximator to estimate the state-action value function or Q-function in the supervised learning step of fitted Q-iteration. The approach is evaluated in a qualitative simulation, comprising a cluster of thermostatically controlled loads that only share their air temperature, whilst their envelope temperature remains hidden. The simulation results show that the presented approach is able to capture the underlying hidden features and successfully reduce the electricity cost the cluster.