Direct Load Control of Thermostatically Controlled Loads Based on Sparse Observations Using Deep Reinforcement Learning

TL;DR

This paper explores using deep reinforcement learning, specifically LSTM networks, to optimize demand response for thermostatically controlled loads with sparse observational data, outperforming other neural network architectures.

Contribution

It demonstrates that LSTM networks effectively extract features from sparse time-series data for near-optimal control policies in residential heating systems.

Findings

LSTM outperforms CNN in this scenario

Deep learning can handle sparse observations effectively

Recurrent neural networks are suitable for demand response tasks

Abstract

This paper considers a demand response agent that must find a near-optimal sequence of decisions based on sparse observations of its environment. Extracting a relevant set of features from these observations is a challenging task and may require substantial domain knowledge. One way to tackle this problem is to store sequences of past observations and actions in the state vector, making it high dimensional, and apply techniques from deep learning. This paper investigates the capabilities of different deep learning techniques, such as convolutional neural networks and recurrent neural networks, to extract relevant features for finding near-optimal policies for a residential heating system and electric water heater that are hindered by sparse observations. Our simulation results indicate that in this specific scenario, feeding sequences of time-series to an LSTM network, which is a specific type of recurrent neural network, achieved a higher performance than stacking these time-series in the input of a convolutional neural network or deep neural network.