Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control
This work addresses partial observability in residential load control, but it is incremental as it applies an existing method to a specific domain.
The paper tackled the high-dimensional control problem of direct load control for residential demand flexibility by using a convolutional neural network to extract hidden state-time features, reducing electricity costs in a simulation with thermostatically controlled loads.
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.