<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://beta.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=undefined&type=result"></script>');
-->
</script>

COPY SCRIPT

For further information contact us at helpdesk@openaire.eu

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

descriptionPublicationkeyboard_double_arrow_right Article , Preprint , Journal 01 Jul 2018Embargo end date: 01 Jan 2016 Belgium Publisher:Institute of Electrical and Electronics Engineers (IEEE)Journal:IEEE Transactions on Smart Grid, volume 9, pages 3,259-3,269 (issn: 1949-3053, eissn: 1949-3061,

Authors: Bert J. Claessens; Peter Vrancx; Frederik Ruelens;

doi: 10.1109/tsg.2016.2629450 , 10.48550/arxiv.1604.08382

arXiv: 1604.08382 , http://arxiv.org/abs/1604.08382

handle: 20.500.14017/ef19a557-27d5-4885-b170-bf34924ca35d

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

- Summary
- Subjects
- Metrics

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.

Submitted to Transactions on Smart Grid

Country

Belgium

Related Organizations

Keywords

FOS: Computer and information sciences, Computer Science - Machine Learning, Systems and Control (eess.SY), Electrical Engineering and Systems Science - Systems and Control, Machine Learning (cs.LG), FOS: Electrical engineering, electronic engineering, information engineering

Impact byBIP!

	citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	114
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Top 1%
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Top 1%
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Top 1%