Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction

In recent years, home energy management systems (HEMS), which enable the automatic control of electrical equipment and home appliances, have been attracting attention as a method for saving electricity at home. HEMS achieve energy saving by visualizing energy consumption at home and controlling ener...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Naoki Kodama, Taku Harada, Kazuteru Miyazaki
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Deep reinforcement learning deep Q-network Q-learning energy management energy cost Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/22b2c6543c9a4030818574b00c440a55
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:22b2c6543c9a4030818574b00c440a55
record_format	dspace
spelling	oai:doaj.org-article:22b2c6543c9a4030818574b00c440a552021-11-20T00:02:23ZHome Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction2169-353610.1109/ACCESS.2021.3126365https://doaj.org/article/22b2c6543c9a4030818574b00c440a552021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9606721/https://doaj.org/toc/2169-3536In recent years, home energy management systems (HEMS), which enable the automatic control of electrical equipment and home appliances, have been attracting attention as a method for saving electricity at home. HEMS achieve energy saving by visualizing energy consumption at home and controlling energy consuming equipment such as air conditioners. The optimum control law is difficult to attain, owing to uncertainties related to power demand and power supply from the electrical equipment. Deep reinforcement learning has been used to address energy optimization problems for home environments. However, in HEMS, several components such as heating, ventilation, and air conditioning (HVAC) systems, storage batteries, and electric water heaters are simultaneously controlled, and therefore, the action space becomes extremely large. Therefore, it may not be feasible to fully learn the rare experience using traditional deep reinforcement learning methods due to the large size of the state-action space and slow propagation of delayed rewards. In this study, we propose an energy management algorithm that uses the Dual Targeting Algorithm to strongly learn the experience of acquiring high returns using the quick propagation of delayed rewards via multistep returns. The proposed energy management algorithm is applied to a HEMS learning experiment to control a storage battery and an HVAC system, and its performance is compared to that of a Deep Deterministic Policy Gradient-based energy management system. As a result, it is confirmed that the proposed method can reduce the number of hours deviating from the comfort temperature range by about 17% compared to the existing method.Naoki KodamaTaku HaradaKazuteru MiyazakiIEEEarticleDeep reinforcement learningdeep Q-networkQ-learningenergy managementenergy costElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 153108-153115 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep reinforcement learning deep Q-network Q-learning energy management energy cost Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Deep reinforcement learning deep Q-network Q-learning energy management energy cost Electrical engineering. Electronics. Nuclear engineering TK1-9971 Naoki Kodama Taku Harada Kazuteru Miyazaki Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction
description	In recent years, home energy management systems (HEMS), which enable the automatic control of electrical equipment and home appliances, have been attracting attention as a method for saving electricity at home. HEMS achieve energy saving by visualizing energy consumption at home and controlling energy consuming equipment such as air conditioners. The optimum control law is difficult to attain, owing to uncertainties related to power demand and power supply from the electrical equipment. Deep reinforcement learning has been used to address energy optimization problems for home environments. However, in HEMS, several components such as heating, ventilation, and air conditioning (HVAC) systems, storage batteries, and electric water heaters are simultaneously controlled, and therefore, the action space becomes extremely large. Therefore, it may not be feasible to fully learn the rare experience using traditional deep reinforcement learning methods due to the large size of the state-action space and slow propagation of delayed rewards. In this study, we propose an energy management algorithm that uses the Dual Targeting Algorithm to strongly learn the experience of acquiring high returns using the quick propagation of delayed rewards via multistep returns. The proposed energy management algorithm is applied to a HEMS learning experiment to control a storage battery and an HVAC system, and its performance is compared to that of a Deep Deterministic Policy Gradient-based energy management system. As a result, it is confirmed that the proposed method can reduce the number of hours deviating from the comfort temperature range by about 17% compared to the existing method.
format	article
author	Naoki Kodama Taku Harada Kazuteru Miyazaki
author_facet	Naoki Kodama Taku Harada Kazuteru Miyazaki
author_sort	Naoki Kodama
title	Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction
title_short	Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction
title_full	Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction
title_fullStr	Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction
title_full_unstemmed	Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction
title_sort	home energy management algorithm based on deep reinforcement learning using multistep prediction
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/22b2c6543c9a4030818574b00c440a55
work_keys_str_mv	AT naokikodama homeenergymanagementalgorithmbasedondeepreinforcementlearningusingmultistepprediction AT takuharada homeenergymanagementalgorithmbasedondeepreinforcementlearningusingmultistepprediction AT kazuterumiyazaki homeenergymanagementalgorithmbasedondeepreinforcementlearningusingmultistepprediction
_version_	1718419822737358848

Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction

Ejemplares similares