Applications of Deep Reinforcement Learning for Home Energy Management Systems: A Review
In the context of the increasing integration of renewable energy sources (RES) and smart devices in domestic applications, the implementation of Home Energy Management Systems (HEMS) is becoming a pivotal factor in optimizing energy usage and reducing costs. This review examines the role of reinforc...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/24/6420 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850059456804552704 |
|---|---|
| author | Dominik Latoń Jakub Grela Andrzej Ożadowicz |
| author_facet | Dominik Latoń Jakub Grela Andrzej Ożadowicz |
| author_sort | Dominik Latoń |
| collection | DOAJ |
| description | In the context of the increasing integration of renewable energy sources (RES) and smart devices in domestic applications, the implementation of Home Energy Management Systems (HEMS) is becoming a pivotal factor in optimizing energy usage and reducing costs. This review examines the role of reinforcement learning (RL) in the advancement of HEMS, presenting it as a powerful tool for the adaptive management of complex, real-time energy demands. This review is notable for its comprehensive examination of the applications of RL-based methods and tools in HEMS, which encompasses demand response, load scheduling, and renewable energy integration. Furthermore, the integration of RL within distributed automation and Internet of Things (IoT) frameworks is emphasized in the review as a means of facilitating autonomous, data-driven control. Despite the considerable potential of this approach, the authors identify a number of challenges that require further investigation, including the need for robust data security and scalable solutions. It is recommended that future research place greater emphasis on real applications and case studies, with the objective of bridging the gap between theoretical models and practical implementations. The objective is to achieve resilient and secure energy management in residential and prosumer buildings, particularly within local microgrids. |
| format | Article |
| id | doaj-art-3d7010e958164ea6b8274bae3ea7f656 |
| institution | DOAJ |
| issn | 1996-1073 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-3d7010e958164ea6b8274bae3ea7f6562025-08-20T02:50:53ZengMDPI AGEnergies1996-10732024-12-011724642010.3390/en17246420Applications of Deep Reinforcement Learning for Home Energy Management Systems: A ReviewDominik Latoń0Jakub Grela1Andrzej Ożadowicz2Department of Power Electronics and Energy Control Systems, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, 30-059 Krakow, PolandDepartment of Power Electronics and Energy Control Systems, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, 30-059 Krakow, PolandDepartment of Power Electronics and Energy Control Systems, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, 30-059 Krakow, PolandIn the context of the increasing integration of renewable energy sources (RES) and smart devices in domestic applications, the implementation of Home Energy Management Systems (HEMS) is becoming a pivotal factor in optimizing energy usage and reducing costs. This review examines the role of reinforcement learning (RL) in the advancement of HEMS, presenting it as a powerful tool for the adaptive management of complex, real-time energy demands. This review is notable for its comprehensive examination of the applications of RL-based methods and tools in HEMS, which encompasses demand response, load scheduling, and renewable energy integration. Furthermore, the integration of RL within distributed automation and Internet of Things (IoT) frameworks is emphasized in the review as a means of facilitating autonomous, data-driven control. Despite the considerable potential of this approach, the authors identify a number of challenges that require further investigation, including the need for robust data security and scalable solutions. It is recommended that future research place greater emphasis on real applications and case studies, with the objective of bridging the gap between theoretical models and practical implementations. The objective is to achieve resilient and secure energy management in residential and prosumer buildings, particularly within local microgrids.https://www.mdpi.com/1996-1073/17/24/6420reinforcement learninghome energy managementsmart homeInternet of Thingsprosumermicrogrid |
| spellingShingle | Dominik Latoń Jakub Grela Andrzej Ożadowicz Applications of Deep Reinforcement Learning for Home Energy Management Systems: A Review Energies reinforcement learning home energy management smart home Internet of Things prosumer microgrid |
| title | Applications of Deep Reinforcement Learning for Home Energy Management Systems: A Review |
| title_full | Applications of Deep Reinforcement Learning for Home Energy Management Systems: A Review |
| title_fullStr | Applications of Deep Reinforcement Learning for Home Energy Management Systems: A Review |
| title_full_unstemmed | Applications of Deep Reinforcement Learning for Home Energy Management Systems: A Review |
| title_short | Applications of Deep Reinforcement Learning for Home Energy Management Systems: A Review |
| title_sort | applications of deep reinforcement learning for home energy management systems a review |
| topic | reinforcement learning home energy management smart home Internet of Things prosumer microgrid |
| url | https://www.mdpi.com/1996-1073/17/24/6420 |
| work_keys_str_mv | AT dominiklaton applicationsofdeepreinforcementlearningforhomeenergymanagementsystemsareview AT jakubgrela applicationsofdeepreinforcementlearningforhomeenergymanagementsystemsareview AT andrzejozadowicz applicationsofdeepreinforcementlearningforhomeenergymanagementsystemsareview |