Optimal Scheduling of Residential Heating, Ventilation and Air Conditioning Based on Deep Reinforcement Learning
Residential heating, ventilation and air conditioning (HVAC) provides important demand response resources for the new power system with high proportion of renewable energy. Residential HAVC scheduling strategies that adapt to real-time electricity price signals formulated by demand response program...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | Journal of Modern Power Systems and Clean Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9965191/ |
| _version_ | 1797679515966636032 |
|---|---|
| author | Mingchao Xia Fangjian Chen Qifang Chen Siwei Liu Yuguang Song Te Wang |
| author_facet | Mingchao Xia Fangjian Chen Qifang Chen Siwei Liu Yuguang Song Te Wang |
| author_sort | Mingchao Xia |
| collection | DOAJ |
| description | Residential heating, ventilation and air conditioning (HVAC) provides important demand response resources for the new power system with high proportion of renewable energy. Residential HAVC scheduling strategies that adapt to real-time electricity price signals formulated by demand response program and ambient temperature can significantly reduce electricity costs while ensuring occupants' comfort. However, since the pricing process and weather conditions are affected by many factors, conventional model-based method is difficult to meet the scheduling requirements in complex environments. To solve this problem, we propose an adaptive optimal scheduling strategy for residential HVAC based on deep reinforcement learning (DRL) method. The scheduling problem can be regarded as a Markov decision process (MDP). The proposed method can adaptively learn the state transition probability to make economical decision under the tolerance violations. Specifically, the residential thermal parameters obtained by the least-squares parameter estimation (LSPE) can provide a basis for the state transition probability of MDP. Daily simulations are verified under the electricity prices and temperature data sets, and numerous experimental results demonstrate the effectiveness of the proposed method. |
| first_indexed | 2024-03-11T23:15:53Z |
| format | Article |
| id | doaj.art-bc455a46944c4fdc9d2920540a810b56 |
| institution | Directory Open Access Journal |
| issn | 2196-5420 |
| language | English |
| last_indexed | 2024-03-11T23:15:53Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | Journal of Modern Power Systems and Clean Energy |
| spelling | doaj.art-bc455a46944c4fdc9d2920540a810b562023-09-20T23:00:33ZengIEEEJournal of Modern Power Systems and Clean Energy2196-54202023-01-011151596160510.35833/MPCE.2022.0002499965191Optimal Scheduling of Residential Heating, Ventilation and Air Conditioning Based on Deep Reinforcement LearningMingchao Xia0Fangjian Chen1Qifang Chen2Siwei Liu3Yuguang Song4Te Wang5School of Electrical Engineering, Beijing Jiaotong University,Beijing,ChinaSchool of Electrical Engineering, Beijing Jiaotong University,Beijing,ChinaSchool of Electrical Engineering, Beijing Jiaotong University,Beijing,ChinaState Grid State Power Economic Research Institute,Beijing,ChinaSchool of Electrical Engineering, Beijing Jiaotong University,Beijing,ChinaSchool of Electrical Engineering, Beijing Jiaotong University,Beijing,ChinaResidential heating, ventilation and air conditioning (HVAC) provides important demand response resources for the new power system with high proportion of renewable energy. Residential HAVC scheduling strategies that adapt to real-time electricity price signals formulated by demand response program and ambient temperature can significantly reduce electricity costs while ensuring occupants' comfort. However, since the pricing process and weather conditions are affected by many factors, conventional model-based method is difficult to meet the scheduling requirements in complex environments. To solve this problem, we propose an adaptive optimal scheduling strategy for residential HVAC based on deep reinforcement learning (DRL) method. The scheduling problem can be regarded as a Markov decision process (MDP). The proposed method can adaptively learn the state transition probability to make economical decision under the tolerance violations. Specifically, the residential thermal parameters obtained by the least-squares parameter estimation (LSPE) can provide a basis for the state transition probability of MDP. Daily simulations are verified under the electricity prices and temperature data sets, and numerous experimental results demonstrate the effectiveness of the proposed method.https://ieeexplore.ieee.org/document/9965191/Residential heatingventilation and air conditioning (HVAC)schedulingdeep reinforcement learningleast-squares parameter estimation (LSPE) |
| spellingShingle | Mingchao Xia Fangjian Chen Qifang Chen Siwei Liu Yuguang Song Te Wang Optimal Scheduling of Residential Heating, Ventilation and Air Conditioning Based on Deep Reinforcement Learning Journal of Modern Power Systems and Clean Energy Residential heating ventilation and air conditioning (HVAC) scheduling deep reinforcement learning least-squares parameter estimation (LSPE) |
| title | Optimal Scheduling of Residential Heating, Ventilation and Air Conditioning Based on Deep Reinforcement Learning |
| title_full | Optimal Scheduling of Residential Heating, Ventilation and Air Conditioning Based on Deep Reinforcement Learning |
| title_fullStr | Optimal Scheduling of Residential Heating, Ventilation and Air Conditioning Based on Deep Reinforcement Learning |
| title_full_unstemmed | Optimal Scheduling of Residential Heating, Ventilation and Air Conditioning Based on Deep Reinforcement Learning |
| title_short | Optimal Scheduling of Residential Heating, Ventilation and Air Conditioning Based on Deep Reinforcement Learning |
| title_sort | optimal scheduling of residential heating ventilation and air conditioning based on deep reinforcement learning |
| topic | Residential heating ventilation and air conditioning (HVAC) scheduling deep reinforcement learning least-squares parameter estimation (LSPE) |
| url | https://ieeexplore.ieee.org/document/9965191/ |
| work_keys_str_mv | AT mingchaoxia optimalschedulingofresidentialheatingventilationandairconditioningbasedondeepreinforcementlearning AT fangjianchen optimalschedulingofresidentialheatingventilationandairconditioningbasedondeepreinforcementlearning AT qifangchen optimalschedulingofresidentialheatingventilationandairconditioningbasedondeepreinforcementlearning AT siweiliu optimalschedulingofresidentialheatingventilationandairconditioningbasedondeepreinforcementlearning AT yuguangsong optimalschedulingofresidentialheatingventilationandairconditioningbasedondeepreinforcementlearning AT tewang optimalschedulingofresidentialheatingventilationandairconditioningbasedondeepreinforcementlearning |