Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach
This paper proposes a privacy-preserving energy management of a shared energy storage system (SESS) for multiple smart buildings using federated reinforcement learning (FRL). To preserve the privacy of energy scheduling of buildings connected to the SESS, we present a distributed deep reinforcement...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4898 |
| _version_ | 1797526090806198272 |
|---|---|
| author | Sangyoon Lee Le Xie Dae-Hyun Choi |
| author_facet | Sangyoon Lee Le Xie Dae-Hyun Choi |
| author_sort | Sangyoon Lee |
| collection | DOAJ |
| description | This paper proposes a privacy-preserving energy management of a shared energy storage system (SESS) for multiple smart buildings using federated reinforcement learning (FRL). To preserve the privacy of energy scheduling of buildings connected to the SESS, we present a distributed deep reinforcement learning (DRL) framework using the FRL method, which consists of a global server (GS) and local building energy management systems (LBEMSs). In the framework, the LBEMS DRL agents share only a randomly selected part of their trained neural network for energy consumption models with the GS without consumer’s energy consumption data. Using the shared models, the GS executes two processes: (i) construction and broadcast of a global model of energy consumption to the LBEMS agents for retraining their local models and (ii) training of the SESS DRL agent’s energy charging and discharging from and to the utility and buildings. Simulation studies are conducted using one SESS and three smart buildings with solar photovoltaic systems. The results demonstrate that the proposed approach can schedule the charging and discharging of the SESS and an optimal energy consumption of heating, ventilation, and air conditioning systems in smart buildings under heterogeneous building environments while preserving the privacy of buildings’ energy consumption. |
| first_indexed | 2024-03-10T09:24:15Z |
| format | Article |
| id | doaj.art-fba01af170a84bf78df2aa45da99100a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:24:15Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fba01af170a84bf78df2aa45da99100a2023-11-22T04:57:41ZengMDPI AGSensors1424-82202021-07-012114489810.3390/s21144898Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning ApproachSangyoon Lee0Le Xie1Dae-Hyun Choi2School of Electrical and Electronics Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 156-756, KoreaDepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USASchool of Electrical and Electronics Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 156-756, KoreaThis paper proposes a privacy-preserving energy management of a shared energy storage system (SESS) for multiple smart buildings using federated reinforcement learning (FRL). To preserve the privacy of energy scheduling of buildings connected to the SESS, we present a distributed deep reinforcement learning (DRL) framework using the FRL method, which consists of a global server (GS) and local building energy management systems (LBEMSs). In the framework, the LBEMS DRL agents share only a randomly selected part of their trained neural network for energy consumption models with the GS without consumer’s energy consumption data. Using the shared models, the GS executes two processes: (i) construction and broadcast of a global model of energy consumption to the LBEMS agents for retraining their local models and (ii) training of the SESS DRL agent’s energy charging and discharging from and to the utility and buildings. Simulation studies are conducted using one SESS and three smart buildings with solar photovoltaic systems. The results demonstrate that the proposed approach can schedule the charging and discharging of the SESS and an optimal energy consumption of heating, ventilation, and air conditioning systems in smart buildings under heterogeneous building environments while preserving the privacy of buildings’ energy consumption.https://www.mdpi.com/1424-8220/21/14/4898building energy management systemshared energy storage systemfederated reinforcement learningdeep reinforcement learningsmart buildings |
| spellingShingle | Sangyoon Lee Le Xie Dae-Hyun Choi Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach Sensors building energy management system shared energy storage system federated reinforcement learning deep reinforcement learning smart buildings |
| title | Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach |
| title_full | Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach |
| title_fullStr | Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach |
| title_full_unstemmed | Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach |
| title_short | Privacy-Preserving Energy Management of a Shared Energy Storage System for Smart Buildings: A Federated Deep Reinforcement Learning Approach |
| title_sort | privacy preserving energy management of a shared energy storage system for smart buildings a federated deep reinforcement learning approach |
| topic | building energy management system shared energy storage system federated reinforcement learning deep reinforcement learning smart buildings |
| url | https://www.mdpi.com/1424-8220/21/14/4898 |
| work_keys_str_mv | AT sangyoonlee privacypreservingenergymanagementofasharedenergystoragesystemforsmartbuildingsafederateddeepreinforcementlearningapproach AT lexie privacypreservingenergymanagementofasharedenergystoragesystemforsmartbuildingsafederateddeepreinforcementlearningapproach AT daehyunchoi privacypreservingenergymanagementofasharedenergystoragesystemforsmartbuildingsafederateddeepreinforcementlearningapproach |