Smart City Gnosys
Smart city article details
| Title | Smart Building Transferable Energy Scheduling Employing Reward Shaping Deep Reinforcement Learning With Demand Side Energy Management |
|---|---|
| ID_Doc | 49209 |
| Authors | Kumaresan S.S.; Jeyaraj P.R. |
| Year | 2025 |
| Published | Journal of Building Engineering, 104 |
| DOI | http://dx.doi.org/10.1016/j.jobe.2025.112316 |
| Abstract | The random nature of consumer energy consumption in building, variable consumer behavior, and the intermittent operation of renewable energy sources in smart cities necessitate advanced computational strategies for effective energy management. To minimize energy cost, HVAC emissions, and grid stress, an optimized demand-side energy management approach with transferable scheduling is essential. This research proposes a novel smart building energy scheduling strategy using Transferable Reward-Shaping Deep Reinforcement Learning (RSDRL) to ensure energy efficiency while maintaining user comfort. First, an aggregator collects real-time data from IoT-connected buildings for training the proposed RSDRL. Then, a reward function iteratively minimizes scheduling deviations, ensuring efficient energy utilization. The final scheduling decisions balance energy savings and user comfort, managed by the aggregator. Simulation experiments and real-time proof-of-concept are tested to validate the practical applicability of RSDRL, demonstrating enhanced energy efficiency, reduced operational costs, and improved grid stability. For the testing treatment group in connected residential buildings, the proposed RSDRL model attains a satisfaction index of 0.93 while achieving 19.2 % energy savings. Similarly, in the control group, the proposed RSDRL model demonstrates a satisfaction index of 0.84 with 16.5 % energy savings. Moreover, for the load transferring test case, the proposed RSDRL model effectively reduces peak load by 6.45 %, particularly during high-demand periods when unexpected peak demand occurs within a one-day load profile. These results confirm the effectiveness of proposed RSDRL in optimizing energy consumption while maintaining a high level of user satisfaction, making it a reliable solution for IoT-enabled smart residential buildings energy management. © 2025 Elsevier Ltd |
| Author Keywords | Data-analysis; Deep reinforcement learning; Energy management; IoT connected building; Smart buildings |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
23349  | 0.891 | Bereketeab L.; Zekeria A.; Aloqaily M.; Guizani M.; Debbah M. | Energy Optimization In Sustainable Smart Environments With Machine Learning And Advanced Communications | IEEE Sensors Journal, 24, 5 (2024) |
| 50953 | 0.885 | Tripathy N.; Tripathy S.S. | Smart Green Cities Using Iot-Based Deep Reinforcement Learning Energy Management | Internet of Things and Big Data Analytics for a Green Environment (2024) |
| 7714 | 0.872 | Ludolfinger U.; Martens M. | An Autonomous Energy Management Concept For Sustainable Smart Cities | 2023 IEEE European Technology and Engineering Management Summit, E-TEMS 2023 - Conference Proceedings (2023) |
| 54040 | 0.872 | Lee D.-K.; Yoon S.-H.; Kwak J.-H.; Cho C.-H.; Lee D.-H. | Sustainable Smart City Building-Energy Management Based On Reinforcement Learning And Sales Of Ess Power | KSII Transactions on Internet and Information Systems, 17, 4 (2023) |
| 22295 | 0.868 | Manzoor A.; Akram W.; Judge M.A.; Khan N.; Khattak H.A. | Efficient Economic Energy Scheduling In Smart Cities Using Distributed Energy Resources | Science and Technology for Energy Transition (STET), 79 (2024) |
| 17807 | 0.867 | Khan M.; Faisal M.; Albogamy F.R.; Diyan M. | Deep Learning And Heuristic Optimization For Secure And Efficient Energy Management In Smart Communities | CMES - Computer Modeling in Engineering and Sciences, 143, 2 (2025) |
| 35929 | 0.865 | Mohamed B.; Hussein A.I. | Machine Learning Based Energy Management System For Smart Buildings | 2025 15th International Conference on Power, Energy, and Electrical Engineering, CPEEE 2025 (2025) |
| 40637 | 0.865 | Alatawi M.N. | Optimization Of Home Energy Management Systems In Smart Cities Using Bacterial Foraging Algorithm And Deep Reinforcement Learning For Enhanced Renewable Energy Integration | International Transactions on Electrical Energy Systems, 2024 (2024) |
| 33797 | 0.862 | Zhang, XD; Manogaran, G; Muthu, B | Iot Enabled Integrated System For Green Energy Into Smart Cities | SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS, 46 (2021) |
| 44356 | 0.862 | Faghri S.; Tahami H.; Amini R.; Katiraee H.; Godazi Langeroudi A.S.; Alinejad M.; Ghasempour Nejati M. | Real-Time Energy Flexibility Optimization Of Grid-Connected Smart Building Communities With Deep Reinforcement Learning | Sustainable Cities and Society, 119 (2025) |