Energy, Journal Year: 2024, Volume and Issue: unknown, P. 133858 - 133858
Published: Nov. 1, 2024
Language: Английский
Energy, Journal Year: 2024, Volume and Issue: unknown, P. 133858 - 133858
Published: Nov. 1, 2024
Language: Английский
Energy and Buildings, Journal Year: 2024, Volume and Issue: 319, P. 114514 - 114514
Published: July 6, 2024
Language: Английский
Citations
9Buildings, Journal Year: 2025, Volume and Issue: 15(3), P. 462 - 462
Published: Feb. 2, 2025
As the penetration rate of renewable energy in power grid increases, imbalance between supply and demand has become one key issues. Buildings their heating, ventilation, air conditioning (HVAC) systems are considered excellent flexible response (DR) resources that can reduce peak loads to alleviate operational pressures on grid. Centralized chiller plants regarded as with large capacity rapid adjustability. The direct load control respond within minutes, making them highly suitable for participation emergency DR. However, existing studies generally based simulations lack experimental research actual large-scale buildings demonstrate effectiveness this method provide related lessons learned. This study conducted field experiments a centralized plant an industrial building Guangdong, China. results indicate strategy shutting down is effective DR measure. It complete reduction process 15 min, rapidly decreasing system by 380~459 kW, maximum duration up 50 without significantly affecting thermal comfort indoor occupants. Additionally, impact logic also discussed.
Language: Английский
Citations
0Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115727 - 115727
Published: April 1, 2025
Language: Английский
Citations
0Building Simulation, Journal Year: 2025, Volume and Issue: unknown
Published: April 29, 2025
Language: Английский
Citations
0Energy Nexus, Journal Year: 2025, Volume and Issue: unknown, P. 100431 - 100431
Published: May 1, 2025
Language: Английский
Citations
0Case Studies in Thermal Engineering, Journal Year: 2025, Volume and Issue: 67, P. 105835 - 105835
Published: Feb. 3, 2025
Language: Английский
Citations
0Buildings, Journal Year: 2024, Volume and Issue: 14(9), P. 2645 - 2645
Published: Aug. 26, 2024
The rapid expansion of renewable energy in buildings has been expedited by technological advancements and government policies. However, including highly permeable intermittent renewables storage presents significant challenges for traditional home management systems (HEMSs). Deep reinforcement learning (DRL) is regarded as the most efficient approach tackling these problems because its robust nonlinear fitting capacity capability to operate without a predefined model. This paper DRL control method intended lower expenses elevate usage optimizing actions battery heat pump HEMS. We propose four algorithms thoroughly assess their performance. In pursuit this objective, we also devise new reward function multi-objective optimization an interactive environment grounded expert experience. results demonstrate that TD3 algorithm excels cost savings PV self-consumption. Compared baseline model, model achieved 13.79% reduction operating costs 5.07% increase Additionally, explored impact feed-in tariff (FiT) on TD3’s performance, revealing resilience even when FiT decreases. comparison provides insights into selection specific applications, promoting development DRL-driven solutions.
Language: Английский
Citations
2Energy and Buildings, Journal Year: 2024, Volume and Issue: 323, P. 114771 - 114771
Published: Sept. 10, 2024
Language: Английский
Citations
2Renewable Energy, Journal Year: 2024, Volume and Issue: 237, P. 121619 - 121619
Published: Oct. 13, 2024
Language: Английский
Citations
2Energy and Buildings, Journal Year: 2024, Volume and Issue: unknown, P. 114896 - 114896
Published: Oct. 1, 2024
Language: Английский
Citations
2