Energy modelling and control of building heating and cooling systems with data-driven and hybrid models—A review

Renewable and Sustainable Energy Reviews, Journal Year: 2023, Volume and Issue: 183, P. 113496 - 113496

Published: July 5, 2023

Implementing an efficient control strategy for heating, ventilation, and air conditioning (HVAC) systems can lead to improvements in both energy efficiency thermal performance buildings. As HVAC buildings are complicated dynamic systems, the effectiveness of data-driven model-based methods has been widely investigated by researchers. However, main challenges that impede practical application real their reliance on precision control-oriented models dependence data-based quantity quality input–output data. The objectives this study are: (1) To present overview prevalent modelling strategies used as or virtual environments methods, addressing requirements models; (2) state-of-the-art MPC RL techniques; (3) data models. findings emphasise need unified guidelines validate verify proposed ensuring implementation Moreover, inclusion occupancy forecasts presents due intricate nature accurately predicting human behaviour, patterns, effects dynamics. Balancing comfort with a supervisory controller remains difficult task, but combining physics-based help overcome challenges. Further research is needed compare approaches, measuring impact behaviour significant obstacle.

Language: Английский

---

Scalable energy management approach of residential hybrid energy system using multi-agent deep reinforcement learning

Applied Energy, Journal Year: 2024, Volume and Issue: 367, P. 123414 - 123414

Published: May 14, 2024

Language: Английский

---

A learning-based model predictive control method for unlocking the potential of building energy flexibility

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115299 - 115299

Published: Jan. 1, 2025

Language: Английский

---

Analyzing the overrated performance of model-based predictive control and energy saving strategies in building energy management: A Review

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 111909 - 111909

Published: Jan. 1, 2025

Language: Английский

---

A scalable approach for real-world implementation of deep reinforcement learning controllers in buildings based on online transfer learning: the HiLo case study

Energy and Buildings, Journal Year: 2025, Volume and Issue: 329, P. 115254 - 115254

Published: Jan. 5, 2025

Language: Английский

---

Adaptive Reinforcement Learning for Energy Management – A progressive approach to boost climate resilience and energy flexibility

Advances in Applied Energy, Journal Year: 2025, Volume and Issue: unknown, P. 100213 - 100213

Published: Jan. 1, 2025

Language: Английский

---

Real building implementation of a deep reinforcement learning controller to enhance energy efficiency and indoor temperature control

Applied Energy, Journal Year: 2024, Volume and Issue: 368, P. 123447 - 123447

Published: May 21, 2024

Deep Reinforcement Learning (DRL) has emerged as a promising approach to address the trade-off between energy efficiency and indoor comfort in buildings, potentially outperforming conventional Rule-Based Controllers (RBC). This paper explores real-world application of Soft-Actor Critic (SAC) DRL controller building's Thermally Activated Building System (TABS), focusing on optimising consumption maintaining comfortable temperatures. Our involves pre-training agent using simplified Resistance-Capacitance (RC) model calibrated with real building data. The study first benchmarks against three RBCs, two Proportional-Integral (PI) controllers Model Predictive Controller (MPC) simulated environment. In simulation study, reduces by 15% 50% decreases temperature violations 25% compared reducing also PI respectively 23% 5%. Moreover, achieves comparable performance terms control but consuming 29% more than an ideal MPC. When implemented during two-month cooling season, performances were those best-performing RBC, enhancing 68% without increasing consumption. research demonstrates effective strategy for training deploying systems, highlighting potential practical management applications.

Language: Английский

---

Model predictive control for demand flexibility of a residential building with multiple distributed energy resources

Energy and Buildings, Journal Year: 2024, Volume and Issue: 305, P. 113884 - 113884

Published: Jan. 5, 2024

Language: Английский

---

Field demonstration of predictive heating control for an all-electric house in a cold climate

Applied Energy, Journal Year: 2024, Volume and Issue: 360, P. 122820 - 122820

Published: Feb. 21, 2024

Language: Английский

---

An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems

Building Simulation, Journal Year: 2024, Volume and Issue: 17(5), P. 739 - 770

Published: Feb. 20, 2024

Abstract Deep Reinforcement Learning (DRL)-based control shows enhanced performance in the management of integrated energy systems when compared with Rule-Based Controllers (RBCs), but it still lacks scalability and generalisation due to necessity using tailored models for training process. Transfer (TL) is a potential solution address this limitation. However, existing TL applications building have been mostly tested among buildings similar features, not addressing need scale up advanced real-world scenarios diverse systems. This paper assesses an online heterogeneous strategy, comparing RBC offline DRL controllers simulation setup EnergyPlus Python. The study tests transfer both transductive inductive settings policy designed manage chiller coupled Thermal Energy Storage (TES). pre-trained on source transferred various target characterised by system including photovoltaic battery storage systems, different envelope occupancy schedule boundary conditions (e.g., weather price signal). approach incorporates model slicing, imitation learning fine-tuning handle state spaces reward functions between buildings. Results show that proposed methodology leads reduction 10% electricity cost 40% mean value daily average temperature violation rate controllers. Moreover, maximises self-sufficiency self-consumption 9% 11% respect RBC. Conversely, achieves worse either or settings. (DRL) agents should be trained at least 15 episodes reach same level as TL. Therefore, effective, completely model-free can directly implemented real satisfying performance.

Language: Английский

---