In situ modeling methodologies in building operation: A review

Building and Environment, Journal Year: 2023, Volume and Issue: 230, P. 109982 - 109982

Published: Jan. 3, 2023

Language: Английский

---

PANDEMIC: Occupancy driven predictive ventilation control to minimize energy consumption and infection risk

Applied Energy, Journal Year: 2023, Volume and Issue: 334, P. 120676 - 120676

Published: Jan. 22, 2023

Language: Английский

---

Building electrification and carbon emissions: Integrated energy management considering the dynamics of the electricity mix and pricing

Advances in Applied Energy, Journal Year: 2023, Volume and Issue: 10, P. 100141 - 100141

Published: May 5, 2023

Electrification and distributed energy resources (DERs) are vital for reducing the building sector's carbon footprint. However, conventional reactive control is insufficient in addressing many current building-operation-related challenges, impeding decarbonization. To reduce emissions, it essential to consider dynamic grid electricity mix incorporate coordination between DERs systems control. This study develops a novel model predictive (MPC)-based integrated management framework buildings with multiple considering pricing. A linear, high-fidelity encompassing adaptive thermal comfort, thermodynamics, humidity, space conditioning, water heating, renewable energy, electric storage, vehicle, developed. An MPC controller developed based on this model. demonstrate applicability, applied single-family home an system through whole-year simulations three climate zones: warm, mixed, cold. In simulations, reduces whole-building costs emissions by 11.9% - 38.3% 7.2% 25.1%, respectively, compared Furthermore, can percent discomfort time from 25.7% 47.4% nearly 0%, The also shift 86.4% 100% of peak loads off-peak periods, while cannot achieve such performance. case results suggest that pursuing cost savings possible tandem emission reduction co-benefits (e.g., simultaneous 37.7% 21.9% reductions respectively) proposed framework.

Language: Английский

---

Augmenting energy time-series for data-efficient imputation of missing values

Applied Energy, Journal Year: 2023, Volume and Issue: 334, P. 120701 - 120701

Published: Jan. 23, 2023

Language: Английский

---

State-of-the-art review of occupant behavior modeling and implementation in building performance simulation

Renewable and Sustainable Energy Reviews, Journal Year: 2023, Volume and Issue: 185, P. 113558 - 113558

Published: Aug. 3, 2023

Occupant Behavior (OB) is one of the major drivers building energy consumption. However, OB usually oversimplified in Building Performance Simulation (BPS), resulting a significant performance gap between actual and simulated use. Thus, understanding true nature its accurate representation within BPS crucial. Despite existence many review articles that focus on several aspects OB, vast majority reviews are centered specific aspect modeling, scattering main findings among various studies. The literature still lacks comprehensive compiles analyzes recent studies each stage such as data collection analysis, integration models into BPS, validation, presentation suitable format. To this end, present summarizes, compiles, every presents an up-to-date evaluation multiple facets modeling BPS. It aims to development implementation steps model tools. A general outline characterizing recommended workflow for described. brief categorization methods used presented. Common quantitative approaches i.e., Stochastic, Statistical, Data mining, Agent-based methods, elucidated. applications, advantages, limitations discussed. available influence different patterns occupants' interaction with systems, cooling, lighting, shading, appliances, evaluated. In brief, study provides offering valuable insights both academic researchers industrial professionals aid them choosing adopting correct strategies accurately incorporate it

Language: Английский

---

Occupant-oriented demand response with multi-zone thermal building control

Applied Energy, Journal Year: 2023, Volume and Issue: 347, P. 121454 - 121454

Published: June 28, 2023

In future energy systems with high shares of renewable sources, the electricity demand buildings has to react fluctuating generation in view stability. As consume one-third global and almost half this accounts for Heating, Ventilation, Air Conditioning (HVAC) systems, HVAC are suitable shifting their consumption time. To end, intelligent control strategies necessary as conventional is not optimized actual occupants current situation grid. paper, we present novel multi-zone controller Price Storage Control (PSC) that only considers room-individual Occupants' Thermal Satisfaction (OTS), but also available storage, prices. The main feature PSC it does need a building model or forecasts demands derive actions multiple rooms building. For comparison, use an ideal, error-free Model Predictive (MPC), simplified variant without storage consideration (PC), hysteresis-based two-point control. We evaluate four controllers environment heating winter consider two different scenarios differ how much permitted temperatures vary. addition, compare impact parameters low thermal capacitance. results show strongly outperforms approach both parameters. capacitance, leads 22 % costs reduction while ideal MPC achieves cost reductions more than 39 %. Considering any forecast, opposed MPC, support suitability our developed strategy controlling systems.

Language: Английский

---

Optimizing Irrigation Efficiency using Deep Reinforcement Learning in the Field

ACM Transactions on Sensor Networks, Journal Year: 2024, Volume and Issue: 20(4), P. 1 - 34

Published: April 30, 2024

Agricultural irrigation is a significant contributor to freshwater consumption. However, the current systems used in field are not efficient. They rely mainly on soil moisture sensors and experience of growers but do account for future loss. Predicting loss challenging because it influenced by numerous factors, including texture, weather conditions, plant characteristics. This article proposes solution improve efficiency, which called DRLIC (deep reinforcement learning control). sophisticated system that uses deep (DRL) optimize its performance. The employs neural network, known as DRL control agent, learns an optimal policy considers both measurement We introduce reward function enables our agent learn from previous experiences. there may be instances output unsafe, such irrigating too much or little. To avoid damaging health plants, we implement safety mechanism predictor estimate performance each action. If predicted outcome deemed perform relatively conservative action instead. demonstrate real-world application approach, develop comprises sprinklers, sensing nodes, wireless network. evaluate deploying testbed consisting six almond trees. During 15-day in-field experiment, compare water consumption with widely scheme. Our results indicate outperforms traditional method achieving savings up 9.52%.

Language: Английский

---

Improving building energy consumption prediction using occupant-building interaction inputs and improved swarm intelligent algorithms

Journal of Building Engineering, Journal Year: 2023, Volume and Issue: 73, P. 106671 - 106671

Published: May 8, 2023

Language: Английский

---

Occupant behavior impact in buildings and the artificial intelligence-based techniques and data-driven approach solutions

Renewable and Sustainable Energy Reviews, Journal Year: 2023, Volume and Issue: 184, P. 113372 - 113372

Published: July 31, 2023

Language: Английский

---

DMFF: Deep multimodel feature fusion for building occupancy detection

Building and Environment, Journal Year: 2024, Volume and Issue: 253, P. 111355 - 111355

Published: Feb. 27, 2024

The 2022 Global Status Report for Buildings and Construction (Buildings-GSR) indicates that construction activities have returned to pre-pandemic levels in most major economies, alongside more building energy consumption. To achieve the Net Zero emissions target by 2050, particularly post-pandemic era, accurate occupancy information is important enhance efficiency improve comfort. While remarkable progress has been made existing studies, they struggle make full use of multi-sensor data high accuracy. Furthermore, there a expectation multimodel multi-temporary fusion Transformer. In this study, we present Transformer-based multimodal, multi-temporal feature method (DMFF) detection. transfer domain knowledge from artificial intelligence into area, DMFF includes pretrain-finetune pipeline leverages pre-trained visual sound models. Multiple Transformer encoders are employed extract features different modalities. Then, propose self-attention mechanism modality learn relationships among various sensors. Our demonstrates superior performance on real dataset, outperforming machine deep learning methods (e.g., Convolutional Neural Networks, Random Forest, Multilayer Perceptrons). Applied room setting, shows promising potential savings. code demo accessible at https://github.com/kailaisun/multimodel_occupancy.

Language: Английский

---