Successful application of predictive information in deep reinforcement learning control: A case study based on an office building HVAC system

Energy, Год журнала: 2024, Номер 291, С. 130344 - 130344

Опубликована: Янв. 15, 2024

Язык: Английский

---

Predicting Daily Heating Energy Consumption in Residential Buildings through Integration of Random Forest Model and Meta-Heuristic Algorithms

Energy, Год журнала: 2024, Номер 301, С. 131726 - 131726

Опубликована: Май 20, 2024

Язык: Английский

---

Optimising building heat load prediction using advanced control strategies and Artificial Intelligence for HVAC system

Thermal Science and Engineering Progress, Год журнала: 2024, Номер 49, С. 102484 - 102484

Опубликована: Фев. 28, 2024

Язык: Английский

---

Sensor deployment configurations for building energy consumption prediction

Energy and Buildings, Год журнала: 2024, Номер 308, С. 113888 - 113888

Опубликована: Янв. 7, 2024

Язык: Английский

---

Time-series machine learning for predictive optimisation of a highly efficient evaporative cooling system

Building Services Engineering Research and Technology, Год журнала: 2025, Номер unknown

Опубликована: Янв. 16, 2025

As data centres become integral to modern infrastructure, their energy consumption, particularly in cooling systems, presents a critical challenge for sustainability. This paper addresses this issue by applying time-series machine learning models forecast the performance of highly efficient 100 kW evaporative system applied real-world centre. Using dataset spanning 4 months, we developed and optimised two predictive based on XGBoost Random Forest, estimate capacity Coefficient Performance (COP). Initial results showed suboptimal performance, with model achieving Mean Absolute Error (MAE) 1.34 6.50 COP, alongside negative R-squared, indicating poor fit. However, after hyperparameter tuning, Forest significantly improved predictions, an MAE 0.39 R-squared 0.85 capacity, 2.21 0.54 COP. These findings underscore potential these optimise efficiency, offering valuable insights reducing consumption operational costs centre operations. research paves way more sustainable designs operations across diverse climatic conditions. Practical application The study enable building environment professionals systems. By accurately forecasting (COP) under varying environmental conditions, allow proactive adjustments strategies, ensuring operation minimising waste. provides practical tool enhancing sustainability centres, directly supporting industry efforts meet stringent efficiency targets reduce carbon footprint infrastructure.

Язык: Английский

---

Predicting Energy Consumption of Residential Buildings Using Metaheuristic-optimized Artificial Neural Network Technique in Early Design Stage

Building and Environment, Год журнала: 2025, Номер unknown, С. 112749 - 112749

Опубликована: Фев. 1, 2025

Язык: Английский

---

Forecasting building energy demand and on-site power generation for residential buildings using long and short-term memory method with transfer learning

Applied Energy, Год журнала: 2024, Номер 368, С. 123500 - 123500

Опубликована: Май 23, 2024

Язык: Английский

---

Predicting the PCM-incorporated building's performance using optimized linear kernel and tree-based machine learning methods

Journal of Energy Storage, Год журнала: 2024, Номер 94, С. 112495 - 112495

Опубликована: Июнь 16, 2024

Язык: Английский

---

Enhancing Building Energy Efficiency: An Integrated Approach to Predicting Heating and Cooling Loads using Machine Learning and Optimization Algorithms

Journal of Building Engineering, Год журнала: 2024, Номер unknown, С. 110759 - 110759

Опубликована: Сен. 1, 2024

Язык: Английский

---

Machine learning based dynamic super twisting sliding mode controller for increase speed and accuracy of MPPT using real-time data under PSCs

Renewable Energy, Год журнала: 2023, Номер 219, С. 119470 - 119470

Опубликована: Окт. 14, 2023

Язык: Английский

---