Enhancing Air Conditioning System Efficiency Through Load Prediction and Deep Reinforcement Learning: A Case Study of Ground Source Heat Pumps

Energies, Journal Year: 2025, Volume and Issue: 18(1), P. 199 - 199

Published: Jan. 5, 2025

This study proposes a control method that integrates deep reinforcement learning with load forecasting, to enhance the energy efficiency of ground source heat pump systems. Eight machine models are first developed predict future cooling loads, and optimal one is then incorporated into learning. Through interaction environment, strategy identified using Q-network optimize supply water temperature from source, allowing for savings. The obtained results show XGBoost model significantly outperforms other in terms prediction accuracy, reaching coefficient determination 0.982, mean absolute percentage error 6.621%, variation root square 10.612%. Moreover, savings achieved through forecasting-based greater than those traditional constant methods by 10%. Additionally, without shortening interval, improved 0.38% compared do not use predictive information. approach requires only continuous between agent which makes it an effective alternative scenarios where sensor equipment data present. It provides smart adaptive optimization solution heating, ventilation, air conditioning systems buildings.

Language: Английский

---

Proactive Operational Strategy of Thermal Energy Storage Tank in an Industrial multi-chiller System Based on Chilled Water Flow Difference Between Supply and Demand Sides

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 134752 - 134752

Published: Jan. 1, 2025

Language: Английский

---

Prospects and Challenges of Reinforcement Learning- Based HVAC Control

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 111080 - 111080

Published: Oct. 1, 2024

Language: Английский

---

Total Cost of Ownership Prediction in Chilled Water Plants: Contributing Factors and Role of Artificial Intelligence

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 1618 - 1618

Published: Feb. 5, 2025

This study investigates key parameters and applications of artificial intelligence (AI) in predicting the total cost ownership (TCO) for chilled water plants (CWPs). Forecasting TCO CWPs is challenging due to diverse dynamic factors that influence it, necessitating understanding their complex correlations causations. While AI non-AI approaches have improved parameter prediction accuracy different engineering applications, comprehensive literature reviews on chiller methodologies influencing are limited. systematic review addresses three objectives: (1) identify estimating CWPs, (2) examine existing techniques employed forecasting benefits energy savings, (3) evaluate how enhances robustness. Following preferred reporting items meta-analyses (PRISMA) guidelines, this analyzed studies from 2017 2024 sourced Web Science Scopus databases. identifies several TCO, including cooling load, consumption, capacity, Coefficient Performance (COP). The shows AI-driven models, such as deep learning machine algorithms, robustness predictions, it further demonstrates scenarios where outperforms conventional methods. Notably, current predicted be capable reducing life cycle costs by up 18%, based modeling estimates.

Language: Английский

---

Advancing organic photovoltaic cells for a sustainable future: The role of artificial intelligence (AI) and deep learning (DL) in enhancing performance and innovation

Solar Energy, Journal Year: 2025, Volume and Issue: 291, P. 113378 - 113378

Published: March 6, 2025

Language: Английский

---

Load flexibility exploration of fan-coil air-conditioning system via coupling of demand response and chilled water storage strategies

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115726 - 115726

Published: April 1, 2025

Language: Английский

---

Joint optimization for temperature and humidity independent control system based on multi-agent reinforcement learning with cooperative mechanisms

Applied Energy, Journal Year: 2024, Volume and Issue: 375, P. 123968 - 123968

Published: Aug. 12, 2024

Language: Английский

---

Recent Methods for Evaluating Crop Water Stress Using AI Techniques: A Review

Sensors, Journal Year: 2024, Volume and Issue: 24(19), P. 6313 - 6313

Published: Sept. 29, 2024

This study systematically reviews the integration of artificial intelligence (AI) and remote sensing technologies to address issue crop water stress caused by rising global temperatures climate change; in particular, it evaluates effectiveness various non-destructive platforms (RGB, thermal imaging, hyperspectral imaging) AI techniques (machine learning, deep ensemble methods, GAN, XAI) monitoring predicting stress. The analysis focuses on variability precipitation due change explores how these can be strategically combined under data-limited conditions enhance agricultural productivity. Furthermore, this is expected contribute improving sustainable practices mitigating negative impacts yield quality.

Language: Английский

---

Massive energy reduction and storage capacity relative to PCM physical size by integrating deep RL clustering and multi-stage strategies into smart buildings to grid reliability

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 109, P. 115058 - 115058

Published: Dec. 30, 2024

Language: Английский

---

A bi-level real-time optimal control strategy for thermal coupled multi-zone dedicated outside air system-assisted HVAC systems

Energy, Journal Year: 2024, Volume and Issue: 306, P. 132343 - 132343

Published: July 9, 2024

Language: Английский

---