Energy-efficient optimization method for air conditioning terminal systems in IDC based on genetic algorithm

Xiaofei Huang, Junwei Yan, Xuan Zhou, Zhixian Yang and Xiaofeng Huang

Energy, 2025, vol. 333, issue C

Abstract: The increasing energy consumption of air conditioning terminal systems (ACTS) in Internet data centers (IDCs) has become a critical global issue. This study presents an energy optimization approach for ACTS by integrating artificial intelligence control (AIC) into the energy management and control system (EMCS). The method combines an energy model, heat transfer model, and genetic algorithm (GA) to enhance the efficiency of computer room air handlers (CRAHs), quantified by E-ACTE. An airflow correction model for CRAHs is developed using operational data, and the AIC is validated through experimental testing. The results demonstrate high accuracy, with cooling capacity deviation of 0.03 % and return air temperature deviation below 5.55 %. After optimization, E-ACTE in the test room increased by 6.76 times. Further analysis shows that optimal E-ACTE of 93.43 is achieved at 160 kW cooling load demand using a “multi-unit low fan speed ratio” strategy. Applied to 18 CRs across five floors, the method led to a 6.02-time improvement in E-ACTE and a 20.16 % reduction in Cooling Load Factor (CLF). These results highlight the potential of advanced control strategies for enhancing energy efficiency and sustainability in IDC cooling systems. Future work should explore additional variables and predictive algorithms to improve long-term performance.

Keywords: Internet data center; Air conditioning system; Energy efficiency; Optimization; Genetic algorithm (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225031445
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:333:y:2025:i:c:s0360544225031445

DOI: 10.1016/j.energy.2025.137502

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().