Data centers devote a substantial share of their energy budgets to cooling, making thermal management a prime target for cost reduction and sustainability improvements. This study extends prior work in the Engineering Economics of RFID by examining how AI-enabled embedded RFID systems can autonomously monitor and optimize data-center cooling performance. Partnering with RFCode, we integrate real-time RFID sensing of temperature and humidity with artificial-intelligence algorithms that dynamically adjust cooling parameters, reducing overcooling and improving efficiency.
An accompanying educational framework introduces a systems-thinking approach to teaching engineering economy within cyber-physical systems. Students apply tornado diagrams, cost-benefit models, and sensitivity analyses to evaluate economic trade-offs among sensor investment, AI implementation, and operational energy savings. Preliminary analyses indicate potential cooling-energy reductions of 10–15 % and payback periods within 12–18 months, reinforcing how economic decision tools can quantify technology value.
By merging RFID-enabled monitoring with AI-driven analytics, this work offers both a technological and pedagogical contribution—illustrating how emerging Industry 4.0 systems can be evaluated, optimized, and taught through an engineering-economy perspective.
http://orcid.org/0000-0003-0559-4699
The University of Texas at Arlington
[biography]
http://orcid.org/https://0000-0002-0931-1935
Prairie View A&M University
[biography]
Are you a researcher? Would you like to cite this paper? Visit the ASEE document repository at peer.asee.org for more tools and easy citations.