본문 바로가기
  • Home

AIoT-Based Digital Modeling Algorithms for Building Energy Optimization

  • Journal of Internet of Things and Convergence
  • Abbr : JKIOTS
  • 2026, 12(4), 12
  • Publisher : The Korea Internet of Things Society
  • Research Area : Engineering > Computer Science > Internet Information Processing
  • Received : July 21, 2026
  • Accepted : August 20, 2026
  • Published : August 31, 2026

Sangmin Park 1

1한국성서대학교

Accredited

ABSTRACT

The building sector accounts for a significant portion of global energy consumption and CO2 emissions, necessitating improvements in energy management practices in existing buildings to achieve carbon neutrality. In particular, many existing buildings rely on analog-based equipment and limited control methods, hindering efficient energy management and optimization. This study, focusing on an aging analog building in Kuala Lumpur, Malaysia, presents a strategy to improve energy management efficiency through digital transformation. We developed an energy-saving system that incorporates Smart IoT sensors and a PV system and applies an AI-based energy control algorithm. To verify the effectiveness of the proposed method, three energy-saving scenarios were constructed: (1) time-based scheduling control, (2) AI-based intelligent control, and (3) PV-linked control. The energy savings rates and operational effectiveness of each scenario were compared and analyzed. The analysis results indicate that the proposed energy management and control approach could achieve approximately 3.96% energy savings compared to conventional operating methods, suggesting that data-driven control has the potential to contribute substantially to improving energy efficiency and reducing carbon emissions in existing buildings. This study demonstrates that the digital transformation of aging buildings and AI-based energy management can serve as effective approaches to sustainable building operation and the achievement of carbon neutrality.

Journal Copyright Policy

No CCL information provided

Citation status

* References for papers published after 2025 are currently being built.