Optimizing Smart Building Safety Management: A Descriptive Analytics Approach Using Microsoft Power BI and IoT Sensor Data

Abstract

As the smart building paradigm establishes a global standard, ensuring occupant well-being has transitioned from a secondary utility to a fundamental safety requirement. Despite the widespread acquisition of environmental data through the Internet of Things (IoT), contemporary systems often suffer from "data overload" and fragmented silos, which obscure the longitudinal value of historical trends and result in reactive safety management. This research addresses these systemic gaps by developing a descriptive analytics dashboard using Microsoft Power BI to synthesize multi-source IoT data specifically CO2 levels, humidity, temperature, light intensity, and motion into actionable intelligence. Adopting a project-based methodology grounded in the Software Development Life Cycle (SDLC), the study operationalizes safety thresholds derived from ASHRAE and World Health Organization (WHO) standards through an "action-driven" traffic-light categorization system. Empirical results demonstrate that monitored environmental conditions remained within "Safe" thresholds for 99.7% of the observation periods. While CO2 (mean: 453.86 ppm) and temperature (mean: 23.52°C) remained stable within recommended ranges, light intensity was consistently observed below indoor standards. Furthermore, correlational analysis identified a direct relationship between occupant density and CO2 fluctuations, emphasizing the necessity of integrated sensing for strategic ventilation planning. By bridging the gap between raw sensing and strategic visualization, this research provides a robust framework for transitioning smart building management from reactive maintenance to a data-driven proactive model.