IoT and Machine Learning for Lifecycle Cost Optimization in Nigerian Commercial High-Rise Buildings

Commercial high-rise buildings in Nigeria’s major urban centres, Lagos and Abuja, face a compounding operational crisis: chronic grid instability, entrenched diesel generator dependency, and reactive maintenance paradigms that inflate lifecycle costs well beyond benchmarks in developed economies. Nigeria loses approximately US$985 million annually to power outages. Although Internet of Things (IoT) sensor networks and machine learning (ML) have demonstrated global potential to cut operational costs by 17.6% and maintenance spend by 13.2%, no empirically validated framework exists for their deployment in sub-Saharan Africa’s commercial real estate markets. This study administered a structured six-section questionnaire to 50 facility managers, property managers, building owners, and technology practitioners across Lagos and Abuja, using a convergent mixed-methods design analysed via descriptive statistics, Cronbach’s alpha, Spearman correlation, and Kruskal-Wallis tests. Findings show 58% of surveyed buildings rely on reactive or schedule-based maintenance, with only 10% practising predictive strategies. A critical willingness-capability gap emerged: practitioners express high investment willingness given demonstrated ROI (mean 4.20/5) yet report low ML familiarity (2.90/5) and inadequately skilled personnel (2.98/5). Contrary to global literature, economic and institutional barriers, high upfront cost (4.42/5), absent incentives (4.38/5), and weak policy support (4.38/5) outrank technical constraints as the dominant adoption impediments. Power outages generated the highest IoT-section score (4.34/5), confirming a Diesel-Grid Paradox as a central operational challenge, while lifecycle cost importance recorded the highest overall rating (4.64/5). Effective IoT-ML adoption in Nigerian commercial high-rises will require fiscal reform, regulatory strengthening, and demonstration-based evidence.