Authors: Malika Usmonova
Abstract: This review article evaluates the technical convergence of wireless internet of things technology and SAP enterprise systems, specifically focusing on the role of machine learning in modernizing infrastructure management. As we move into , the transition from fixed, wired monitoring to massive machine-type communication powered by 5G RedCap, NB-IoT, and nascent 6G protocols has created a paradigm shift in how physical assets are tracked and maintained. The research analyzes the architectural role of the SAP Business Technology Platform as a digital twin hub, bridging the gap between high-frequency, unstructured MQTT sensor streams and the structured digital core of S/4HANA. A primary focus is placed on the application of unsupervised and supervised machine learning models, such as autoencoders for structural anomaly detection and graph neural networks for managing interconnected utility grids. By examining use cases in smart cities, predictive asset management, and environmental monitoring, the article illustrates how machine learning translates raw wireless telemetry into automated SAP work orders and real-time inventory adjustments. The review further addresses critical implementation challenges, including signal optimization for zero-energy IoT nodes and AI-driven cybersecurity for wireless networks. Ultimately, the article demonstrates that the integration of wireless IoT and machine learning transforms infrastructure from a passive operational expense into an active, self-reporting strategic asset, essential for achieving long-term industrial resilience and sustainability goals.
DOI: https://doi.org/10.5281/zenodo.19437564
