AI-IoT Integration in Smart Warehousing: A Systematic Review of Forecasting Technologies and Strategic Applications

Abstract

This review synthesizes recent advances in combining Artificial Intelligence (AI) and the Internet of Things (IoT) to optimize warehouse operations. Analyzing 18 peer-reviewed studies published between 2021 and 2025, the review identifies four key themes: AI-enhanced inventory forecasting, IoT-driven inventory management, automation and robotics, and digital twin-based strategic planning. Findings show that Machine Learning algorithms significantly improve forecasting accuracy when trained on high-frequency IoT data, while IoT infrastructures, like RFID and sensors, enhance real-time inventory visibility. Robotics enables adaptable, high-throughput operations, and digital twins support predictive modeling and scenario planning. Despite these benefits, challenges remain: many implementations lack real-world validation, and issues such as inconsistent performance metrics, system interoperability, and underrepresented small-scale warehouses limit progress. Additionally, human-machine interaction design is often overlooked. To address these challenges, a four-layer integration model is proposed, covering data acquisition, processing, automation control, and strategic planning, emphasizing the need for a unified sensor infrastructure, learning algorithms, and planning mechanisms. Future research should focus on operational deployment, standardization, and inclusive design to expand applicability across various warehouse sizes. This synthesis provides valuable insights and a conceptual framework for advancing AI-IoT integration in smart warehouses.