AI-Driven Self-Optimizing Networks for Integrated LPWAN and 5G in Next-Generation IoT Systems
Disciplines
Computer and Systems Architecture | Digital Communications and Networking | Systems and Communications
Abstract (300 words maximum)
The widespread adoption of smart connected devices over the past decade has significantly driven the growth of the Internet of Things (IoT). While 5G networks provide high-speed, low-latency connectivity, their high power consumption and limited range pose challenges for IoT applications requiring long-distance, energy-efficient data transmission. This study explores a hybrid networking approach that integrates 5G with low-power wide area network (LPWAN) technologies to enhance IoT performance. We analyze the challenges of merging these architectures, emphasizing network efficiency, scalability, and reliability. Specifically, we compare the performance of standalone LPWAN with integrated LPWAN-5G networks using existing solutions and essential network simulations, examine the complexity of network operations within the hybrid framework, and evaluate AI-driven optimization techniques for data packet transmission. Ultimately, our findings aim to demonstrate how AI-based self-optimizing network designs can improve data transmission efficiency, minimize failures, and support the next generation of IoT applications in diverse environments. Our study results will provide insights into how a self-optimizing network design can significantly benefit from AI algorithms to meet the demands of next-generation IoT applications.
Academic department under which the project should be listed
CCSE - Computer Science
Primary Investigator (PI) Name
Ahyoung Lee
AI-Driven Self-Optimizing Networks for Integrated LPWAN and 5G in Next-Generation IoT Systems
The widespread adoption of smart connected devices over the past decade has significantly driven the growth of the Internet of Things (IoT). While 5G networks provide high-speed, low-latency connectivity, their high power consumption and limited range pose challenges for IoT applications requiring long-distance, energy-efficient data transmission. This study explores a hybrid networking approach that integrates 5G with low-power wide area network (LPWAN) technologies to enhance IoT performance. We analyze the challenges of merging these architectures, emphasizing network efficiency, scalability, and reliability. Specifically, we compare the performance of standalone LPWAN with integrated LPWAN-5G networks using existing solutions and essential network simulations, examine the complexity of network operations within the hybrid framework, and evaluate AI-driven optimization techniques for data packet transmission. Ultimately, our findings aim to demonstrate how AI-based self-optimizing network designs can improve data transmission efficiency, minimize failures, and support the next generation of IoT applications in diverse environments. Our study results will provide insights into how a self-optimizing network design can significantly benefit from AI algorithms to meet the demands of next-generation IoT applications.