Smart Preventive Maintenance of Hybrid Networks and IoT Systems Using Software Sensing and Future State Prediction.

Area of Science:

• Internet of Things (IoT)
• Wireless Communication Technologies
• Predictive Maintenance

Background:

• Large-scale deployment of IoT and intelligent applications necessitates stable wireless connectivity across diverse standards (ZigBee, LoRA, Bluetooth, cellular).
• Maintaining consistent service levels in expanding IoT networks poses significant challenges for maintenance operators.

Purpose of the Study:

• To propose an integrated solution for managing preventive maintenance in complex IoT systems.
• To enhance the efficiency and response time of maintenance operations.
• To increase the resilience of complex systems through improved service recovery.

Main Methods:

• Employing software-defined sensing for hardware components, applications, and client satisfaction.
• Developing a specific algorithm for monitoring service levels.
• Utilizing network future state prediction for maintenance management.
• Investigating a case study in smart city applications.

Main Results:

• Demonstrated the expandability and flexibility of the proposed approach in a smart city context.
• Developed a novel algorithm for service level monitoring.
• Proposed an integrated instrument for preventive maintenance management based on predictive analytics.

Conclusions:

• The integrated solution effectively improves preventive maintenance efficiency and response times.
• The approach aids in rapid recovery of required service levels, enhancing system resilience.
• Software-defined sensing and predictive modeling offer a robust framework for managing complex IoT ecosystems.