Recent Developments in AI and ML for IoT: A Systematic Literature Review on LoRaWAN Energy Efficiency and Performance...

Area of Science:

• Computer Science
• Electrical Engineering
• Telecommunications

Background:

• The Internet of Things (IoT) requires efficient, low-power, long-range communication technologies.
• Low Power Wide Area Networks (LPWANs), particularly Long Range Wide Area Networks (LoRaWAN), are crucial for scalable IoT deployments.
• Optimizing LoRaWAN performance is essential for enabling advanced IoT applications in smart cities and industrial settings.

Purpose of the Study:

• To systematically review the integration of Machine Learning (ML) and Artificial Intelligence (AI) in optimizing LoRaWAN operations.
• To identify and analyze state-of-the-art ML/AI techniques used for enhancing LoRaWAN network performance.
• To highlight improvements in energy consumption, resource management, and network stability through ML/AI integration.

Main Methods:

• A systematic literature review (SLR) following the PRISMA model.
• Identification and synthesis of 25 relevant primary studies on ML/AI in LoRaWAN.
• Analysis of research questions focusing on parameter optimization using ML, Deep Learning (DL), and Reinforcement Learning (RL).

Main Results:

• ML and AI techniques effectively optimize various LoRaWAN parameters, leading to enhanced operational efficiency.
• Significant improvements were observed in energy consumption, resource allocation, and overall network stability.
• Advanced ML, DL, and RL methods are key enablers for achieving superior performance in LoRaWAN networks.

Conclusions:

• The integration of ML and AI is a transformative approach for optimizing LoRaWAN performance in IoT.
• These intelligent techniques are vital for addressing the challenges of resource management and energy efficiency in large-scale IoT deployments.
• Future research should continue exploring novel ML/AI applications to further advance LoRaWAN capabilities.