A Novel Method for Data Aggregation in Internet of Things (IoT) Networks Using Colored Petri Net (CPN) Modeling and Reinforcement Learning (RL)

This paper proposes a novel method for data aggregation in Internet of Things (IoT) networks, utilizing Colored Petri Net (CPN) modeling and Reinforcement Learning (RL) to outperform traditional data aggregation techniques in terms of energy consumption, end-to-end delay, and network lifetime. Experimental results indicate that the proposed method achieves a 20-25% reduction in energy consumption, 15-20% lower end-to-end delay, and a 20-25% increase in network lifetime. These findings provide scalability and improved quality of service for resource-constrained IoT applications. Potential challenges include computational overhead, convergence time, and security concerns, necessitating further research. Future research directions involve integrating the method with edge computing, real-world deployment testing, developing hybrid algorithms, exploring adaptive reward functions, and assessing the environmental impact.