Energy-aware latency minimization in multi-source spatiotemporal data fusion for IoT networks

Area of Science:

• Smart City Technologies
• Data Fusion and Integration
• Wireless Communication Networks

Background:

• Smart city infrastructures generate vast spatiotemporal data from diverse sources like sensors and cameras.
• Efficient data fusion is critical for ultra-low latency applications (2-5 ms) in time-sensitive operations.
• Data source heterogeneity and resource constraints challenge latency and energy efficiency goals.

Purpose of the Study:

• To propose a joint optimization framework for multi-source spatiotemporal data fusion.
• To dynamically allocate bandwidth and CPU resources to minimize latency and energy consumption.
• To address challenges posed by data heterogeneity and resource limitations in smart city environments.

Main Methods:

• Developed a joint optimization framework for dynamic resource allocation (bandwidth and CPU).
• Incorporated realistic wireless channel conditions and strict resource constraints.
• Evaluated performance against traditional equal and delay-tolerant strategies.

Main Results:

• The proposed framework consistently achieved low latency and energy-efficient performance across all data sources.
• Demonstrated significant reductions in both latency and energy consumption compared to traditional methods.
• Validated the framework's robustness and scalability for smart city applications.

Conclusions:

• The joint optimization framework effectively balances latency and energy consumption for spatiotemporal data fusion.
• The approach offers a superior solution for smart city applications requiring efficient, time-sensitive data processing.
• The framework's efficiency, robustness, and scalability make it highly suitable for evolving smart city infrastructures.