Researchers Build GA-DQL Hybrid to Improve Fog Task Mapping for Growing IoT Loads
Updated
Updated · geneonline · Jun 5
Researchers Build GA-DQL Hybrid to Improve Fog Task Mapping for Growing IoT Loads
1 articles · Updated · geneonline · Jun 5
Summary
Tripathy, Sahoo, Alghamdi and colleagues developed a hybrid Genetic Algorithm-Deep Q-Learning model to improve task mapping efficiency in fog computing environments.
The framework pairs GA's broad search of large solution spaces with DQL's reinforcement-learning adaptation to changing network conditions, targeting better scheduling as IoT data volumes rise.
Fog nodes—the layer between connected devices and centralized cloud servers—are meant to use the approach to cut latency and improve energy consumption while allocating resources more efficiently.
The study positions the dual-method system as a way to maintain fog-computing performance as expanding IoT networks place heavier demands on data processing and distribution.