Enhanced Dynamic Deep Q-Network for Federated Learning scheduling policies on IoT devices using explanation-driven trust

Recent advancements in Internet of Things (IoT) and edge computing have led to rapid growth in the number of IoT devices generating extensive volumes of data at the network edge. Efficiently scheduling tasks on these devices, particularly under strict latency constraints in federated learning (FL) environments, poses substantial challenges. In this paper, we propose a novel trust-energy-aware scheduling framework specifically designed for latency-constrained federated edge computing scenarios. Our innovative strategy integrates Dynamic Deep Q-Network (Dynamic-DQN) reinforcement learning with Local Interpretable Model-agnostic Explanations (LIME), enabling dynamic, real-time assessment of device trustworthiness with interpretability and transparency. This combined approach allows the framework to intelligently allocate tasks to IoT devices, explicitly optimizing for reduced latency, improved energy efficiency, and enhanced system reliability. Extensive experimental evaluations confirm that our proposed method substantially outperforms conventional reinforcement learning and heuristic scheduling algorithms, demonstrating significant reductions in latency, superior energy management, and improved scalability. These results underscore the robustness and practical effectiveness of our framework in addressing critical FL challenges. • Our dynamic-DQN policy integrates trust and energy for IoT task scheduling. • The solution evaluates the devices trustworthiness based on interpretable features. • The framework optimizes task allocation in federated edge computing environments. • The experimental results demonstrated improvement in task scheduling performance. • We contribute to resource efficiency and cost optimization in IoT edge computing.