This paper proposes RL-ACK, a reinforcement learning–based adaptive acknowledgment framework implemented at the edge router that reduces latency, control-plane overhead, reliability violations, and utilization pressure, and maintains Tier 1 deadline-compliant delivery above 95% under high network utilization.
Abstract
Smart kitchen IoT environments integrate robotic manipulators, sensing modules, and intelligent appliances within dense wireless deployments. Such environments generate heterogeneous traffic including latency-critical control signals, high-bandwidth multimedia streams, and best-effort telemetry. Conventional MQTT deployments rely on static QoS-based acknowledgment (ACK) behaviors that cannot adapt to dynamic congestion and packet loss. This paper proposes RL-ACK, a reinforcement learning–based adaptive acknowledgment framework implemented at the edge router. Per-message ACK selection is formulated as a Markov Decision Process (MDP), and the ACK policy is learned using a Deep Q-Network (DQN). The reward function balances latency, control-plane overhead, reliability violations, and utilization pressure. Extensive NS-3 simulations and a real Wi-Fi testbed demonstrate up to 36.7% latency reduction, approximately 22% signaling overhead reduction, and ACK-induced energy reduction for Tier 3 (BET) devices compared with static MQTT QoS 1, while maintaining Tier 1 deadline-compliant delivery above 95% under high network utilization ( $\rho = 0.9$ ).
Results confirm that reinforcement learning–based resource allocation provides a scalable and effective solution for IoT networks, particularly in environments characterized by large state spaces, dynamic network conditions, and stochastic traffic patterns.
L. Hoang, Van-Tam Hoang, Huu-Huy Ngo· International journal of Com...· 1 citation
A dynamic reward structuring framework within deep reinforcement learning to enable adaptive and balanced routing in IoT-WSNs and achieves significant performance gains, including approximately 30% improvement in energy efficiency, 25% reduction in latency, and 35% increase in network throughput compared with baseline methods.
Suresh Betam, S. Nagendram, Bathula Prasanna Kumar et al.· Scientific Reports· 0 citations
Unmanned Aerial Vehicles (UAVs) have emerged as a flexible, cost-effective solution for connecting Internet of Things (IoT) devices where traditional infrastructure falls short. However, managing their limited energy alongside the diverse demands of densely deployed devices makes resource allocation a genuinely hard problem. This paper presents a Deep Reinforcement Learning (DRL) framework that jointly optimizes user scheduling, IoT device transmit power, bandwidth, and UAV movement in a 6G-enabled UAV-relay uplink network, using a deterministic large-scale air-to-ground path-loss channel model. The UAV acts as an aerial decode-and-forward relay between IoT devices and a Base Station (BS), with a Deep Q-Network (DQN) making decisions based on queue backlogs, channel conditions, UAV position, and remaining battery. The reward function balances Energy Efficiency (EE), queue stability, fairness, and battery longevity. We benchmark the DQN against six baselines; Round Robin (RR), Random Allocation (RA), the Single-to-Noise Ratio (Max-SNR), Proportional Fair (PF), a Lyapunov heuristic, and a GreedyEE scheme; across a range of device counts, traffic loads, battery budgets, and flight altitudes. Simulations consistently show that the DQN outperforms all baselines, including a RA baseline with equal access to UAV mobility; in EE, throughput, delay, and fairness, confirming that the gain stems from the learned joint control policy rather than from UAV mobility being available.
Alissa Nauman, Sung Won Kim· Italian National Conference...· 0 citations
With the rapid expansion of smart grid infrastructure, robust and scalable communication is essential to support Advanced Metering Infrastructure (AMI). This paper presents a hybrid communication architecture that combines Power Line Communication (PLC) and Radio Frequency (RF) technologies to enable reliable, adaptive data transmission in smart metering networks. The proposed system employs a PLC-based mesh topology that utilizes existing electrical wiring to relay meter data to a Data Concentrator Unit (DCU), alongside an RF-based star topology that provides direct wireless links between smart meters and the DCU. A cloud-based web application is integrated for real-time visualization of power consumption, network health, and active communication paths. To dynamically select the optimal channel based on real-time latency, packet loss, and Signal-to-Noise Ratio (SNR), a Proximal Policy Optimization (PPO) reinforcement learning agent is implemented and benchmarked against tabular Q-Learning, Double Deep Q-Network (DDQN), and Deep Deterministic Policy Gradient (DDPG). The system is validated through hardware prototyping and subjected to multi-seed training, reward function sensitivity analysis, edge microcontroller profiling, and network-scale simulation to assess deployment viability. Evaluated over 5, 000 deterministic test cases against a reward-derived oracle, the PPO agent achieved an accuracy of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$93.78\%$$\end{document} and an F1 score of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$87.74\%$$\end{document}, attaining the highest single-run performance among all evaluated agents, with statistically significant advantages over Q-Learning and, for F1 score, over DDPG. Multi-seed training across ten initializations confirmed superior convergence stability with an accuracy standard deviation of only \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$8.74\%$$\end{document}, mitigating policy collapse. Edge AI profiling on an Arm Cortex-M4 platform demonstrated that INT8 quantization compresses the model by \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$2.36\times$$\end{document} to 64.7 KB while preserving \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$>99.9\%$$\end{document} of baseline accuracy at a 1.93 ms on-device latency. A reward sensitivity sweep across 16 coefficient perturbations verified policy robustness under varying weight configurations. Finally, a network-scale simulation across 500 to 5, 000 nodes confirmed scale-invariant performance with a Packet Delivery Ratio above \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$92\%$$\end{document} and consistent resilience under node outages, traffic overload, and channel degradation, providing simulation-based evidence of the scalability and resilience of AI-driven adaptive communication for large-scale smart grid deployments.
Noor El-Deen M. Mohamed, Mahmoud A. Shafea, Alaa M. Yousry et al.· Scientific Reports· 0 citations
An intelligent routing algorithm called Reinforcement Learning-based Congestion-Aware Routing (RLbCAR) is introduced for intelligent routing in IoT sensor networks and ensures reliable, congestion-adaptive, and computationally efficient routing in a resource-limited IoT sensor network.
M. Sunitha, M. Prashanth, Yenugula Swapna et al.· Discover Computing· 0 citations
A constrained, risk-sensitive multi-agent reinforcement learning framework is presented for joint task offloading and EH scheduling in battery-less 6G industrial networks, yielding a Pareto-non-dominated, statistically validated policy.
G. Marzoog, Ammar Kazm, Mustafa K. Ati· Sulaimani Journal for Engine...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
