Aug 2026· Computers and artificial intelligence· 0 citations· 41 references
TL;DR
It is concluded that future Internet of Things systems should adopt communication-computation-learning co-design, lightweight and adaptive models, privacy-aware distributed intelligence, and cross-layer orchestration to achieve scalable, trustworthy, and energy-efficient edge intelligence.
Abstract
This structured review investigates how machine learning-enabled edge intelligence can improve the performance, efficiency, and resilience of Internet of Things communication systems under constraints of latency, bandwidth, energy, privacy, and device heterogeneity. A structured literature review was conducted using peer-reviewed studies from major academic databases, with the selected work classified according to learning paradigms, edge deployment strategies, communication functions, application domains, evaluation metrics, and practical limitations. The synthesis shows that supervised learning, deep learning, reinforcement learning, federated learning, lightweight model compression, and Tiny Machine Learning can support adaptive scheduling, intelligent routing, computation offloading, bandwidth allocation, anomaly detection, and privacy-preserving collaboration across device-edge-cloud architectures. The reviewed evidence indicates that these approaches can reduce end-to-end delay, communication traffic, and energy consumption while improving resource utilization, local autonomy, and responsiveness in smart cities, industrial systems, healthcare, agriculture, and intelligent transportation. However, performance gains remain strongly dependent on communication conditions, model size, data distribution, hardware capability, synchronization overhead, and security requirements. The review further identifies unresolved challenges involving non-independent and identically distributed data, unstable wireless links, model adaptability, privacy leakage, adversarial threats, and the absence of standardized multi-objective benchmarks. It concludes that future Internet of Things systems should adopt communication-computation-learning co-design, lightweight and adaptive models, privacy-aware distributed intelligence, and cross-layer orchestration to achieve scalable, trustworthy, and energy-efficient edge intelligence.
This study investigates energy-efficient distributed machine learning techniques, including federated learning, model compression, adaptive resource management, dynamic task offloading, and communication-efficient optimization, and proposes a distributed learning framework that integrates local model training, adaptive communication scheduling, gradient compression, and workload balancing to minimize energy consumption while maintaining learning accuracy.
Venkatesh Iyer· International Journal of App...· 0 citations
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
This paper proposes a communication-efficient adaptive federated learning algorithm for heterogeneous defect classification tasks that achieves competitive classification accuracy while reducing single-round training time by up to 70%.
Shuo He, He-Yang Wei, Congxian Bi et al.· Electronics· 0 citations
The rapid advancement of Industry 4.0 has accelerated the development of intelligent and autonomous smart factories powered by Industrial Internet of Things (IIoT) devices, cyber-physical systems (CPS), and advanced manufacturing technologies. Although cloud computing offers significant computational and storage capabilities, it suffers from latency, bandwidth limitations, privacy concerns, and delayed decision-making in time-critical industrial environments. This paper proposes an Integrated Intelligent Edge Computing Architecture for Real-Time Smart Factory Operations, combining edge computing, Artificial Intelligence (AI), digital twins, and predictive analytics to enable real-time local data processing with seamless cloud integration. The framework employs machine learning for anomaly detection, deep learning for automated quality inspection, reinforcement learning for adaptive production scheduling, and predictive models for equipment health monitoring. Secure communication protocols enhance data protection and system reliability. Experimental results demonstrate improved latency, prediction accuracy, manufacturing efficiency, energy utilization, fault detection, and operational resilience compared with conventional cloud-based approaches. The proposed architecture provides a scalable and sustainable solution for next-generation autonomous smart factories, improving equipment reliability, reducing operational costs, and increasing manufacturing productivity.
Seshagiri N· International Journal of Mod...· 0 citations
With the development of 5G and the widespread adoption of home IoT devices and wearable smart devices, home edge IoT devices generate a large amount of data. This data contains sensitive personal privacy and cannot be uploaded to public servers for training. Distributed machine learning technology, specifically federated training, is designed to protect data privacy, ensuring that data does not leave the local environment while multiple parties collaboratively train and share the model. However, home IoT devices differ significantly from industrial-grade IoT devices, exhibiting substantial heterogeneity, primarily in computing power, memory, power consumption, network connectivity, and in user data distribution, which makes it impossible to deploy federated training directly. This paper systematically reviews lightweight federated learning techniques for home edge IoT, analyzing two technical approaches: "device-aware adaptive lightweight training" and "data distribution-aware weighted aggregation." This paper proposes a co-optimization research framework, incorporating pruning rate, quantization bit width, and aggregation weights into a unified optimization space. The goal is to strike a balance among global model accuracy, training energy consumption, and convergence speed under device resource constraints, thereby providing a theoretical reference for future research.
Yiwei Zeng· Applied and Computational En...· 0 citations
Recent progress in intelligent, adaptive, and security-aware Software-Defined Wireless Sensor Networks (SDWSNs) is driven by the integration of Machine Learning (ML) with Software-Defined Networking (SDN) and Wireless Sensor Networks (WSNs). This systematic survey analyzes 46 peer-reviewed articles published between 2024 and 2025, providing a problem-oriented synthesis of ML-SDWSN research. Emphasizing security, routing, and performance optimization, with a particular focus on deployment architectures, the survey identifies three major trends: increased adoption of ensemble and Reinforcement Learning (RL) methods for security and adaptive control; broader implementation of edge-based ML to minimize inference latency; and greater emphasis on privacy-preserving techniques, especially Federated Learning (FL). The survey presents a structured taxonomy encompassing seven thematic areas: Distributed Denial-of-Service (DDoS) mitigation, Intrusion Detection Systems (IDSs), routing optimization, Quality of Service (QoS) management, privacy preservation, data integrity, and network-efficiency optimization. Findings are synthesized from over 120 experimental configurations reported in the literature. Due to substantial differences among the reviewed studies in terms of datasets, network topologies, hardware platforms, measurement definitions, and validation methodologies, the reported values are presented as descriptive cross-study aggregates rather than direct comparative benchmarks or formal effect-size estimates. Within these constraints, the survey identifies recurring trade-offs among accuracy, latency, scalability, and privacy. It provides evidence-based design considerations for researchers and practitioners. The survey also highlights eight critical research gaps, including limited multi-dataset validation, a lack of real-world deployments, insufficient scalability analysis, and the need for rigorous evaluation of RL-based SDWSN control.
Ahmed Nader al-Dulaimy, Hannes Frey· Electronics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
