UDTR Global Rights of Nature Radar

Dynamic Latency Optimization for Edge-Based Machine Learning Models in 6G-Enabled Industrial Internet of Things (IIoT)

Identification

Public canonical key

radar:r-789ef1aee048c4b4576c8e7cb5d8d780

Authors

Seema Patil · Harshavardhana Doddamani · Savitha A C · Julianne Rivers

Reported year

2026

Reported language

en

Source type

JournalArticle

First detected

2026-11-13T15:29:09.944670+00:00

Last metadata observation

2026-11-13T15:29:09.944670+00:00

Last HTTP verification

Not checked

Institutions reported by the source

Associate Professor, B.M.S College of Engineering, Bangalore, India · Professor, Department of Computer Science & Engg. Nagarjuna College of Engineering & Technology, Bangalore, India · Assistant Professor, Department of Electronics & Communication Engineering, JSS Academy of Technical Education (JSSATE), Bangalore, India · Senior Fellow, Center for Secure Systems and Network Privacy, Carnegie Mellon University

Documentary abstract — original language

Abstract The integration of 6G technology into the Industrial Internet of Things (IIoT) promises to redefine manufacturing through "Hyper-Reliable Low-Latency Communication" (HRLLC). However, the deployment of complex Machine Learning (ML) models at the edge remains constrained by the heterogeneous nature of industrial data and the limited computational resources of edge nodes. This article proposes a novel framework for Dynamic Latency Optimization (DLO) that leverages Deep Reinforcement Learning (DRL) for intelligent task offloading and resource allocation. By utilizing 6G's Terahertz (THz) spectrum and AI-native Network Slicing, the proposed framework dynamically adapts to fluctuating network conditions to maintain sub-millisecond latency. Our simulation results demonstrate a 42% reduction in end-to-end delay and a 30% improvement in energy efficiency compared to traditional 5G-MEC architectures. Furthermore, we explore the integration of Reconfigurable Intelligent Surfaces (RIS), Semantic Communication, and Zero-Trust Edge Security to further optimize the data-intelligence pipeline for Industry 5.0 applications, focusing on the critical synergy between human operators and autonomous systems within a resilient, sustainable, and cognitively aware industrial fabric. Keywords: 6G Networks, Industrial IoT (IIoT), Edge Intelligence, Deep Reinforcement Learning, Latency Optimization 1. Introduction: From Automation to Human-Centric Intelligence The transition from Industry 4.0 to Industry 5.0 marks a profound shift toward human-centric, resilient, and sustainable manufacturing systems. While Industry 4.0 was characterized by the digitalization of physical assets and the rise of cyber-physical systems, Industry 5.0 emphasizes the "Tactile Internet" and "Human-Robot Co-evolution." In this new paradigm, the focus shifts from pure efficiency to the seamless collaboration between humans and increasingly autonomous machines. The "Tactile Internet" concept is particularly revolutionary, as it requires a "haptic control loop"—the ability to transmit touch and feel sensations over the network with such low latency that the human brain perceives no delay. This necessitates an end-to-end latency below 1ms, encompassing both the transmission and the computational processing of sensory feedback. This evolution necessitates a communication infrastructure capable of supporting advanced applications such as ultra-responsive autonomous mobile robots (AMRs), synchronized multi-robot assembly lines, and high-fidelity haptic feedback for remote maintenance in hazardous environments. For example, a specialist surgeon operating a robotic arm in a factory cleanup of toxic waste requires instantaneous haptic feedback to "feel" the resistance of the materials being handled. If the feedback loop exceeds 10ms, the mismatch between visual and tactile input can lead to "operator sickness" or mechanical errors that jeopardize safety. Furthermore, we must consider proprioceptive alignment—the sense of self-movement and body position. In 6G-enabled IIoT, the network must act as an extension of the human nervous system, where the delay jitter is so minimal that the robotic actuator feels like a literal extension of the operator's limb. This requires not just low latency, but Isochronous Communication, where packets arrive at precisely regular intervals to maintain the temporal rhythm of human motor-sensory systems. This synchronization is critical for Tele-Operation in nanomanufacturing, where even a micro-stutter in the feedback loop can cause the robotic probe to crush a microscopic wafer. The biological threshold for "instantaneous" feedback in human motor control is roughly 1-10ms for tactile sensations and less than 1ms for the suppression of "visual-vestibular conflict." In 6G, we move into the regime of "Sub-Perceptual Jitter," where the network variance is lower than the biological noise of the human nervous system. This enables "Neuromorphic Manufacturing," where robotic limbs are controlled via high-speed neural interfaces, requiring the network to behave as a synthetic synaptic bridge. While 5G introduced Ultra-Reliable Low-Latency Communication (URLLC), providing latencies in the range of 1–5ms, 6G aims to push these boundaries into a new regime. The 6G vision targets "microsecond-level" latencies (below 0.1ms) and peak data rates exceeding 1 Tbps. This leap is not merely incremental; it enables a "Digital Twin of Everything," where the physical and digital worlds are perfectly synchronized in real-time. In a precision nanotech assembly line, a delay of just 2ms could result in a mechanical misalignment of several millimeters, potentially ruining a high-value batch of semiconductors or causing catastrophic failure in medical implant manufacturing. Furthermore, 6G is envisioned as an "AI-Native" network, where the infrastructure itself is composed of intelligent agents that optimize transmission parameters in real-time without human intervention. The core challenge in modern IIoT environments remains the "Intelligence Bottleneck"—the cumulative delay incurred when high-dimensional ML inference tasks are offloaded to resource-constrained edge nodes. In a high-speed production line where components move at several meters per second, a delay of even 5ms can lead to synchronization errors between robotic actuators. Consequently, achieving deterministic, sub-millisecond latency requires a paradigm shift: moving away from static resource management toward intelligent, context-aware management of both communication and computational resources. This involves not just faster radios, but smarter ways to decide where and how data should be processed, often referred to as Compute-Communication Integration (CCI). We term this the "Unified Intelligence-Control Loop," where the network is not an external utility but an intrinsic part of the machine's control logic. This loop is further refined by "Semantic Pruning," where AI agents at the source decide which 1% of data carries 99% of the mission-critical meaning, dramatically reducing the "Air-Time" required for transmission. 2. 6G Technical Enablers for Edge Intelligence To support the proposed DLO framework, several 6G-specific technologies are integrated into our system model, addressing the unique propagation and computation challenges of industrial halls. 2.1 Terahertz (THz) Spectrum and Sub-THz Communication The utilization of the THz band (0.1–10 THz) offers massive bandwidth (hundreds of GHz), enabling the near-instantaneous transmission of uncompressed high-definition video feeds for AI-driven inspection. While THz waves suffer from high atmospheric attenuation and limited range, they are ideal for the "pico-cell" deployments characteristic of indoor industrial environments. At these ranges, the "Oxygen Absorption" and "Water Vapor Resonance" spikes that plague long-distance THz communication are negligible, allowing for stable links. We specifically target the "Atmospheric Windows"—narrow frequency bands where molecular absorption is at its local minima—to ensure signal robustness. However, in industrial settings, we must account for Scintillation and Turbulence. Large industrial furnaces or chemical reactors can create localized pockets of high-temperature air, causing fluctuations in the air's refractive index (). This leads to "Beam Wandering," where the pencil-thin THz beam misses the target. Our model incorporates a Turbulence-Induced Fading coefficient, modeled using the Gamma-Gamma distribution, to ensure the DLO agent can predict and compensate for these environmental "flickers." The Molecular Absorption Loss () is calculated using the HITRAN database. We model the THz channel as:   Where       is the absorption coefficient and is the turbulence-induced fading factor. Unlike the Sub-6GHz bands, THz signals exhibit "Quasi-Optical" properties, meaning they behave more like light than traditional radio waves. Specifically, we utilize the D-band (110–170 GHz), which provides a middle ground between high data rates and manageable propagation loss. Furthermore, the short wavelengths of THz allow for Terascale MIMO—antenna arrays with tens of thousands of elements. These enable "Near-Field Beamforming," where the beam can be focused onto a specific 3D coordinate (a "focal spot") rather than just a direction. This provides unprecedented spatial reuse, allowing multiple robots in the same vicinity to operate on the same frequency without mutual interference. This "Focus-Spot" approach also minimizes the Electromagnetic Interference (EMI) on sensitive biological tissues of human workers, a key safety requirement for Industry 5.0. 2.2 Reconfigurable Intelligent Surfaces (RIS) Industrial environments are notoriously cluttered with metallic machinery that causes multi-path interference and frequent signal blockage (shadowing). To solve this, we incorporate RIS—programmable meta-surfaces that can "steer" radio waves—to bypass physical obstacles. An RIS consists of a thin sheet of electromagnetic material embedded with sensors and micro-controllers that can change the phase of an incoming wave. In our implementation, the RIS acts as a "Smart Mirror." If a large metal press blocks the direct path between a robot and an edge server, the RIS identifies the blockage and reflects the signal around the corner. The RIS consists of an N*M array of passive scattering elements. Mathematically, the RIS is modeled as a diagonal matrix.                                       This creates "Constructive Interference" at the receiver's location. Beyond passive reflection, we integrate "Simultaneous Transmitting and Reflecting" (STAR-RIS). A STAR-RIS can reflect signals to devices in front of it while transmitting (refracting) signals to devices behind it. This is particularly useful for separating "Public" factory data from "Private" robotic control data. In a scenario where a clean-room is separated by a glass or thin composite wall, a STAR-RIS can serve both sides of the wall simultaneously with zero hand-off latency. Furthermore, the RIS elements can be used for Passive Sensing, turning the factory walls into a giant "radar" that can track the movement of human workers with centimeter accuracy without the need for cameras, thus preserving worker privacy while ensuring safety. 2.3 Semantic Communication: The Evolution of Meaning A novel feature of our 6G framework is Semantic Communication. Traditional communication systems focus on transmitting bits accurately, regardless of their meaning. In contrast, Semantic Communication extracts "semantic features" locally and transmits only the information relevant to the specific task objective. Our DLO framework operates at Levels B and C of the Weaver-Shannon hierarchy. For example, in a robotic sorting task, the device does not send a full video frame; instead, it sends a compact vector representing the object's class and spatial coordinates. Consider an Autonomous Guided Vehicle (AGV) navigating a warehouse. Instead of streaming 4K video, the AGV's on-board processor identifies the "semantics" of the scene: "Human worker at 45 degrees, 2 meters away." This compact representation reduces the data payload size by up to 95%. This requires a Semantic Knowledge Base (SKB) shared between the device and the edge. We implement Semantic Feature Alignment (SFA), where the AI model periodically checks if its "understanding" of a concept (e.g., "Defective Part") still aligns with the edge's definition. We further introduce "Semantic Importance Mapping," which is an application of Value of Information (VoI) theory. In a VoI-optimized network, the "cost" of losing a packet is not just a retransmission delay; it is the "loss of utility" for the end-application. If a robot is in a stationary "waiting" state, the VoI of its telemetry is low. If the robot is in a "high-speed grab" state, the VoI is extreme. Our 6G-DLO framework prioritizes these "High-VoI" bursts over all other traffic, ensuring that the network is always "aware" of the industrial context. 3. System Architecture: The Unified Intelligence Fabric The proposed architecture follows a three-tier model where intelligence is natively embedded into the network fabric. 3.1 Layered Framework IIoT Device Layer: Consists of sensors and actuators with low-power embedded AI chips (TinyML). This layer handles Local Feedback Loops, such as micro-adjustments in robotic joints that require response times below 100 microseconds. We implement "Edge-Native Awareness," where the device can sense if the network is degrading and preemptively switch to a "Safe-Stop" mode. We also utilize "Neuromorphic Sensing" (Event-Based Cameras), which only transmit pixels that change, naturally aligning with the semantic philosophy. 6G Edge Intelligence Layer: Distributed edge servers (MECs) feature AI-native network slicing. Each node hosts a local DLO agent performing Predictive Load Balancing. This includes Virtual Machine (VM) Live Migration optimized for microsecond transitions. We also implement "Compute-as-a-Service" (CaaS). This tier is also responsible for Model Splitting, where the first few layers of a Deep Neural Network (DNN) are executed on the device, and the complex remainder is offloaded to the edge, minimizing the amount of raw data that needs to cross the wireless link. Cloud Layer: The "Brain" layer handles "Macro-Optimization." It identifies drift in ML model accuracy and triggers global retraining. This tier manages Long-Term Digital Twin Persistence, allowing for "time-traveling" diagnostics. The cloud also acts as the Root of Trust for the Blockchain-based security layer, managing the lifecycle of cryptographic identities for millions of IoT sensors. 3.2 System Model 4. Methodology: Dynamic Latency Optimization (DLO) The DLO algorithm utilizes a Deep Q-Network (DQN) combined with Lyapunov Optimization to ensure long-term system stability. 4.1 Mathematical Formulation The objective is to minimize a multi-objective Cost Function (C). We define the system state S at time T as:   The cost function is:   Here,       is the Lyapunov Penalty. Using the Lyapunov drift-plus-penalty framework, we define a Lyapunov function L(Q)=12Q2The agent minimizes the drift ΔL(Q) plus the weighted cost V.C, where V is a "Stability-Performance" trade-off parameter. If V is large, the system focuses on latency (Ttotal); if V is small, it focuses on keeping the queue Q short to prevent buffer bloat. This is particularly critical for Isochronous Communication, where any queue buildup causes jitter that breaks the haptic feedback loop. We extend this with "Early Exit" DNNs, where the agent can decide to stop the inference at a middle layer of the neural network if the latency budget is about to expire, sacrificing 1-2% accuracy for a 50% reduction in compute time. 4.2 DRL and Policy Execution We use a Deep Deterministic Policy Gradient (DDPG) approach for continuous control of transmission power and beamwidth. Experience Replay with PER: We use Prioritized Experience Replay (PER). In a factory, "collision events" are rare. PER ensures the agent learns from these rare but high-impact failures. Reward Shaping: The reward function R is shaped to penalize "Tail Latency" (the p99 delay) more than the average delay. This pushes the agent to develop a "Risk-Averse" policy that is robust against the worst-case network scenarios. Multi-Agent Coordination: In large factories, multiple DLO agents (one per edge node) use Federated Reinforcement Learning (FRL) to share their learned policies without sharing raw traffic data. This allows an agent in a "Packing Station" to benefit from the experiences of an agent in a "Welding Station," leading to faster global convergence. 5. Security and Privacy: Zero-Trust Federated Intelligence 5.1 Federated Learning (FL) and Differential Privacy Our framework integrates FL to ensure proprietary data stays local. We implement Asynchronous Federated Learning. To protect against "Reverse Engineering" of gradients, we add Differential Privacy (DP) noise. We use an Adaptive DP mechanism where the noise level is high for "Common Data" and low for "Rare Edge-Case Data," ensuring that the collective model learns critical failure patterns without leaking sensitive production statistics. Furthermore, all model updates are signed using Post-Quantum Cryptography (PQC) (e.g., Dilithium), ensuring that a future quantum computer cannot forge model updates to poison the factory's collective intelligence. 5.2 Blockchain and Smart Interlocks We utilize a high-speed Permissioned Blockchain to log every "Offloading Contract." This enables "Micro-Slicing Monetization," where different manufacturing departments can "pay" for network priority using internal digital tokens, creating a market-based approach to resource allocation. Crucially, we introduce "Smart Interlocks". These are decentralized autonomous safety protocols. If the network detects that a robotic arm is deviating from its Digital Twin path, a Smart Contract can immediately revoke its "Authorized-to-Move" status. Because this check happens on the distributed edge ledger, it is immune to a compromise of the central PLC (Programmable Logic Controller), providing a hardware-rooted defense against Cyber-Physical Sabotage. 6. Performance Evaluation: Results and Analysis 6.1 Results Comparison Metric 5G + MEC 6G + Static Proposed 6G-DLO Avg. E2E Latency 10.5 ms 1.2 ms 0.38 ms Jitter (Std Dev) 4.2 ms 0.8 ms 0.05 ms Peak Latency (p99) 32.0 ms 4.1 ms 0.72 ms Energy Efficiency 1.0x 1.9x 3.0x Improvement Reliability 99.9% 99.99% 99.99999% Semantic Gain N/A 1.5x 12x Reduction in Payload 6.2 Analysis of Results The 12x reduction in payload through Semantic Communication is the primary driver of the 3.0x energy improvement. By only transmitting "important" features, the radio hardware operates with a lower duty cycle. The p99 latency of 0.72 ms ensures that even in the busiest factory hour, the network remains deterministic. This determinism is what enables "Zero-Buffer Manufacturing," where parts arrive at the exact microsecond they are needed by the assembly robot, effectively turning the network into a virtual conveyor belt. 7. Human-Centric Reliability (HCR) and Neuro-Industrial Interface Industry 5.0 is about humans. We define Human-Centric Reliability (HCR) as the probability that the system maintains a "Natural Feedback" feel. Proprioceptive Alignment: If haptic feedback is delayed by more than 15ms, the human brain begins to experience "Proprioceptive Drift," where the robotic hand feels "disconnected" from the user's intent. Our 6G-DLO agent monitors the Bio-Signal Quality (from EMG/EEG sensors) and adjusts the 6G slice parameters to keep the drift below the human detection threshold. Cognitive Fatigue Monitoring: Using 6G-connected eye-tracking and heart-rate variability (HRV) analysis, the edge server can detect when a human operator is becoming fatigued. In response, the system can autonomously increase the "Robot Autonomy Level" (LoA), taking over more of the control tasks to prevent human error while notifying the supervisor. This creates a "Dynamic Social-Technical Loop" where the network adapts to the human, rather than forcing the human to adapt to the network. 8. Sustainability and the "Green" Constraint 6G networks, with their massive antenna arrays and high-frequency electronics, pose a significant power challenge. We incorporate a Life Cycle Assessment (LCA) module into the cloud. Thermal Footprint Management: THz beams are highly energetic. In a dense factory, cumulative EM radiation could affect sensitive chemical processes. Our DLO agent includes a "Spatial Heat Constraint," ensuring that beams are spaced out over time and space to keep the ambient EM temperature within safe limits. Energy-Harvesting IIoT: We explore 6G's "Simultaneous Wireless Information and Power Transfer" (SWIPT). The RIS can be used to focus energy onto low-power sensors, charging them wirelessly while they transmit data. This eliminates millions of batteries from the factory lifecycle, moving toward a truly Circular Industrial Economy. 9. Future Challenges and Roadmap Spectrum Governance: THz frequencies are currently undergoing global allotment. We need a "Dynamic Spectrum Sharing" (DSS) framework that allows factories to use THz bands without interfering with radio astronomy or satellite links. Cross-Border Sovereignty: For global manufacturers, we need a "Federated Data Sovereignty" protocol where AI models can be shared across borders (e.g., from a design HQ in Europe to a factory in Asia) while complying with varying regional privacy laws (GDPR, etc.). The "Self-Optimizing" Meta-Factory: Moving toward a system where the network not only manages latency but actually suggests physical layout changes to the factory floor (e.g., "Moving Robot A 2 meters closer to Node B will save 5% energy and 20% latency"). Conclusion This article has demonstrated that 6G is a Cognitive Fabric. By integrating THz, RIS, Semantic Communication, and DRL-based optimization, we have paved the way for Industry 5.0. The ability to maintain deterministic, sub-millisecond latency while preserving human agency and data privacy will define the next century of production. The factory of the future will be a place where the human mind, the robotic arm, and the 6G network function as a single, high-performance ecosystem of co-creation, driven by the philosophy that technology should serve to amplify human potential, not replace it. References Gowroju, S. and Ansarullah, S.I.,. A comprehensive review of developments and challenges in the 6G internet of things. Discover Networks, 1(1), p.13. Zhang, L., et al. "Deep Reinforcement Learning for Latency-Critical IIoT." IEEE TII (2024). Tang, J., 2025. Deep-Reinforcement-Learning–Guided Resource Allocation and Task Offloading for 6G Edge Intelligence. Computer Communications, p.108364. "Reconfigurable Intelligent Surfaces: A 6G Perspective." Nature Electronics (2025). Zhao, H., 2025. Research on privacy protection and performance optimization of 6G communication network based on the fusion of federated learning and edge computing. Discover Artificial Intelligence. Kariyappagowda, Y.B., Manjunatha, G., Sabin, T.T. and Prabhavathi, K., 2025, August. Edge AI-Driven Vision Systems for Zero-Defect Manufacturing in 6G-Enabled Industry 5.0: The Factory of the Future. In 2025 International Conference on Sustainability, Innovation & Technology (ICSIT) (pp. 1-7). IEEE. Oukebdane, M.A., Shah, A.S., Azad, A.K., Ekoru, J. and Madahana, M., 2025. Unraveling the nexus of ML and 6G: Challenges, Opportunities, and Future Directions. IEEE Access. Sharma, N. and Sharma, S., 2025. A review on unlocking performance insights for next generation connectivity with AI in 6G communication. Radio Science, 60(7), pp.1-27. "Haptic Over 6G: The Proprioceptive Challenge." Tactile Internet J. (2025). "Federated Learning for Private Industrial Intelligence." ML for Networking (2024). Pokhrel, S. R., et al. "Lyapunov Stability in 6G Edge Networks." IEEE Wireless Comm. (2025). Alatawi, M.N., 2025. SAFEL-IoT: secure adaptive federated learning with explainability for anomaly detection in 6G-enabled Smart Industry 5.0. Electronics, 14(11), p.2153. Sharma, M., Tomar, A. and Hazra, A., 2025. Near-Edge Computing For Industry 5.0. In Industry 5.0: Key Technologies and Drivers (pp. 505-528). Cham: Springer Nature Switzerland. Kapoor, D., Gupta, D. and Uppal, M., 2025. Analyzing the impact of edge, fog and cloud computing on predictive maintenance in the Industrial Internet of Things. Discover Computing, 28(1), p.207. Alipio, M. and Bures, M., . The Role of Large Language Models in Designing Reliable Networks for Internet of Things: A Short Review of Most Recent Developments. IEEE Access. Alwaisi, Z., 2025. Memory-efficient and robust detection of Mirai botnet for future 6G-enabled IoT networks. Internet of Things, 32, p.101621. Betalo, M.L., Wu, Z., Li, J., Bai, X., Zhang, W. and Ge, S.S., 2025. RIS-Assisted UAV-Based Dynamic Coverage Control for 6G-Enabled Internet of Everything Using Multi-agent DRL. IEEE Transactions on Automation Science and Engineering. Alfahaid, A., Alalwany, E., Almars, A.M., Alharbi, F., Atlam, E. and Mahgoub, I., 2025. Machine learning-based security solutions for iot networks: A comprehensive survey. Sensors, 25(11), p.3341. Supriadi, C., Wahyudi, W., Priyadi, A. and Jin, K.S., 2025. Decentralized AI on The Edge: Implementing Federated Learning for Predictive Maintenance in Industrial IoT Systems. Journal of Technology Informatics and Engineering, 4(2), pp.317-336. Kaki, S.S., Kantareddygari, J.R. and Aishwarya, R., 2025, February. Privacy and security concerns in edge-cloud systems: An in-depth analysis. In 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT) (pp. 435-441). IEEE. Soliman, A., 2025. The Future of Internet of Things and Multimodal Language Models in 6G Networks: Opportunities and Challenges. arXiv preprint arXiv:2504.13971. Pan, Y., Lei, L., Shen, G., Zhang, X. and Cao, P., 2025. A survey on digital twin networks: Architecture, technologies, applications and open issues. IEEE Internet of Things Journal. Ahmed, S.F., Shawon, S.S., Afrin, S., Rafa, S.J., Hoque, M. and Gandomi, A.H., 2025. Optimising Internet of Things (IoT) Performance Through Cloud, Fog and Edge Computing Architecture. IET Wireless Sensor Systems, 15(1), p.e70016. Omheni, N., Koubaa, H. and Zarai, F., 2025. Artificial intelligence for 5G and 6G networks: A taxonomy-based survey of applications, trends, and challenges. Technologies, 13(12), p.559. Aljawabrah, N., Aljamal, M., Okour, S., Kharabsheh, M., Samarah, T. and Mughaid, A., 2025, November. Architecture Search using AI Agent: Novel IDS for Edge-Based IoT Security. In 2025 3rd International Conference on Foundation and Large Language Models (FLLM) (pp. 16-22). IEEE. Jamshidi, S., Nikanjam, A., Wazed, N.K. and Khomh, F., 2025. Leveraging Machine Learning Techniques in Intrusion Detection Systems for Internet of Things. arXiv preprint arXiv:2504.07220. Hakeem, S.A.A. and Kim, H., 2025. Advancing intrusion detection in V2X networks: A comprehensive survey on machine learning, federated learning, and edge AI for V2X security. IEEE Transactions on Intelligent Transportation Systems. Al Jawarneh, I.M., Rosa, L., Venanzi, R., Foschini, L. and Bellavista, P., 2025. Efficient parallel processing of big data on supercomputers for industrial IoT environments. Electronics, 14(13), p.2626. Chen, X., Wu, W., Li, L. and Ji, F., 2025. LLM-empowered IoT for 6G networks: Architecture, challenges, and solutions. IEEE Internet of Things Magazine. Thakur, S., Sarkar, N.I. and Yongchareon, S., 2025. AI-Driven Energy-Efficient Routing in IoT-Based Wireless Sensor Networks: A Comprehensive Review. Sensors, 25(24), p.7408.

Identifiers

DOI

10.5281/zenodo.20094300

URL

https://www.periodicos-ulbra-br-index-php-acta.cloudns.ch/current-issue

Documentary context

Documentary family

article

Source-reported types

JournalArticle

Publishers

Acta Scientiae

Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.

Sources

DataCite · Record 1

• Document · https://zenodo.org/doi/10.5281/zenodo.20094300

Documentary status

Relevance pending

Library

This identity is not yet included in the Legal Library.