6G Revolution Transforming Connectivity: Recent Developments in 6G Communication Systems and the Crucial Role of URLLC in India

6G Revolution Transforming Connectivity: Recent Developments in 6G Communication Systems and the Crucial Role of URLLC in India

Abstract – This article explores the current phase of 5G wireless technology, which is undergoing global rollout and standardization. Despite its advancements, 5G still lacks the intelligence and automation needed for fully connected, intelligent systems. These capabilities are expected to emerge with 6G, as countries around the world begin laying the groundwork to meet the communication demands of the 2030s. The transition to 6G invites deeper discussion on the future of wireless communication and its adaptability to a broader range of use cases and applications. As 5G becomes increasingly accessible, both industry leaders and academic researchers have started shifting their focus to what lies beyondnamely, the transformative potential of 6G. India is actively preparing for the commercial launch of 6G by 2030, with the International Telecommunication Union (ITU) backing its vision of affordable, high-speed internet access for a large population. Beyond faster connectivity, 6G will be vital in supporting pervasive artificial intelligencefrom the core of the network to the edge. AI will play a crucial role in shaping the architecture, protocols, and operation of 6G systems. One of the key components in next-generation networks will be Ultra-Reliable Low-Latency Communication (URLLC), which is indispensable for mission-critical applications like remote robotic surgery, autonomous vehicles, smart manufacturing, and augmented reality. 6G infrastructures, equipped with URLLC and integrated AI capabilities, will be able to handle time-sensitive and safety-critical tasks with precision. This article highlights the importance of URLLC in 6G, its synergy with deep learning, related security challenges, and potential solutions.

Keywords: 6G Communication, URLLC (Ultra-Reliable Low-Latency Communication), Artificial Intelligence in Wireless Networks, Future Wireless Technologies.

1. INTRODUCTION

   The evolution of wireless communications has entered a transformative stage as the industry and academia push beyond the 5G horizon into the nascent era of 6G. As highlighted by Kamath et al. (2023), the current 5G architecture, while widely deployed and standardized, lacks the inherent intelligence and automation needed to support truly connected systems. Their review anticipates that 6G will catalyze an unprecedented shift in cellular networksushering in seamless AI-enabled services from the network core to edge devices, and enabling applications that 5G cannot adequately support.

   One of the defining features of 6G will be its support for Ultra-Reliable Low-Latency Communication (URLLC), a critical component for time-sensitive, mission-critical applications. According to Gomathi et al. (2025), Edge AI integrated within 6G URLLC frameworks offers a powerful solution: by processing data closer to devices, it meets stringent latency and reliability requirements essential for industrial automation, autonomous vehicles, remote robotic surgery, and VR/AR environments. This convergence of edge intelligence with real-time communication marks a pivotal advancement beyond 5G.

   Source: Article Muhammad Zeeshan Asghar, Shafique Ahmed Memon, Jyri Hämäläinen (2022)

   In India, this technological shift is gaining decisive momentum. National initiatives such as the Bharat 6G Alliance demonstrate a coordinated effort to establish India as a leader in 6G innovation. The Alliance emphasizes policy support, spectrum planning, and robust R&D to contribute significantly to global standard-setting bodies, including ITU and 3GPP. By combining URLLC, Edge AI, and secure, low-latency protocols, Indias strategic 6G roadmap is designed to support a wide range of transformative use cases from smart manufacturing and intelligent transport to telemedicine and immersive virtual experiences. This introduction sets the stage for a detailed review of how URLLC evolves within 6G, addressing its deep-learning integration, security challenges, and regulatory implications in the Indian context.

   Wireless communication has progressed dramatically since the 1980s when analog-based 1G enabled voice calls. Each successive generation from 2Gs digital voice and SMS to 3Gs mobile internet and 4Gs mobile broadband has transformed connectivity paradigms. The 5G era brought high speed, low latency, and massive device connectivity, yet it falls short of delivering full AI-native intelligence and automation. The evolution chart above illustrates how key performance indicators (KPIs) like throughput, lat ency, reliability, and spectral efficiency have spiked each generation, reaching terabit-level ambitions with 6G. Asghar et al. (2022) provided a detailed mapping of 6Gs envisioned capabilities, highlighting how future applicationssuch as holographic communications and Internet-of-Bio-Nano-Things (IoBNT) demand unprecedented throughput, end-to-end latency under 1 ms, and ultra-high reliability. These network evolutions point toward integrating space air ground sea infrastructure and novel frequency bands like terahertz (THz), laying the foundation for next-gen systems.

2. 6G VISION AND CORE

   The vision for 6G extends beyond enhanced mobile broadband (eMBB), URLLC, and massive machine-type communications (mMTC) the core triad of 5G. Instead, it emphasizes ultra-reliable ultra-low-latency communication (xURLLC), 3D ubiquitous coverage, integrated sensing-communication (ISAC), and onboard AI systems. Chowdhury et al. (2019) projected 6G to offer peak data rates in the terabit-per-second range, latency in sub-millisecond, spectrally efficient cell-free MIMO and intelligent surfaces, and broad use of THz and visible light communications.

   Sustainability and resilience are also crucial. Asghar et al. showed that 6G architecture must balance extreme performance with energy efficiency and environmental concerns Additionally, global standardization tracking via IMS-2030 emphasizes universal network coverage while enabling diverse vertical applications

3. TECHNOLOGICAL PILLARS UNDERPIN 6G:

   Terahertz Communications (100 GHz3 THz): Rappaport et al. (2019) and Wikipedia metadata predict use of THz bands, offering huge bandwidth yet suffering from high path loss, prompting research into beamforming, intelligent surfaces, and hybrid network topologies.

   Reconfigurable Intelligent Surfaces (RIS): MDPI studies on RIS show real-time electromagnetic wave manipulation, particularly when steered by AI algorithms, enhancing spectral efficiency and interference control

   AI-native Architecture: Yang et al. (2019) and Wen et al. (2024) coined "intent-based communication," integrating AI deeply at every layerfrom sensing and data mining to control and applicationto support dynamic resource allocation and service provisioning

   Space-Air-Ground-Sea Integration: Chowdhury et al. (2019) highlighted the expansion to non-terrestrial networks (NTNs) and cell- free massive MIMO, ensuring worldwide coverage and robustness

   1. URLLC and xURLLC

      URLLC is a central pillar of 6G, enabling mission-critical use cases across industry, healthcare, and transportation.Gomathi et al. (2025) demonstrated how Edge AI within URLLC frameworks drastically reduces latency and boosts reliability, essential for real- time control like robotic surgery and autonomous driving. Salh et al. (2023) surveyed AI-driven enhancements, noting advancements in deep learning for coding, resource allocation, and network slicing to meet terabit throughput and sub-millisecond latency within xURLLC contexts. The combined hardware-software innovation enables predictable, ultra-deterministic performance.

   2. ULTRA-RELIABLE LOW-LATENCY COMMUNICATION (URLLC)

      According to Changyang She et al., (2020 Ultra-Reliable Low-Latency Communication (URLLC) has emerged as a defining element of next-generation wireless systems. It bridges the gap between high-speed mobile broadband and mission-critical applications delivering sub-millisecond latency and reliability above 99.999%. As She et al. (2020) explain, current 5G implementations fall short in supporting true end-to-end URLLC. They propose a multi-tier deep learning architecture integrating device, edge, and cloud intelligence to address theoretical and practical barriers. In the context of 6G, URLLC demands extreme performance. An MDPI review defines key KPIs: end-to-end latency under 1 ms, jitter control, and reliability in the order of 10^-9 . These metrics serve haptic communications, industrial automation, autonomous driving, and remote surgery. For academic framing, Park et al. (2020) introduce xURLLC extreme URLLC which extends the URLLC paradigm by integrating non-RF modalities and ML predictions for predicting rare events, ensuring reliability beyond 5Gs scope.

   3. Architectural Design: Multi-Level Intelligence

      Changyang She and colleagues (2020) propose a deep learning-infused architecture where device-level, edge, and cloud computing collaborate to satisfy stringent URLLC demands (see diagram). The architecture layers:

      • Device Intelligence: Lightweight deep models for low-latency signal processing.

      • Edge Intelligence: Medium-compute units for aggregating data and real-time optimization.

      • Cloud Intelligence: Large-scale training and coordination.

   This blended approach ensures latency-sensitive tasks remain at the edge while complexity-heavy optimizations occur centrally, enhancing responsiveness and efficiency. AI/ML play a central role in URLLC design. She et al. (2020) explore supervised, unsupervised, and reinforcement learning for optimizing coding and resource allocation. Additionally, Salh et al. (2021) surv ey

   how AI-driven, fully data-centric URLLC systemsencompassing deep neural networks, transfer learning, and federated learning are vital for managing vast volumes of data in real-world 6G environments.

   Traditional cryptography introduces delays incompatible with URLLC. Chen et al. (2019) propose physical-layer security (PLS) as a lightweight alternative. Using channel randomness, PLS secures transmissions without compromising latency. A 2024 survey extends this, highlighting PLS implementations in URLLC enhanced by ML for covert, fast, and reliable operation. Nielsen et al. (2017) propose using multiple interfaces and erasure-coding schemes to concurrently transmit URLLC data across varied paths boosting reliability without tackling the physical layer directly. URLLCs coexistence with eMBB and mMTC brings resource- slicing challenges. Works such as Al-Ali and Yaacoub (2023) offer algorithms that prioritize URLLC traffic while maximizing spectral efficiency a balance crucial for mixed-use environments Additionally, Steeles survey (2024) on AI/ML-augmented strategies underscores massive MIMO, beamforming, and intelligent scheduling as key to meeting URLLCs dual demands

4. ARTIFICIAL INTELLIGENCE IN WIRELESS NETWORKS

   The intersection of artificial intelligence (AI) and wireless communications has evolved from a promising concept to an essential paradigm, especially as the world gears up for 6G. Early perspectives such as Letaief et al. (2019) envisaged 6G as an AI-native network where machine learning shapes protocols, resource allocation, and self-optimization, transforming wireless from connected things into connected intelligence.

   Yang et al. (2019) introduced a four-layer intelligent frameworksensing, analytics, control, and applicationthat guides dynamic network behavior. Their architecture supports smart spectrum management, mobility, and edge computing. Elsayed & Erol-Kantarci (2021) proposed foundational AI deployment strategiescentralized, decentralized, and hybridfor B5G/6G systems. They analyzed survey results, highlighting cost-performance trade-offs and noted that cell-free massive MIMO systems greatly benefit from AI-enhanced channel estimation . Letaief et al. (2021) highlighted edge AI as a cornerstone for deploying swarm intelligence at the network edge. They underlined its role in reducing latency, enhancing privacy, and improving computing efficiency when embedding training and inference directly into base stations .

   A recent arXiv survey by Cui et al. (2024/25) outlines three evolutionary stages of AI in networks:

   1. AI for Network leveraging ML to optimize network performance.

   2. Network for AI building networks that support distributed AI workloads.

   3. AI as a Service delivering AI functionalities (e.g., inference, semantic communication) as part of network offerings This staged progression emphasizes the journey from intelligence-enhanced networking to inherently intelligent networks that actively serve AI applications.

      Technologies Empowered by AI

      AI enhances several emerging wireless technologies:

      • Terahertz (THz) and millimetre-wave communications require real-time beam mitigation and blockage prediction tasks well-suited for AI

      • Ultra-massive MIMO and cell-free architectures benefit from AI-driven resource and interference management.

      • Reconfigurable Intelligent Surfaces (RIS) rely on AI to dynamically configure reflecting elements based on spatial and environmental data

      • Non-terrestrial Networks (UAVs/satellites) use AI for trajectory optimization and efficient bandwidth allocation

        These AI applications enhance efficiency, coverage, and reliability across all wireless layers.

        Nvidia's 2024 research platform, integrating AI and wireless system synergies, underscores industry momentum. Platform simulations combining city terrains and network models aim to accelerate innovation in real-world wireless environments.

      • Smart Cities & IoT: AI orchestrates device communication, energy use, and service quality.

      • Autonomous Systems: AI supports seamless handovers and predictive routing .

      • Edge-Cloud Continuum: AI-enabled edge gateways process latency-sensitive applications while cloud infrastructure provides scalable distributed intelligence.

5. FUTURE WIRELESS TECHNOLOGIES

   Wireless communications have undergone remarkable evolution, transitioning from 1G analog voice to todays 5G high-speed, massive connectivity platforms. As demands growdriven by AI, IoT, smart manufacturing, and immersive applicationsthe journey now heads toward 6G and beyond. Recent review works examine this path, highlighting both novel technologies and integration challenges. Bindushree GT (2023) offers a comprehensive analysis of emerging wireless innovations, tracing the trajectory from 5G through IoT, Wi-Fi 6 to the envisioned 6G era. The review emphasizes the incorporation of AI/ML to improve network efficiency and energy use. It explores spectrum managemnt, especially for terahertz communications, and the use of intelligent surfaces to enhance coverage and beam steering. This broad survey sets the context for the transformational objectives of future wireless technologies

   Shafie et al. (2022) dive into terahertz (THz) communication, a cornerstone for 6Gs projected terabit-per-second data rates. They review key challenges: massive attenuation, the requirement for new antenna arrays, ultra-narrow beamforming, and advanced materials. The article also examines end-to-end system designfrom physical to network layersand proposes integration strategies for THz links in future architectures. A study in ICT Express (2024) highlights how edge computing is critical for low-latency applications like autonomous driving, industrial automation, and AR/VR. It investigates resource orchestrationbalancing computation, storage, and communicationwithin heterogeneous networks. The work evaluates synergy between 5G and edge computing and outlines how 6G will require even tighter integration with resource-aware, distributed architectures.

   The paper AI empowered 6G technologies and network layers (Expert Systems with Applications, 2025) focuses on AIs role across stack layers. It highlights deep learning for beam management, reinforcement learning for network slicing, and federated learning for privacy-preserving orchestration. The review identifies technical, ethical, and regulatory challengessuch as AI bias and cloud/edge coordinationwhile charting promising research directions

6. SUGGESTIONS AND IMPLICATIONS

   The convergence of Edge AI and URLLC, as emphasized by Gomathi et al. (2025), suggests opportunities in deploying on-device learning models that adapt in real time to network dynamics. Researchers should explore federated learning at the network edge to boost performance without compromising privacy or latency. Shafie et al. (2022) and Asghar et al. (2022) highlight the potential of THz communications paired with reconfigurable intelligent surfaces (RIS). Experimental research should investigate joint protocols for beam steering and RIS configuration under real-world mobility conditions, especially in urban settings. Material science partnerships will be critical to reduce signal attenuation and hardware costs.

   Chowdhury et al. (2019) and Elsayed & Erol-Kantarci (2021) note fragmented progress in global standard frameworks. Indias Bharat 6G Alliance should spearhead efforts within ITU and 3GPP to standardize Edge AI, URLLC, and THz communication layers. Harmonized APIs, spectrum-sharing agreements, and shared testbeds can accelerate global adoption. The need for Physical Layer Security (Chen et al., 2019) and ultra-low latency is paramount. Future work should formalize threat models unique to AI-enabled protocols such as RIS and edge orchestration. Quantum-safe encryption methods paired with lightweight AI classifiers could offer a viable approach to simultaneous security and responsiveness.

   According to Asghar et al. (2022) and Letaief et al. (2021) underscore, energy-optimized AI and network design are crucial. Research should investigate green architecturesfor instance, AI-managed sleep modes in THz transceivers or AI-controlled power

   scheduling in massive MIMO arraysto align connectivity gains with environmental stewardship. Despite prolific simulation-based studies, real-world URLLC and Edge AI demonstrations remain scarce. India and other regions should prioritize live testbeds across industrial, healthcare, and transportation domains to understand system efficacy, integration challenges, and policy implications under operational conditions.

7. CONCLUSION

   In this article form a cohesive roadmap: AI-integrated edge networks, URLLC for mission-critical systems, THz-RIS physical layers, and interoperable global standards represent the cornerstones of next-gen wireless. However, challenges remain in security, energy use, and real-world deployment. Coordinated policy support like Indias Bharat 6G Alliancecoupled with federated AI, quantum- resistant protocols, and green communication strategies can convert theoretical advances into societal impact. By bridging research silos through live validation, the wireless ecosystem can deliver transformative connectivity for healthcare, industry, autonomous transport, and immersive user experiences.

8. REFERENCE

1. Al-Ali, M., & Yaacoub, E. (2023). Resource allocation scheme for eMBB and uRLLC coexistence in 6G networks. Wireless Networks, 29, 25192538. https://doi.org/10.1007/s11276-023-03328-2

2. Asghar, M. Z., Memon, S. A., & Hämäläinen, J. (2022). Evolution of wireless communication to 6G: Potential applications and research directions.

   Sustainability, 14(10), Article 6356. https://doi.org/10.3390/su14106356

3. Asghar, M. Z., Memon, S. A., & Hämäläinen, J. (2022). Evolution of wireless communication to 6G: Potential applications and research directions.

   Sustainability, 14(10), Article 6356. https://doi.org/10.3390/su14106356

4. Author, A. (2025). AI empowered 6G technologies and network layers: Recent trends, opportunities, and challenges. Expert Systems with Applications, 267, 125985. https://doi.org/10.1016/j.eswa.2024.125985

5. Bindushree, G. T. (2023). Next-generation wireless communication: Innovations, challenges, and the convergence of AI, IoT, and 6G. World Journal of Advanced Research and Reviews, 19(2), 16541662. https://doi.org/10.30574/wjarr.2023.19.2.1613 Wjarr

6. Chen, R., Li, C., Yan, S., Malaney, R., & Yuan, J. (2019). Physical layer security for ultra-reliable and low-latency communications. arXiv. https://doi.org/10.48550/arXiv.1906.08443

7. Chen, R., Li, C., Yan, S., Malaney, R., & Yuan, J. (2019). Physical layer security for ultra-reliable and low-latency communications. arXiv. https://doi.org/10.48550/arXiv.1906.08443

8. Chen, T., Deng, J., Tang, Q., & Liu, G. (2023). Optimization of quality of AI service in 6G native AI wireless networks. Electronics, 12(15), 3306. https://doi.org/10.3390/electronics12153306

9. Chowdhury, M. Z., Shahjalal, M., Ahmed, S., & Jang, Y. M. (2019, September 25). 6G wireless communication systems: Applications, requirements, technologies, challenges, and research directions. arXiv. https://doi.org/10.48550/arXiv.1909.11315

10. Chowdhury, M. Z., Shahjalal, M., Ahmed, S., & Jang, Y. M. (2019, September 25). 6G wireless communication systems: Applications, requirements, technologies, challenges, and research directions. arXiv. https://doi.org/10.48550/arXiv.1909.11315

11. Cui, Q., et al. (2025). Overview of AI and communication for 6G network: fundamentals, challenges, and future research opportunities. Science China Information Sciences. https://doi.org/10.1007/s11432-024-4337-1

12. Elsayed, M., & Erol-Kantarci, M. (2021). AI-enabled future wireless networks: Challenges, opportunities and open issues. arXiv. https://doi.org/10.48550/arXiv.2103.04536

13. Elsayed, M., & Erol-Kantarci, M. (2021). AI-enabled future wireless networks: challenges, opportunities and open issues. https://doi.org/10.48550/arXiv.2103.04536

14. Gomathi, T., Panigrahi, S., Rajendran, N. K., Savita, , & Jadhav, Y. (2025). Edge AI for ultra-reliable low-latency communication (URLLC) in 6G networks.

    National Journal of Antennas and Propagation, 7(1), 5461. https://doi.org/10.31838/NJAP/07.01.09

15. Gomathi, T., Panigrahi, S., Rajendran, N. K., Savita, , & Jadhav, Y. (2025, June 4). Edge I for UltraReliable Low Latency Communication (URLLC) in 6G networks. National Journal of Antennas and Propagation, 7(1), 5461. https://doi.org/10.31838/NJAP/07.01.09

16. Gomathi, T., Panigrahi, S., Rajendran, N. K., Savita, , Kapoor, P., Goyal, S., & Jadhav, Y. (2025, June 4). Edge AI for UltraReliable Low Latency Communication (URLLC) in 6G networks. National Journal of Antennas and Propagation, 7(1), 5461. https://doi.org/10.31838/NJAP/07.01.09

17. ICT Express. (2024). Edge computing in future wireless networks: A comprehensive evaluation and vision for 6G and beyond. ICT Express, 10(5), 11511173. https://doi.org/10.1016/j.icte.2024.08.007

18. Kamath, S., Anand, S., Buchke, S., & Agnihotri, K. (2023, October). A review of recent developments in 6G communications systems. Engineering Proceedings. Presented at the International Conference on Recent Advances in Science and Engineering, Dubai.

19. Letaief, K. B., Chen, W., Shi, Y., Zhang, J., & Zhang, Y.-J. A. (2019). The roadmap to 6GAI empowered wireless networks. arXiv. https://doi.org/10.48550/arXiv.1904.11686

20. Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2021). Edge artificial intelligence for 6G: Vision, enabling technologies, and applications. arXiv. https://doi.org/10.48550/arXiv.2111.12444

21. Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2021). Edge artificial intelligence for 6G: vision, enabling technologies, and applications. https://doi.org/10.48550/arXiv.2111.12444

22. Matin, M. A., Goudos, S. K., & Wan, S. et al. (2023). Artificial intelligence (AI) and machine learning (ML) for beyond 5G/6G communications. EURASIP Journal on Wireless Communications and Networking, 2023, Article 22. https://doi.org/10.1186/s13638-023-02212-z

23. Nielsen, J. J., Liu, R., & Popovski, P. (2017). Ultra-Reliable Low-Latency Communication (URLLC) using interface diversity. arXiv. https://doi.org/10.48550/arXiv.1711.07771

24. Nvidia introduces AI-powered 6G research platform. (2024, March 18). Reuters.

25. Nvidia seeks to advance 6G wireless through AI. (2024, March 18). Barrons.

26. Park, J., Samarakoon, S., Shiri, H., Abdel-Aziz, M. K., Nishio, T., Elgabli, A., & Bennis, M. (2020). Extreme URLLC: Vision, challenges, and key enablers. arXiv. https://doi.org/10.48550/arXiv.2001.09683

27. Salh, A., Audah, L., Abdullah, Q., & Hamzah, S. (2021). Development of a fully data-driven AI and deep learning for URLLC application in 6G wireless systems: A survey. arXiv. https://doi.org/10.48550/arXiv.2108.10076

28. Salh, A., Audah, L., Abdullah, Q., Abdullah, N., Shah, N., Mukred, J., Hamzah, S. (2023). Development of a fully data-driven artificial intelligence and deep learning for URLLC application in 6G wireless systems: A survey. AIP Conference Proceedings, 2564, 080003. https://doi.org/10.1063/5.0122677

29. Scindia, J. (2025, July 12). India aiming to contribute 10% of global 6G patents. The Times of India.

30. Scindia, J., & Budhiraja, R. (2025, July 12). India aiming to contribute 10% of global 6G patents [Press release]. The Times of India

31. Shafie, A., Yang, N., Han, C., Jornet, J. M., Juntti, M., & Kurner, T. (2022). Terahertz communications for 6G and beyond wireless networks: Challenges, key advancements, and opportunities. arXiv. https://doi.org/10.48550/arXiv.2207.11021

32. Shafie, A., Yang, N., Han, C., Jornet, J. M., Juntti, M., & Kurner, T. (2022). Terahertz communications for 6G and beyond wireless networks: Challenges, key advancements, and opportunities.

33. She, C., Sun, C., Gu, Z., Li, Y., Yang, C., Poor, H. V., & Vucetic, B. (2020). A tutorial on URLLC in 6G: Integrating domain knowledge into deep learning.

    arXiv. https://doi.org/10.48550/arXiv.2009.06010

34. Steele, [Author]. (2024). AI/ML-aided capacity maximization strategies for URLLC in 5G/6G systems: A survey. Computer Networks, 249, 110506. https://doi.org/10.1016/j.comnet.2024.110506

35. Steele, [Author]. (2024). AI/ML-aided capacity maximization strategies for URLLC in 5G/6G systems: A survey. Computer Networks, 249, 110506. https://doi.org/10.1016/j.comnet.2024.110506

36. Wen, T., Jianglei, M., Peiying, Z., & Yan, C. (2024, December). 6G and AI: Bridging the physical and digital worlds through connected intelligence. RS-OJICT. https://doi.org/10.46470/03d8ffbd.b810ef97

37. Yang, H., Alphones, A., Xiong, Z., Niyato, D., Zhao, J., & Wu, K. (2019). Artificial intelligence-enabled intelligent 6G networks. arXiv. https://doi.org/10.48550/arXiv.1912.05744

38. Yang, H., Alphones, A., Xiong, Z., Niyato, D., Zhao, J., & Wu, K. (2019). Artificial intelligence-enabled intelligent 6G networks. https://doi.org/10.48550/arXiv.1912.05744

39. Yang, H., Alphones, A., Xiong, Z., Niyato, D., Zhao, J., & Wu, K. (2019, December 12). Artificial intelligence-enabled intelligent 6G networks. arXiv. https://doi.org/10.48550/arXiv.1912.05744