An AI-Driven Deep Reinforcement Learning Using Information Security Approach For Green Computation with Quality of Service Optimization in 6G Network

Adil Fahad

Author(s)

Adil Fahad Faculty of Computing & Information, Department of Computer Science, Al Baha University,Al Baha,Saudi Arabia

Abstract

An escalating energy demand is a critical challenge for future 6G networks due to the increase in data traffic caused by accumulation of connected devices and more complex (data-intensive) applications. Algorithmically, green computation has been desired for 6G deployment because this model is specially focused on the energy footprint of ICT (information & communication technologies) which makes it environmentally sustainable. Hence, in this paper we explore the capability of DRL, a state-of-the-art AI technique, to fine-tune resource allocation and computation, an offloading strategy for green computing within 6G networks that guarantees satisfactory Quality of Service (QoS) for users and also enhance the information security of model. These sources highlight the drawbacks of Classical optimization techniques, which require simple mathematical models that may not be suitable for modelling the dynamic complexities and heterogeneous requirements of 6G network, whereas DRL represents an alternative solution by enabling agents to learn optimal policies when interacting with environment. Specifically, in this paper, we investigate how DRL agents can be used to learn when and where computing offloading processes should happen or not on both the MEC servers (computation) as well as network configurations dynamically under stochastic traffic patterns and wireless channel conditions for energy management purpose by considering QoS constraints such that latency time bound of 10 m/s is satisfied with a probability higher than 95%. The paper will also leverage examples from the sources DRL applications in systems such as AI enabled Base station (BS) management where intelligent BS activation/deactivation strategy can be done which shall keep energy consumption on low during low-traffic periods. It will also investigate the application of DRL to flexibly optimize energy harvesting, security of model and trading for machine-type communications (MTC), a major power-limited scenario in 6G. The paper will also discuss the issues in practicing DRL, including resource-intensive experiences of training elaborate deep reinforcement learning models and reward model efficiency optimization that balances both energy conservation and QoS satisfaction. We further discuss how to address these challenges in order for DRL and other AI models to truly realize their potential as green computation strategies, when it comes down as a final solution at operating 6G network scales.

Publication Details

Page(s) 694-716

DOI DOI not available

Published Journal: International Journal of Communication Networks and Information Security, Volume: 16, Issue: S1, Year: 2024

Request the full text from PASTIC

Keywords

optimization, Techniques, Networks, information security, Quality of Service, computation, communications, driven

References

Guo H.,Li J.,Liu J.,Tian N.,Kato N. . .A survey on space-air- ground-sea integrated network security in 6G,” IEEE Commun. [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12], 24 : 53-87.

Mao B.,Tang F.,Kawamoto Y.,Kato N. .2022 .AI models for green communications towards 6G,” IEEE Commun. , 24 : 210-247.

K. B. Letaief W.,Chen Y.,Shi J.,Zhang Y.-J. A.,Zhang Y.-J. A. .2019 .The roadmap to 6G: AI empowered wireless networks. ” IEEE Commun. Mag., 57 : 84-90.

IMT-2030 (6G) Promotion Group . .6G vision and candidate technologies. , : .

. .. , : .

Tataria H.,Shafi M.,Molisch A. F.,Dohler M. . .. ” Proc. IEEE, : .

.2021 .. , : 1166-1199.

Shi Y.,Yang K.,Jiang T.,Zhang J.,K. B. Letaief J.,edge AI .2020 .Algorithms and systems. , 22 : 2167-2191.

Feng Z.,Wei Z.,Chen X.,Yang H.,Zhang Q. .2021 .Joint communication, sensing, and computation enabled 6G intelligent machine system. ” IEEE Netw., 35 : 34-42.

K. B. Letaief Y.,Shi J.,Lu J.,Lu J.,Select J. . .Edge artificial intelligence for 6g: Vision, enabling technologies, and applications. , 40 : 5-36.

Beck E.,Bockelmann C.,Dekorsy A. .2022 .Semantic communication: An information bottleneck view. ” arXiv preprint arXiv:2204.13366, : .

Li B.,Yang L.-L.,Maunder R.,Sun S.,Xiao P. .2022 .Heteroge- neous graph neural network for power allocation in multicarrier- division duplex cell-free massive mimo systems. ” arXiv preprint arXiv:2205.00546, : .

Khani M.,Alizadeh M.,Hoydis J.,Fleming P. .2020 .Adaptive neural signal detection for massive mimo. ” IEEE Trans. Wireless Commun., 19(8) : 5635-5648.

Wan L.,Liu K. .2022 .Deep learning-aided off-grid channel estimation for millimeter wave cellular systems. ” IEEE Trans. Wireless Commun., 21 : 3333-3348.

Fang W.,Jiang Y.,Shi Y.,Zhou Y.,Chen W.,K. B. Letaief W. .2021 .Over- the-air computation via reconfigurable intelligent surface,”. IEEE Trans. Commun., 69 : 8612-8626.

Shi Y.,Choi H.,Shi Y.,Zhou Y. . .Algorithm unrolling for massive access via deep neural networks with theoretical guarantee,”. IEEE Trans. Wireless Commun., 21 : .

.2022 .. , : 959.

Shen Y.,Shi Y.,Zhang J.,K. B. Letaief J. .2020 .Learning to optimize for resource management in wireless networks with few training samples,”. IEEE Trans. Wireless Commun., 19 : 665-679.

Yu W.,Sohrabi F. .2022 .Role of deep learning in wireless communications. , : .

Amos B. .2022 .Tutorial on amortized optimization for learning to optimize over continuous domains. ” arXiv preprint arXiv:2202.00665, : .

Shlezinger N.,Eldar Y. C.,Boyd S. P. .2022 .Model-based deep learning: On the intersection of deep learning and optimization. ” arXiv preprint arXiv:2205.02640, : .

He H.,C.-K. Wen S.,Jin G. Y.,Li G. Y. .2020 .Model-driven deep learning for mimo detection. ” IEEE Trans. Signal Process., 68 : 1702-1715.

Wei X.,Hu C.,Dai L. .2021 .Deep learning for beamspace channel estimation in millimeter-wave massive mimo systems. ” IEEE Trans. Commun., 69 : 182-193.

Commun Wireless .2021 .. , 20 : 1394-1410.

Shen Y.,Shi Y.,Zhang J.,K. B. Letaief J. .2021 .Graph neural networks for scalable radio resource management: Architecture design and theoretical analysis. ” IEEE J. Sel. Areas Commun, 39 : 101-115.

Khan A.,Zhang C.,Lee D. D.,Kumar V.,Ribeiro A. .2018 .Scalable centralized deep multi-agent reinforcement learning via policy gradi- ents. , : .

Zhang J.,He Y.,Li Y.-W.,Jin S. . .Meta learning- based mimo detectors: Design, simulation, and experimental test. ” IEEE Trans. Wireless Commun., 20 : .

.2020 .. , : 1137.

Sun H.,Pu W.,Fu X.,Chang T.-H.,Hong M. .2022 .Learning to continuously optimize wireless resource in a dynamic environment: A bilevel optimization perspective,”. IEEE Trans. on Signal Process., 70 : 1900-1917.

Wang Z.,Zong J.,Zhou Y.,Shi Y.,Wong V. W. S. . .Decentralized multi-agent power control in wireless networks with frequency reuse,”. IEEE Trans. Commun., 70 : .

.2022 .. , : 1681.

Shi G.,Xiao Y.,Li Y.,Xie and X. . .From semantic communication to semantic-aware networking: Model, architecture. , 59 : .

.2021 .. , : 50.

A. M. Elbir A. K.,Papazafeiropoulos S.,Chatzinotas S. .2021 .Federated learning for physical layer design,” IEEE Commun. , 59 : 81-87.

Soltani M.,Pourahmadi V.,Mirzaei A.,Sheikhzadeh H. .2019 .Deep learning-based channel estimation,” IEEE Commun. Lett., 23 : 652-655.

Haykin S.,Network N. . .A comprehensive foundation,” Neural Netw. , 2 : .

.2004 .. , : 41.

Ye H.,Li G. Y.,Juang B. F. .2019 .Deep reinforcement learning based resource allocation for V2V communications,”. IEEE Trans. Veh, 68(4) : 3163-3173.

Samuel N.,Diskin T.,Wiesel A. .2019 .and. IEEE Trans. Signal Process., 67(10) : 2554-2564.

Shen Y.,Zhang J.,Song S. H.,K. B. Letaief S. H. .2022 .Graph neural networks for wireless communications: From theory to practice,” ArXiv. abs/2203.10800, : .

Xie H.,Qin Z.,Li G. Y.,Juang B.-H. .2021 .Deep learning enabled se- mantic communication systems. ” IEEE Trans. Signal Process., 69 : 2663-2675.

Monga V.,Li Y.,Eldar Y. C. .2021 .Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing,” IEEE Signal Process. , 38 : 18-44.

Tong W.,Li G. Y.,Access Early .2022 .Nine challenges in artificial intelligence and wireless communications for 6g,” IEEE Wireless Commun. , : 1-10.

Chen M.,Challita U.,Saad W.,Yin C.,Debbah M. .2017 .Machine learning for wireless networks with artificial intelligence: A tutorial on neural networks. ” arXiv preprint arXiv:1710.02913, 9 : .

Zappone A.,Renzo M. Di,Debbah M. . .Wireless networks design in the era of deep learning: Model-based, AI-based, or both?,”. IEEE Trans. Commun., 67(10) : .

Zhang C.,Haddadi H. .2019 .Deep learning in mobile and wireless networking: A survey,” IEEE Commun. , 21 : 2224-2287.

Mao Q.,Hu F.,Hao Q. .2018 .Deep learning for intelligent wireless networks: A comprehensive survey. ” IEEE Commun. Surveys Tuts., 20 : 2595-2621.

.2019 .. , : 3072-3108.

Conf. Mach. Learn. ,Haifa Israel .2010 .. , : 399-406.

Borgerding M.,Schniter P.,Rangan S. . .AMP-inspired deep networks for sparse linear inverse problems,”. IEEE Trans. Signal Process., 65 : 4293-4308.

Chen T.,Chen X.,Chen W.,Heaton H.,Liu J.,Wang Z.,Yin W. .2021 .Learning to optimize: A primer and. ” arXiv preprint arXiv:2103.12828, : .

Yang Y.,Sun J.,Li H.,Xu Z. .2018 .ADMM-CSNet: A deep learning approach for image compressive sensing,” IEEE trans. on patt. analysis and machine intell. , 42 : 521-538.

Li Y.,Tofighi M.,Monga V.,Eldar Y. C. .2019 .An algorithm unrolling approach to deep image deblurring,”. in Proc. IEEE Int. Conf. Acoustic, Speech and Sig. Proc. (ICASSP), : .

Chen Y.,Pock T. .2016 .Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration,” IEEE trans. on patt. analysis and machine intell. , 39 : 1256-1272.

.2021 .. , : 8214-8227.

Yassine T.,Le L.,Magoarou L. .2022 .mpNet: variable depth unfolded neural network for massive mimo channel estimation,”. IEEE Trans. Wireless Commun., 21 : 5703-5714.

Mao Z.,Liu X.,Peng M.,Chen Z. .2022 .Joint channel estimation and active-user detection for massive access in internet of things-a deep learning approach. vol. 9, : 2870-2881.