{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T17:18:06Z","timestamp":1767633486988,"version":"3.48.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Manipal University Jaipur"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Netw Distrib Comput"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s44227-025-00081-0","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T14:35:03Z","timestamp":1767018903000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["2DRL: Cognitive D2D Control Under Imperfect CSI Via Adaptive Deep Reinforcement Learning"],"prefix":"10.1007","volume":"14","author":[{"given":"Panduranga Ravi","family":"Teja","sequence":"first","affiliation":[]},{"given":"Krati","family":"Dubey","sequence":"additional","affiliation":[]},{"given":"Rishav","family":"Dubey","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,29]]},"reference":[{"unstructured":"Chen X et al. (2019) Energy-efficient resource management in D2D-assisted 5G networks: a game-theoretic approach. Ad Hoc Networks 89:101\u2013115","key":"81_CR1"},{"doi-asserted-by":"crossref","unstructured":"Nuanyai K, Tarbut P, Chantaraskul S (2025) Cell-edge user satisfaction-based dynamic CoMP clustering with load awareness in ultra-dense networks. Int J Networked And Distrib Comput 13(1):6","key":"81_CR2","DOI":"10.1007\/s44227-024-00042-z"},{"unstructured":"Liu Z et al. (2020) Multi-agent deep reinforcement learning for scalable resource allocation in D2D-based V2V communications. Ad Hoc Networks 99, Art. 102067)","key":"81_CR3"},{"doi-asserted-by":"crossref","unstructured":"Chantaraskul S, Tarbut P, Nuanyai K (2023) Load-aware greedy dynamic CoMP clustering mechanism for DPS CoMP in 5G networks. Int J Networked And Distrib Comput 11(1):31\u201348","key":"81_CR4","DOI":"10.1007\/s44227-023-00008-7"},{"doi-asserted-by":"crossref","unstructured":"Chowdhury M (2024) Kaizen: a street smart low latency-aware resource choreography scheme for decentralized autonomous organization (DAO) and non-DAO based application execution over blockchain and MEC empowered 6 G network. Int J Networked And Distrib Comput 12(2):277\u2013305","key":"81_CR5","DOI":"10.1007\/s44227-024-00033-0"},{"unstructured":"Sun Y et al. (2019) Adaptive mode selection and resource allocation for D2D communications using matching theory. Ad Hoc Networks 84:1\u201312","key":"81_CR6"},{"doi-asserted-by":"crossref","unstructured":"Abuthahir SS, Peter JSP (2024) A combined marine predators and particle swarm optimization for task offloading in vehicular edge computing network. Int J Networked And Distrib Comput 12(2):265\u2013276","key":"81_CR7","DOI":"10.1007\/s44227-024-00034-z"},{"unstructured":"Zhang Q et al. (2020) Deep reinforcement learning for resource allocation in D2D underlay networks with imperfect CSI. Ad Hoc Networks 102, Art. 102138)","key":"81_CR8"},{"doi-asserted-by":"crossref","unstructured":"Shirsath VA, Chandane MM (2025) Beyond the basics: an in-depth analysis and multidimensional survey of programmable switch in software-defined networking. Int J Networked And Distrib Comput 13(1):8","key":"81_CR9","DOI":"10.1007\/s44227-024-00049-6"},{"unstructured":"Wang S et al. (2019) Energy-efficient resource allocation for D2D communications using deep reinforcement learning. Ad Hoc Networks 93, Art. 101903)","key":"81_CR10"},{"doi-asserted-by":"crossref","unstructured":"Vishnoi V, Budhiraja I, Gupta S, Kumar N (2023 Oct) A deep reinforcement learning scheme for sum rate and fairness maximization among D2D pairs underlaying cellular network with NOMA. IEEE Trans Veh Technol 72(10):13506\u201313522","key":"81_CR11","DOI":"10.1109\/TVT.2023.3276647"},{"issue":"7","key":"81_CR12","first-page":"4982","volume":"19","author":"Z Li","year":"2020","unstructured":"Li Z, Guo C (2020 Jul) Multi-agent deep reinforcement learning based spectrum allocation for D2D underlay communications. IEEE Trans Wirel Commun 19(7):4982\u20134994. [Originally arXiv:1912.03447, 2019","journal-title":"IEEE Trans Wirel Commun"},{"issue":"2","key":"81_CR13","first-page":"574","volume":"6","author":"Z Li","year":"2020","unstructured":"Li Z, Guo C, Xuan Y (2020 Jun) Neighbor-agent actor critic framework for D2D spectrum allocation. IEEE Trans Cogn Commun Netw 6(2):574\u2013588. [Originally arXiv:1904.11457, 2019","journal-title":"IEEE Trans Cogn Commun Netw"},{"key":"81_CR14","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1007\/s12083-021-01265-5","volume":"15","author":"V Hakami","year":"2022","unstructured":"Hakami V, Barghi H, Mostafavi S, Arefinezhad Z (2022) A resource allocation scheme for D2D communications with unknown channel state information. Peer-To-Peer Netw Appl 15:1189\u20131213","journal-title":"Peer-To-Peer Netw Appl"},{"doi-asserted-by":"crossref","unstructured":"Xu J, Yang D (2024 Sep) Energy-efficient resource allocation for D2D communication underlaying cellular networks with incomplete CSI. Comput Netw 251, Art. no. 110664)","key":"81_CR15","DOI":"10.1016\/j.comnet.2024.110664"},{"issue":"4","key":"81_CR16","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MNET.2019.1800461","volume":"33","author":"Y Liu","year":"2019","unstructured":"Liu Y et al. (2019 Jul) Deep learning for ultra-reliable low-latency communications. IEEE Netw 33(4):82\u201389","journal-title":"IEEE Netw"},{"issue":"6","key":"81_CR17","first-page":"3834","volume":"20","author":"G Zhou","year":"2021","unstructured":"Zhou G, Pan C, Ren H, Wang K, Nallanathan A (2021 Jun) Robust resource allocation for D2D communications. IEEE Trans Wirel Commun 20(6):3834\u20133847","journal-title":"IEEE Trans Wirel Commun"},{"doi-asserted-by":"crossref","unstructured":"Li X, Ma L, Xu Y, Shankaran R (2020) Resource allocation for D2D-based V2X communication with imperfect CSI. IEEE Internet Things J, Early Access, Feb","key":"81_CR18","DOI":"10.1109\/JIOT.2020.2973267"},{"doi-asserted-by":"crossref","unstructured":", 2022) Deep reinforcement learning based resource allocation for D2D communications underlaying cellular networks. Sensors 22(23, Art. 9459)","key":"81_CR19","DOI":"10.3390\/s22239459"},{"doi-asserted-by":"crossref","unstructured":"Li X, Chen G, Wu G, Sun Z, Chen G (2023) Research on multi-agent D2D communication resource allocation algorithm based on A2C. Electronics 12(2, Art. 360)","key":"81_CR20","DOI":"10.3390\/electronics12020360"},{"issue":"1","key":"81_CR21","first-page":"550","volume":"70","author":"KK Nguyen","year":"2022","unstructured":"Nguyen KK et al. (2022 Jan) Deep reinforcement learning for intelligent reflecting surface-assisted D2D communications. IEEE Trans Commun 70(1):550\u2013565. [Originally arXiv:2108.12737, 2021","journal-title":"IEEE Trans Commun"},{"issue":"9","key":"81_CR22","doi-asserted-by":"crossref","first-page":"5678","DOI":"10.1109\/TWC.2020.2999667","volume":"19","author":"K Wang","year":"2020","unstructured":"Wang K et al. (2020 Sep) PrecoderNet: hybrid beamforming for mmWave systems with imperfect CSI. IEEE Trans Wirel Commun 19(9):5678\u20135692. [Originally arXiv:1907.09313, 2019","journal-title":"IEEE Trans Wirel Commun"},{"issue":"5","key":"81_CR23","first-page":"1","volume":"44","author":"M Eskandari","year":"2022","unstructured":"Eskandari M, Zhu H, Shojaeifard A, Wang J (2022) Statistical CSI-Based beamforming via deep reinforcement learning for RIS-Aided multiuser miso systems. J Electron Inf Technol 44(5):1\u201312","journal-title":"J Electron Inf Technol"},{"issue":"8","key":"81_CR24","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/JSAC.2008.081002","volume":"26","author":"DJ Love","year":"2008","unstructured":"Love DJ, Heath RW, Lau VKN, Gesbert D, Rao BD, Andrews M (2008 Oct) An overview of limited feedback in wireless communication systems. IEEE J Sel Areas Commun 26(8):1341\u20131365. [Corrected from 2005 reference","journal-title":"IEEE J Sel Areas Commun"},{"issue":"9","key":"81_CR25","doi-asserted-by":"publisher","first-page":"1996","DOI":"10.1109\/JSAC.2017.2720856","volume":"35","author":"J Choi","year":"2017","unstructured":"Choi J, Love DJ, Bidigare P (2017 Sep) Channel estimation for hybrid architecture-based wideband millimeter wave systems. IEEE J Sel Areas Commun 35(9):1996\u20132009","journal-title":"IEEE J Sel Areas Commun"},{"unstructured":"Schulman J et al. (2017) Proximal policy optimization algorithms. arXiv: 1707.06347","key":"81_CR26"},{"unstructured":"Schulman J et al. (2016) High-dimensional continuous control using generalized advantage estimation. In Proc. ICLR. [Originally arXiv:1506.02438, 2015","key":"81_CR27"},{"unstructured":"Jang E, Gu S, Poole B (2017) Categorical reparameterization with Gumbel-Softmax. In Proc. ICLR. [Originally arXiv:1611.01144, 2016","key":"81_CR28"},{"key":"81_CR29","first-page":"1","volume":"ICML","author":"RP Adams","year":"2011","unstructured":"Adams RP, Ghahramani Z, Jordan MI (2011) Tractable nonparametric bayesian inference. Proc ICML:1\u20138","journal-title":"Proc"},{"unstructured":"Molisch AF (2012) Wireless communications, 2nd edn. Wiley-IEEE Press","key":"81_CR30"},{"issue":"2","key":"81_CR31","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1109\/MCOM.2014.6736752","volume":"52","author":"C-X Wang","year":"2014","unstructured":"Wang C-X et al. (2014 Feb) Cellular architecture and key technologies for 5G wireless communication networks. IEEE Commun Mag 52(2):122\u2013130","journal-title":"IEEE Commun Mag"},{"doi-asserted-by":"crossref","unstructured":"Qi Y, Geng S (2023) Deep-reinforcement-learning-based resource allocation for energy harvesting D2D communication. In Proc. Int. Conf. Electron., Commun. Artif. Intell., Paper 10176743","key":"81_CR32","DOI":"10.1109\/ICECAI58670.2023.10176743"},{"unstructured":"He Y, Lin J, Liu Z, Wang H, Li L-J, Han S (2020) AMC: AutoML for Model compression and acceleration on Mobile devices. Proc. ECCV 784\u2013800","key":"81_CR33"},{"issue":"1","key":"81_CR34","first-page":"401","volume":"19","author":"L Fern\u00e1ndez","year":"2020","unstructured":"Fern\u00e1ndez L et al. (2020 Jan) Pilot contamination in massive MIMO systems. IEEE Trans Wirel Commun 19(1):401\u2013415","journal-title":"IEEE Trans Wirel Commun"},{"key":"81_CR35","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1109\/ACCESS.2013.2260813","volume":"1","author":"TS Rappaport","year":"2013","unstructured":"Rappaport TS et al. (2013 May) Millimeter wave mobile communications for 5G cellular. IEEE Access 1:335\u2013349","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Guo L, Jia J, Chen J, Du A, Wang X (2023) Deep reinforcement learning empowered joint mode selection and resource allocation for RIS-aided D2D communications. Neural Comput Appl 35:18231\u201318249","key":"81_CR36","DOI":"10.1007\/s00521-023-08745-0"},{"unstructured":"EAI (2023) 5G; nr; physical layer procedures for data. Ts 138 314, v17(4.0)","key":"81_CR37"},{"unstructured":"Jang E et al. (2016) Categorical reparameterization with Gumbel-Softmax. arXiv: 1611.01144","key":"81_CR38"},{"unstructured":"GPP (2022 Mar) Study on channel model for frequencies from 0.5 to 100 GHz (release 17). 3gpp Tr 38(901, v17.0.0","key":"81_CR39"},{"unstructured":"GPP (2024 Jan) Nr; physical channels and modulation (release 18). 3gpp Ts 38(211, v18.1.0","key":"81_CR40"},{"unstructured":"Gupta AK, Jha RK, Brik SV (2021) 5G-NR module for NS-3: overview and extension to millimeter wave. IEEE Access 9:104459\u2013104476","key":"81_CR41"},{"unstructured":"GPP (2022) Study on channel model for frequencies from 0.5 to 100 GHz. TR 38(901, v17.0.0","key":"81_CR42"},{"unstructured":"Liu Y et al. (2019) Deep learning for ultra-reliable low-latency communications. IEEE Network 33(4):82\u201389","key":"81_CR43"},{"doi-asserted-by":"crossref","unstructured":"Zhou G et al. (2021) Robust resource allocation for D2D communications. IEEE Trans Wireless Commun 20(6):3834\u20133847","key":"81_CR44","DOI":"10.1109\/TWC.2021.3053354"},{"doi-asserted-by":"crossref","unstructured":"Li Z, Guo C (2019) Multi-agent deep reinforcement learning based spectrum allocation for D2D underlay communications. arXiv: 1912.03447","key":"81_CR45","DOI":"10.1109\/GLOBECOM38437.2019.9013763"},{"doi-asserted-by":"crossref","unstructured":"Ye Z, Li G (2018 May) Deep reinforcement learning for resource allocation in V2V communications. In Proc. IEEE ICC","key":"81_CR46","DOI":"10.1109\/ICC.2018.8422586"}],"container-title":["International Journal of Networked and Distributed Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44227-025-00081-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44227-025-00081-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44227-025-00081-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T12:52:21Z","timestamp":1767617541000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44227-025-00081-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,29]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["81"],"URL":"https:\/\/doi.org\/10.1007\/s44227-025-00081-0","relation":{},"ISSN":["2211-7938","2211-7946"],"issn-type":[{"type":"print","value":"2211-7938"},{"type":"electronic","value":"2211-7946"}],"subject":[],"published":{"date-parts":[[2025,12,29]]},"assertion":[{"value":"4 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Consent for Publication","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"The authors declare that they have no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"6"}}