{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:45:24Z","timestamp":1760147124876,"version":"build-2065373602"},"reference-count":53,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Advances in machine learning have widened the range of its applications in many fields. In particular, deep learning has attracted much interest for its ability to provide solutions where the derivation of a rigorous mathematical model of the problem is troublesome. Our interest was drawn to the application of deep learning for channel state information feedback reporting, a crucial problem in frequency division duplexing (FDD) 5G networks, where knowledge of the channel characteristics is fundamental to exploiting the full potential of multiple-input multiple-output (MIMO) systems. We designed a framework adopting a 5G New Radio convolutional neural network, called NR-CsiNet, with the aim of compressing the channel matrix experienced by the user at the receiver side and then reconstructing it at the transmitter side. In contrast to similar solutions, our framework is based on a 5G New Radio fully compliant simulator, thus implementing a channel generator based on the latest 3GPP 3-D channel model. Moreover, realistic 5G scenarios are considered by including multi-receiving antenna schemes and noisy downlink channel estimation. Simulations were carried out to analyze and compare the performance with current feedback reporting schemes, showing promising results for this approach from the point of view of the block error rate and throughput of the 5G data channel.<\/jats:p>","DOI":"10.3390\/s23020910","type":"journal-article","created":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T02:57:33Z","timestamp":1673578653000},"page":"910","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Implementation of Deep-Learning-Based CSI Feedback Reporting on 5G NR-Compliant Link-Level Simulator"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7714-9191","authenticated-orcid":false,"given":"Daniel","family":"Riviello","sequence":"first","affiliation":[{"name":"Department of Electrical, Electronic, and Information Engineering, University of Bologna, 40136 Bologna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Riccardo","family":"Tuninato","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunications (DET), Politecnico di Torino, 10129 Torino, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisa","family":"Zimaglia","sequence":"additional","affiliation":[{"name":"TIM S.p.A., 10148 Torino, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Fantini","sequence":"additional","affiliation":[{"name":"TIM S.p.A., 10148 Torino, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0292-4648","authenticated-orcid":false,"given":"Roberto","family":"Garello","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunications (DET), Politecnico di Torino, 10129 Torino, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/MWC.2016.1500356WC","article-title":"Machine Learning Paradigms for Next-Generation Wireless Networks","volume":"24","author":"Jiang","year":"2017","journal-title":"IEEE Wirel. Commun."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/SURV.2012.100412.00017","article-title":"A Survey on Machine-Learning Techniques in Cognitive Radios","volume":"15","author":"Bkassiny","year":"2013","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Sharma, V., and Bohara, V. (2014, January 24\u201327). Exploiting machine learning algorithms for cognitive radio. Proceedings of the 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Delhi, India.","DOI":"10.1109\/ICACCI.2014.6968571"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Murudkar, C.V., and Gitlin, R.D. (2019, January 8\u20139). Optimal-Capacity, Shortest Path Routing in Self-Organizing 5G Networks using Machine Learning. Proceedings of the 2019 IEEE 20th Wireless and Microwave Technology Conference (WAMICON), Cocoa Beach, FL, USA.","DOI":"10.1109\/WAMICON.2019.8765434"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"6792","DOI":"10.1109\/ACCESS.2020.2964697","article-title":"5G Vehicular Network Resource Management for Improving Radio Access Through Machine Learning","volume":"8","author":"Khattak","year":"2020","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1109\/COMST.2020.2964534","article-title":"Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges","volume":"22","author":"Hussain","year":"2020","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/CC.2017.8233654","article-title":"Deep learning for wireless physical layer: Opportunities and challenges","volume":"14","author":"Wang","year":"2017","journal-title":"China Commun."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"67366","DOI":"10.1109\/ACCESS.2020.2986330","article-title":"Deep Learning for Modulation Recognition: A Survey With a Demonstration","volume":"8","author":"Zhou","year":"2020","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, M., Zeng, Y., Han, Z., and Gong, Y. (2018, January 25\u201328). Automatic Modulation Recognition Using Deep Learning Architectures. Proceedings of the 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Kalamata, Greece.","DOI":"10.1109\/SPAWC.2018.8446021"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TCCN.2018.2835460","article-title":"Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors","volume":"4","author":"Rajendran","year":"2018","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1109\/MWC.2019.1900027","article-title":"Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions","volume":"27","author":"Huang","year":"2020","journal-title":"IEEE Wirel. Commun."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1109\/LWC.2018.2818160","article-title":"Deep Learning for Massive MIMO CSI Feedback","volume":"7","author":"Wen","year":"2018","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1109\/LWC.2018.2874264","article-title":"Deep Learning-Based CSI Feedback Approach for Time-Varying Massive MIMO Channels","volume":"8","author":"Wang","year":"2019","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"8440","DOI":"10.1109\/TVT.2018.2848294","article-title":"Deep Learning for an Effective Nonorthogonal Multiple Access Scheme","volume":"67","author":"Gui","year":"2018","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3027","DOI":"10.1109\/TVT.2019.2893928","article-title":"Deep-Learning-Based Millimeter-Wave Massive MIMO for Hybrid Precoding","volume":"68","author":"Huang","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1109\/TCCN.2017.2758370","article-title":"An Introduction to Deep Learning for the Physical Layer","volume":"3","author":"Hoydis","year":"2017","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1109\/LWC.2017.2757490","article-title":"Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems","volume":"7","author":"Ye","year":"2018","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/LCOMM.2019.2898944","article-title":"Deep Learning-Based Channel Estimation","volume":"23","author":"Soltani","year":"2019","journal-title":"IEEE Commun. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1109\/LWC.2021.3134826","article-title":"Low-Complexity Downlink Channel Estimation in mmWave Multiple-Input Single-Output Systems","volume":"11","author":"Fascista","year":"2022","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kebede, T., Wondie, Y., and Steinbrunn, J. (November, January 31). Channel Estimation and Beamforming Techniques for mm Wave-Massive MIMO: Recent Trends, Challenges and Open Issues. Proceedings of the 2021 International Symposium on Networks, Computers and Communications (ISNCC), Dubai, United Arab Emirates.","DOI":"10.1109\/ISNCC52172.2021.9615760"},{"key":"ref_21","unstructured":"Dahlman, E., Parkvall, S., and Skold, J. (2018). 5G NR: The Next Generation Wireless Access Technology, Elsevier Science."},{"key":"ref_22","unstructured":"3GPP (2018). Study on Channel Model for Frequencies from 0.5 to 100 GHz, 3rd Generation Partnership Project (3GPP). Version 14.3.0; Technical Report (TR) 38.901."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Riviello, D.G., Di Stasio, F., and Tuninato, R. (2022). Performance Analysis of Multi-User MIMO Schemes under Realistic 3GPP 3-D Channel Model for 5G mmWave Cellular Networks. Electronics, 11.","DOI":"10.3390\/electronics11030330"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4206","DOI":"10.1109\/TWC.2018.2821667","article-title":"Channel Estimation for TDD\/FDD Massive MIMO Systems With Channel Covariance Computing","volume":"17","author":"Xie","year":"2018","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3161","DOI":"10.1109\/TWC.2019.2911497","article-title":"Efficient Downlink Channel Reconstruction for FDD Multi-Antenna Systems","volume":"18","author":"Han","year":"2019","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2624","DOI":"10.1109\/LCOMM.2021.3076504","article-title":"Lightweight Convolutional Neural Networks for CSI Feedback in Massive MIMO","volume":"25","author":"Cao","year":"2021","journal-title":"IEEE Commun. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"7295","DOI":"10.1109\/ACCESS.2020.2963896","article-title":"A Novel CSI Feedback Approach for Massive MIMO Using LSTM-Attention CNN","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.1109\/LWC.2021.3057934","article-title":"ChannelAttention: Utilizing Attention Layers for Accurate Massive MIMO Channel Feedback","volume":"10","author":"Ji","year":"2021","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1305","DOI":"10.1109\/LWC.2021.3064963","article-title":"Binary Neural Network Aided CSI Feedback in Massive MIMO System","volume":"10","author":"Lu","year":"2021","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1109\/JSAC.2020.3041397","article-title":"Deep Learning-Based CSI Feedback for Beamforming in Single- and Multi-Cell Massive MIMO Systems","volume":"39","author":"Guo","year":"2021","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"4761","DOI":"10.1109\/TCOMM.2020.2993626","article-title":"An Efficient Deep Learning Framework for Low Rate Massive MIMO CSI Reporting","volume":"68","author":"Liu","year":"2020","journal-title":"IEEE Trans. Commun."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zimaglia, E., Riviello, D.G., Garello, R., and Fantini, R. (2020, January 1\u20132). A Novel Deep Learning Approach to CSI Feedback Reporting for NR 5G Cellular Systems. Proceedings of the 2020 IEEE Microwave Theory and Techniques in Wireless Communications (MTTW), Riga, Latvia.","DOI":"10.1109\/MTTW51045.2020.9245055"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ahmadi, S. (2019). 5G NR: Architecture, Technology, Implementation, and Operation of 3GPP New Radio Standards, Elsevier Science.","DOI":"10.1016\/B978-0-08-102267-2.00001-4"},{"key":"ref_34","unstructured":"3GPP (2009). Evolved Universal Terrestrial Radio Access (E-UTRA); Physical Channels and Modulation (Release 8), 3rd Generation Partnership Project (3GPP). Version 8.9.0; Technical Specification (TS) 36.211."},{"key":"ref_35","unstructured":"3GPP (2013). Evolved Universal Terrestrial Radio Access (E-UTRA); Physical Channels and Modulation (Release 10), 3rd Generation Partnership Project (3GPP). Version 10.7.0; Technical Specification (TS) 36.211."},{"key":"ref_36","unstructured":"3GPP (2010). Evolved Universal Terrestrial Radio Access (E-UTRA); Further Advancements for E-UTRA Physical Layer Aspects (Release 9), 3rd Generation Partnership Project (3GPP). Version 9.0.0; Technical Specification (TS) 36.814."},{"key":"ref_37","unstructured":"3GPP (2020). NR; Physical Layer Procedures for Data (Release 15), 3rd Generation Partnership Project (3GPP). Version 15.9.0; Technical Specification (TS) 38.214."},{"key":"ref_38","unstructured":"Roy, R.H. (1997, January 4\u20137). Spatial division multiple access technology and its application to wireless communication systems. Proceedings of the 1997 IEEE 47th Vehicular Technology Conference. Technology in Motion, Phoenix, AZ, USA."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1109\/MCOM.2012.6146493","article-title":"Downlink MIMO in LTE-advanced: SU-MIMO vs. MU-MIMO","volume":"50","author":"Liu","year":"2012","journal-title":"IEEE Commun. Mag."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1109\/MCOM.2004.1341262","article-title":"An introduction to the multi-user MIMO downlink","volume":"42","author":"Spencer","year":"2004","journal-title":"IEEE Commun. Mag."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2240","DOI":"10.1109\/TCOMM.2021.3049399","article-title":"Achievable DoF Regions of Three-User MIMO Broadcast Channel With Delayed CSIT","volume":"69","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Commun."},{"key":"ref_42","unstructured":"3GPP (2019). NR; Physical Channels and Modulation, 3rd Generation Partnership Project (3GPP). Version 15.6.0; Technical Specification (TS) 38.211."},{"key":"ref_43","unstructured":"3GPP (2019). NR; Multiplexing and Channel Coding, 3rd Generation Partnership Project (3GPP). Version 15.6.0; Technical Specification (TS) 38.212."},{"key":"ref_44","unstructured":"3GPP (2019). NR; Physical Layer Procedures for Control, 3rd Generation Partnership Project (3GPP). Version 15.6.0; Technical Specification (TS) 38.213."},{"key":"ref_45","unstructured":"3GPP (2020). Radio Resource Control (RRC); Protocol Specification, 3rd Generation Partnership Project (3GPP). Version 16.1.0; Technical Report (TR) 38.331."},{"key":"ref_46","unstructured":"3GPP (2018). User Equipment (UE) Radio Access Capabilities, 3rd Generation Partnership Project (3GPP). Version 15.3.0; Technical Report (TR) 38.306."},{"key":"ref_47","unstructured":"3GPP (2018). NR; Study on Test Methods, 3rd Generation Partnership Project (3GPP). Version 2.4.0; Technical Report (TR) 38.810."},{"key":"ref_48","unstructured":"(2023, January 05). Tensorflow Keras Module. Available online: https:\/\/www.tensorflow.org\/api_docs\/python\/tf\/keras."},{"key":"ref_49","unstructured":"(2023, January 05). ReLU Keras API. Available online: https:\/\/keras.io\/api\/layers\/activation_layers\/relu\/."},{"key":"ref_50","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning (Adaptive Computation and Machine Learning), MIT Press."},{"key":"ref_51","unstructured":"(2023, January 05). Batch Normalization Keras API. Available online: https:\/\/keras.io\/api\/layers\/normalization_layers\/batch_normalization\/."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_53","unstructured":"(2023, January 05). Softmax Keras API. Available online: https:\/\/keras.io\/api\/layers\/activation_layers\/softmax\/."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/910\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:04:40Z","timestamp":1760119480000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/2\/910"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,12]]},"references-count":53,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["s23020910"],"URL":"https:\/\/doi.org\/10.3390\/s23020910","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2023,1,12]]}}}