{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T07:23:21Z","timestamp":1780730601798,"version":"3.54.1"},"reference-count":49,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["TED2021-129938B-I00"],"award-info":[{"award-number":["TED2021-129938B-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Reconfigurable intelligent surfaces (RIS) offer the potential to customize the radio propagation environment for wireless networks, and will be a key element for 6G communications. However, due to the unique constraints in these systems, the optimization problems associated to RIS configuration are challenging to solve. This paper illustrates a new approach to the RIS configuration problem, based on the use of artificial intelligence (AI) and deep learning (DL) algorithms. Concretely, a custom convolutional neural network (CNN) intended for edge computing is presented, and implementations on different representative edge devices are compared, including the use of commercial AI-oriented devices and a field-programmable gate array (FPGA) platform. This FPGA option provides the best performance, with \u00d720 performance increase over the closest FP32, GPU-accelerated option, and almost \u00d73 performance advantage when compared with the INT8-quantized, TPU-accelerated implementation. More noticeably, this is achieved even when high-level synthesis (HLS) tools are used and no custom accelerators are developed. At the same time, the inherent reconfigurability of FPGAs opens a new field for their use as enabler hardware in RIS applications.<\/jats:p>","DOI":"10.3390\/s24030899","type":"journal-article","created":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T12:06:58Z","timestamp":1706616418000},"page":"899","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Hardware Implementations of a Deep Learning Approach to Optimal Configuration of Reconfigurable Intelligence Surfaces"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5237-7756","authenticated-orcid":false,"given":"Alberto","family":"Mart\u00edn-Mart\u00edn","sequence":"first","affiliation":[{"name":"eesy-Innovation GmbH, 82008 Unterhaching, Germany"},{"name":"Department of Electronics and Computer Technology, University of Granada, 18071 Granada, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9741-4351","authenticated-orcid":false,"given":"Rub\u00e9n","family":"Padial-Allu\u00e9","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Technology, University of Granada, 18071 Granada, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6476-8105","authenticated-orcid":false,"given":"Encarnaci\u00f3n","family":"Castillo","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Technology, University of Granada, 18071 Granada, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8126-1146","authenticated-orcid":false,"given":"Luis","family":"Parrilla","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Technology, University of Granada, 18071 Granada, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1930-0241","authenticated-orcid":false,"given":"Ignacio","family":"Parellada-Serrano","sequence":"additional","affiliation":[{"name":"Department of Signal Theory, Telematics and Communications, University of Granada, 18071 Granada, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7628-0019","authenticated-orcid":false,"given":"Alejandro","family":"Mor\u00e1n","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering & Construction, University of Balearic Islands, 07120 Palma, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3533-4660","authenticated-orcid":false,"given":"Antonio","family":"Garc\u00eda","sequence":"additional","affiliation":[{"name":"Department of Electronics and Computer Technology, University of Granada, 18071 Granada, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,30]]},"reference":[{"key":"ref_1","unstructured":"International Data Corporation (2023, August 01). Future of Industry Ecosystems: Shared Data and Insights. Available online: https:\/\/blogs.idc.com\/2021\/01\/06\/future-of-industry-ecosystems-shared-data-and-insights\/."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Global System for Mobile Communications Association (2023, August 01). Second Wave of 5G: 30 Countries to Launch Services in 2023. Available online: https:\/\/www.gsma.com\/newsroom\/press-release\/second-wave-of-5g-30-countries-to-launch-services-in-2023\/.","DOI":"10.12968\/S0047-9624(23)60543-7"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"116753","DOI":"10.1109\/ACCESS.2019.2935192","article-title":"Wireless Communications Through Reconfigurable Intelligent Surfaces","volume":"7","author":"Basar","year":"2019","journal-title":"IEEE Access"},{"key":"ref_4","unstructured":"Klemic, K., Peters, M., and Fetunmbi, L. (2023, August 01). Future Directions Workshop on Wireless Communications: XG and beyond, Available online: https:\/\/basicresearch.defense.gov\/Portals\/61\/Documents\/future-directions\/Future%20Directions%20-%20Wireless%20Communications%20-%20for%20public%20release.pdf?ver=LL4z9Lfey_VSpFp6Nnmwmw%3D%3D."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1592","DOI":"10.1109\/JSAC.2023.3274037","article-title":"5G-Advanced Toward 6G: Past, Present, and Future","volume":"41","author":"Chen","year":"2023","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1109\/TCCN.2020.2992604","article-title":"Reconfigurable Intelligent Surfaces for Wireless Communications: Principles, Challenges, and Opportunities","volume":"6","author":"ElMossallamy","year":"2020","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"45913","DOI":"10.1109\/ACCESS.2020.2977772","article-title":"Reconfigurable Intelligent Surface-Based Wireless Communications: Antenna Design, Prototyping, and Experimental Results","volume":"8","author":"Dai","year":"2020","journal-title":"IEEE Access"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1109\/COMST.2021.3077737","article-title":"Reconfigurable Intelligent Surfaces: Principles and Opportunities","volume":"23","author":"Liu","year":"2021","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MCOM.001.2001161","article-title":"Metamaterial-Based Reconfigurable Intelligent Surface: 3D Meta-Atoms Controlled by Graphene Structures","volume":"59","author":"Molero","year":"2021","journal-title":"IEEE Commun. Mag."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1109\/MWC.008.2200124","article-title":"Intelligent reflecting surface-enhanced UAV communications: Advances, challenges, and prospects","volume":"30","author":"Ge","year":"2023","journal-title":"IEEE Wirel. Commun."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yuan, J., Ngo, H.Q., and Matthaiou, M. (2020, January 7\u201311). Large Intelligent Surface (LIS)-based Communications: New Features and System Layouts. Proceedings of the ICC 2020\u20142020 IEEE International Conference on Communications (ICC), Dublin, Ireland.","DOI":"10.1109\/ICC40277.2020.9149302"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"398","DOI":"10.3390\/network2030025","article-title":"Phase Shift Design in RIS Empowered Wireless Networks: From Optimization to AI-Based Methods","volume":"2","author":"Li","year":"2022","journal-title":"Network"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"85714","DOI":"10.1109\/ACCESS.2020.2991734","article-title":"An Overview on Edge Computing Research","volume":"8","author":"Cao","year":"2020","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"131788","DOI":"10.1109\/ACCESS.2022.3229767","article-title":"Efficient Hardware Architectures for Accelerating Deep Neural Networks: Survey","volume":"10","author":"Dhilleswararao","year":"2022","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/MCOM.001.2001076","article-title":"Reconfigurable Intelligent Surfaces for 6G Systems: Principles, Applications, and Research Directions","volume":"59","author":"Pan","year":"2021","journal-title":"IEEE Commun. Mag."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2718","DOI":"10.1109\/TVT.2022.3214818","article-title":"RIS-Aided 6G Communication System with Accurate Traceable User Mobility","volume":"72","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.23919\/ICN.2022.0005","article-title":"Reconfigurable intelligent surfaces for wireless communications: Overview of hardware designs, channel models, and estimation techniques","volume":"3","author":"Jian","year":"2022","journal-title":"Intell. Converg. Netw."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects","volume":"33","author":"Li","year":"2022","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"7457","DOI":"10.1109\/JIOT.2020.2984887","article-title":"Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence","volume":"7","author":"Deng","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ghimire, D., Kil, D., and Kim, S.H. (2022). A Survey on Efficient Convolutional Neural Networks and Hardware Acceleration. Electronics, 11.","DOI":"10.3390\/electronics11060945"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1109\/TAP.2021.3111325","article-title":"Design of a Compact Polarization-Agile and Frequency-Tailored Array Antenna With Digital-Controllable Radiation Beams","volume":"70","author":"Wu","year":"2022","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1055","DOI":"10.1109\/OJCOMS.2021.3076271","article-title":"A Reconfigurable Intelligent Surface at mmWave Based on a Binary Phase Tunable Metasurface","volume":"2","author":"Gros","year":"2021","journal-title":"IEEE Open J. Commun. Soc."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","article-title":"Res2Net: A New Multi-Scale Backbone Architecture","volume":"43","author":"Gao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2103","DOI":"10.1109\/TITS.2020.3032396","article-title":"Recognizing Very Small Face Images Using Convolution Neural Networks","volume":"23","author":"Horng","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3235","DOI":"10.1007\/s13042-020-01248-7","article-title":"IoT enabled depthwise separable convolution neural network with deep support vector machine for COVID-19 diagnosis and classification","volume":"12","author":"Le","year":"2021","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ji, M., Al-Ars, Z., Hofstee, P., Chang, Y., and Zhang, B. (2023). FPQNet: Fully Pipelined and Quantized CNN for Ultra-Low Latency Image Classification on FPGAs Using OpenCAPI. Electronics, 12.","DOI":"10.3390\/electronics12194085"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation Applied to Handwritten Zip Code Recognition","volume":"1","author":"LeCun","year":"1989","journal-title":"Neural Comput."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Islam, M.R., and Matin, A. (2020, January 19\u201321). Detection of COVID 19 from CT image by the novel LeNet-5 CNN architecture. Proceedings of the 2020 23rd International Conference on Computer and Information Technology (ICCIT), Dhaka, Bangladesh.","DOI":"10.1109\/ICCIT51783.2020.9392723"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yuan, Y., and Peng, L. (2018, January 8\u201311). Wireless device identification based on improved convolutional neural network model. Proceedings of the 2018 IEEE 18th International Conference on Communication Technology (ICCT), Chongqing, China.","DOI":"10.1109\/ICCT.2018.8600086"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1748302619873601","DOI":"10.1177\/1748302619873601","article-title":"Pedestrian detection based on improved LeNet-5 convolutional neural network","volume":"13","author":"Zhang","year":"2019","journal-title":"J. Algorithms Comput. Technol."},{"key":"ref_32","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and LeCun, Y. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv."},{"key":"ref_33","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2023, December 15). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_34","unstructured":"Chollet, F. (2023, December 15). Keras. Available online: https:\/\/keras.io\/getting_started\/faq\/#how-should-i-cite-keras."},{"key":"ref_35","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_36","unstructured":"(2023, December 15). ROCK 4C Plus. Available online: https:\/\/wiki.radxa.com\/Rock4\/4cplus."},{"key":"ref_37","unstructured":"(2023, December 15). Jetson Nano Developer Kit. Available online: https:\/\/developer.nvidia.com\/embedded\/jetson-nano-developer-kit."},{"key":"ref_38","unstructured":"(2023, December 15). Google Coral Dev Board. Available online: https:\/\/coral.ai\/products\/dev-board."},{"key":"ref_39","unstructured":"(2023, December 15). Intel\u00ae Arria\u00ae 10 SX SoC Development Kit. Available online: https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/fpga\/development-kits\/arria\/10-sx.html."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10586-016-0536-2","article-title":"Fast implementation of block ciphers and PRNGs in Maxwell GPU architecture","volume":"19","author":"Lee","year":"2016","journal-title":"Clust. Comput."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"100749","DOI":"10.1016\/j.iot.2023.100749","article-title":"Exploring Edge TPU for deep feed-forward neural networks","volume":"22","author":"Hosseininoorbin","year":"2023","journal-title":"Internet Things"},{"key":"ref_42","unstructured":"(2023, December 15). MATLAB\u00ae Deep Learning ToolboxTM. Available online: https:\/\/www.mathworks.com\/products\/deep-learning.html."},{"key":"ref_43","unstructured":"(2023, December 15). MATLAB\u00ae Deep Learning HDL ToolboxTM. Available online: https:\/\/www.mathworks.com\/products\/deep-learning-hdl.html."},{"key":"ref_44","unstructured":"(2023, December 15). OpenVINO Toolkit. Available online: https:\/\/docs.openvino.ai\/2023.2\/home.html."},{"key":"ref_45","unstructured":"(2023, December 15). Intel\u00ae FPGA AI Suite. Available online: https:\/\/www.intel.com\/content\/www\/us\/en\/software\/programmable\/fpga-ai-suite\/overview.html."},{"key":"ref_46","unstructured":"(2024, January 18). Intel\u00ae Quartus\u00ae Prime Software. Available online: https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/fpga\/development-tools\/quartus-prime.html."},{"key":"ref_47","unstructured":"Erickson, J. (2023, December 15). Deploying Deep Learning on Embedded Devices\u2014When FPGAs Make Sense. Available online: https:\/\/www.matlabexpo.com\/content\/dam\/mathworks\/mathworks-dot-com\/images\/events\/matlabexpo\/online\/2020\/deploying-deep-learning-on-embedded-devices-when-fpgas-make-sense.pdf."},{"key":"ref_48","unstructured":"(2023, December 15). Intel\u00ae FPGA AI Suite: IP Reference Manual. Available online: https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/programmable\/768974\/2023-2\/reference-manual.html."},{"key":"ref_49","unstructured":"(2023, December 15). Nios\u00ae V Processor for Intel\u00ae FPGA. Available online: https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/fpga\/nios-processor\/v.html."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/3\/899\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:51:47Z","timestamp":1760104307000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/3\/899"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,30]]},"references-count":49,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["s24030899"],"URL":"https:\/\/doi.org\/10.3390\/s24030899","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,30]]}}}