[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121773-en":3,"doc-seo-121773-105":29,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":20,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},121773,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Enhancement of Satellite Free-Space Laser Communication Systems using Machine Learning methods - Technology Use Cases and Algorithms","Satellite free-space laser communication systems offer substantially higher data rates than conventional RF by using light, yet many current optical payloads remain largely unoptimized in SatCom deployments. This study, developed with CGI UK, applies machine learning to upgrade laser communication terminals by improving link acquisition robustness and enabling autonomous network outage handling. Use cases include ML-based uplink beacon detection under noise and DNN-driven local traffic re-routing based on limited network state, validated via dedicated LCT and SDN simulator test benches.","Enhancement of Satellite Free-Space Laser Communication Systems using Machine Learning methods  \nCraft Prospect: Mikulas Cebecauer, Cameron Anderson, Georgia Harvey, Craig Colquhoun, Murray Ireland  \nCGI UK: Rob Hunter, Afonso Nunes, Rob Stansfield  \nBACKGROUND  \nLaser communication systems have many advantages over conventional radio frequency (RF) systems. Using light instead of RF supports significantly higher communication data rates. However, such optical payloads are currently mainly used in non-optimised SatCom systems, and thus their full capabilities remain unexploited. In response to this Craft Prospect with CGI UK is focused on upgrading optical systems by using machine learning (ML) methods to improve link acquisition of laser communication terminals (LCTs) and to manage networked laser SatCom system outages.  \nUSE CASES  \nThe European OPS-SAT Versatile Optical Laboratory for Telecoms (VOLT) is a CubeSat mission which will demonstrate next generation optical and quantum communication payloads. Furthermore, the ESA High Throughput Optical Network (HydRON) project aims to deliver high-capacity interconnected optical space and terrestrial network which is self-organising. Through the study of these and the state-of-the-art LCTs on market, the following technology use cases were selected:  \nA. Optimising the LCT acquisition mode by using machine learning to improve detection algorithms of the uplink beacon spot from a noisy background. We expect that this will enable a faster simultaneous acquisition scheme where a weak incoming beacon will be detected on a detector in the presence of back reflections from outgoing beacon.  \nB. Optimising network fault handling by using machine learning deployed onto network nodes to perform autonomous local traffic network re-routing in response to link impairments. This is in-particular due to cloud cover and atmospheric conditions.  \nData  \nProducer  \nAffected Node  \nData  \nConsumer  \nFigure 1 – Example network use case with original flow shown in green which autonomously re-routed locally in blue by ML algorithm on nodes.  \nSSC23-P5-27  \nFigure 2 – Testbench showing LCT used for ML algorithm development.  \nTEST BENCHES  \nA. LCT developed for quantum coms with a CMOS based beacon detector is being used for acquisition. An incoming and an outgoing laser with variable optical parameters (power, angle of incidence, size) are used to create an image dataset at the detector and for testing of ML based detection under noise conditions.  \nB. An SDN network simulator testbed is being used for producing flows through network and development of data. Into this, the ML algorithm will be deployed for testing of re-routing of flows.  \nALGORITHM FOR ACQUISITION  \nBeacon detection is treated as a real-time object detection task performed with YOLOv3 CNN model [1] selected for its high inference rates and ease of implementation. Transfer learning was used to train the model on a dataset captured from the LCT testbench allowing a high accuracy on a relatively small dataset.  \nFigure 3 – Average intersection over union of predicted and target bounding boxes for different blinding laser powers.  \nALGORITHM FOR NETWORK FAULT HANDLING  \nA novel DNN for network fault re-routing was developed to be deployable on network nodes which monitors traffic statistics of edges and predicts the latency to destination for its edges based on the nodes limited view of the network state. This is used by nodes to make decisions about which edges to re-route traffic onto and when to notify local neighbouring nodes to react to a fault. The model uses an autoencoder to learn a low dimensional representation of the time-series traffic statistics [2], combined with a multilayer perceptron to predict the latency. Optimisation work is currently being carried out to maximise the model's accuracy.  \nFigure 4 – Architecture of deep temporal regressor with the deployable layers in bold.  \nCONCLUSIONS  \nInitial results for both pro","cbCainudi1rWBRuA","https://ap.wps.com/l/cbCainudi1rWBRuA","pdf",366322,1,"English","en",105,"# Background\n# Use Cases\n## LCT acquisition optimization\n## Network fault handling\n# Data Flow Example\n# Test Benches\n## LCT acquisition dataset generation\n## SDN network simulator for flow development\n# Algorithm for Acquisition\n# Algorithm for Network Fault Handling\n# Conclusions\n# References","[{\"question\":\"Why are laser communication systems considered superior to radio frequency (RF) systems?\",\"answer\":\"Laser communication uses light instead of RF, enabling significantly higher communication data rates. The document highlights the advantage while noting that optical payload capabilities are often not fully exploited.\"},{\"question\":\"How does machine learning improve link acquisition for laser communication terminals (LCTs)?\",\"answer\":\"Beacon detection is modeled as real-time object detection using a YOLOv3 CNN. Transfer learning trains on datasets captured from an LCT test bench to detect weak beacons within noisy background conditions.\"},{\"question\":\"How is network fault handling implemented using machine learning?\",\"answer\":\"A deployable DNN monitors traffic statistics of network edges and predicts latency to destinations using limited network state information. It employs an autoencoder for low-dimensional time-series representation and a multilayer perceptron for latency prediction to support autonomous local re-routing.\"}]","Enhancement of Satellite Free-Space Laser Communication Systems using Machine Learning methods - Technology Use Cases and Algorithms | PDF",1785806766,3,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":27},"enhancement-of-satellite-free-space-laser-communication-systems-using-machine-learning-methods-technology-use-cases-and-algorithms","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":28},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/enhancement-of-satellite-free-space-laser-communication-systems-using-machine-learning-methods-technology-use-cases-and-algorithms/121773/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"Why are laser communication systems considered superior to radio frequency (RF) systems?","Question",{"text":73,"@type":74},"Laser communication uses light instead of RF, enabling significantly higher communication data rates. The document highlights the advantage while noting that optical payload capabilities are often not fully exploited.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How does machine learning improve link acquisition for laser communication terminals (LCTs)?",{"text":78,"@type":74},"Beacon detection is modeled as real-time object detection using a YOLOv3 CNN. Transfer learning trains on datasets captured from an LCT test bench to detect weak beacons within noisy background conditions.",{"name":80,"@type":71,"acceptedAnswer":81},"How is network fault handling implemented using machine learning?",{"text":82,"@type":74},"A deployable DNN monitors traffic statistics of network edges and predicts latency to destinations using limited network state information. It employs an autoencoder for low-dimensional time-series representation and a multilayer perceptron for latency prediction to support autonomous local re-routing.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]