[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126936-en":3,"doc-seo-126936-105":30,"detail-sidebar-cat-0-en-105":90},{"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":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126936,137451207643,"Noah","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Comparison of Statistical and Machine Learning-Based Approaches for Telemetry Data Size Reduction - read","Next generation beyond 5G Digital Twin (DT) deployments rely on transporting increasingly large sensor telemetry time series. Compression of this shaped data delivers benefits including reduced sensor energy consumption, lower transport network bandwidth usage, and improved overall system efficiency. The document compares two telemetry time series compression strategies: a statistical similarity-based method and an autoencoder (AE)-based machine learning approach, evaluating their differing effectiveness and applicability for efficient, reliable data reduction.","Comparison of Statistical and Machine Learning-Based Approaches for Telemetry Data Size Reduction  \nAhmad El Sayed1, Marc Ruiz1*, Hassan Harb2, and Luis Velasco1  \n1 Optical Communications Group (GCO), Universitat Politècnica de Catalunya, Barcelona, Spain  \n2 College of Engineering and Technology, American University of the Middle East, Kuwait  \n*[e-mail: marc.ruiz-ramirez@upc.edu](e-mail: marc.ruiz-ramirez@upc.edu)  \nABSTRACT  \nThe implementation of next generation beyond 5G use cases such as the Digital Twin (DT) requires the transportation of increasingly large amounts of sensor telemetry data. The reduction of the size of these time series shaped data through compression has many benefits, ranging from energy savings in systems where sensors have limited power to transport network bandwidth reduction. Both statistical analysis-based and machine learning (ML)-based approaches have been employed to tackle this task with varying degrees of success. In this paper, we compare two methods for time series data compression: a statistical similarity-based one, and an autoencoder (AE)-based one.  \nKeywords: Telemetry Data, B5G, Compression, Statistical Similarity, Auto-Encoders  \n1. INTRODUCTION  \nOne of the most notable use cases of the beyond 5G (B5G) era is the Digital Twin (DT) [1] . It is a high bandwidth consuming application and requires innovation in the manner which the collected sensor telemetry data, essential for its operation. This data is typically transported from its distributed components to its central component, i.e., DT manager (DTM) . This DT use case, as well as other B5G use cases, need from pervasive monitoring solutions to deal with efficient and reliable collection and processing of telemetry data from largely distributed and heterogeneous data sources [2] .  \nOne of the goals of telemetry data processing is to reduce the volume to be conveyed from sources to the central manager without losing neither veracity nor value of the collected data [3] . The reduction of the size of transported telemetry data is key in order to avoid overwhelming the transport layer, and to reduce the network operation cost and complexity. It also has other benefits such as reducing the amount of power the sensors consume during data transmission, which is extremely important in the cases where the sensors have a limited power source such as a battery [4] . Moreover, data analysis in order to perform compression at the sensor node offer the opportunity to perform important tasks, such as anomaly detection, which can provide early signs of problems [5] . Traditionally, reducing the size of collected data can be achieved by either lowering the sampling rate, i.e., increasing the period between the collection of data points, or by compacting the volume of the data through compression [6] . Another approach is to use machine learning (ML) based models to perform the compression, which indeed is a recent trend in autonomous network operation, e.g., using auto-encoders (AE) with the potential to perform such compression tasks with higher efficiency [7] .  \nThis paper presents a comparison of two distinct approaches for telemetry data size reduction to be applied close to telemetry data sources. The first, named Zoom-In Zoom-Out (ZIZO) [8], exploits the redundancy in collected telemetry data to compress it by aggregating values of high similarity, with an algorithm called index bit encoding (IBE) . In addition, ZIZO also tries to minimize collected data by adapting the sensing rate to the redundancy levels measured in a group of close proximity sensors through statistical analysis, using an algorithm called Sensing Rate Adaption (SRA) . The second approach, named Adaptive AE-based Compression (AAC) [9] employs AEs for compression, while also performing localized anomaly detection. It makes use of their intrinsic dimensionality reduction abilities to reduce the size of transported data by sending through the network only the set of laten","cbCaigGEmFaLzbEb","https://ap.wps.com/l/cbCaigGEmFaLzbEb","pdf",563211,1,4,"English","en",105,"# Abstract\n# Introduction\n## Digital Twin and telemetry compression goals\n## Statistical similarity vs autoencoder-based compression\n# Reference Architecture\n## Sensors and Device Agent (DA)\n## Cluster Agent (CA) and DT manager (DTM)","[{\"question\":\"Why is telemetry data size reduction important in beyond 5G Digital Twin use cases?\",\"answer\":\"Digital Twin applications require high-bandwidth sensor telemetry, so reducing data volume helps prevent overwhelming the transport layer and lowers network operation cost and complexity while supporting reliable system operation.\"},{\"question\":\"What are the two compression approaches compared in the document?\",\"answer\":\"The document compares a statistical similarity-based approach called Zoom-In Zoom-Out (ZIZO) with algorithms such as index bit encoding and sensing rate adaptation, and a machine learning approach called Adaptive AE-based Compression (AAC) using autoencoders to transmit latent features.\"},{\"question\":\"What is the role of the device-side architecture in the proposed compression scheme?\",\"answer\":\"A Device Agent (DA) runs at the sensing/monitoring device layer to perform telemetry data processing and compression, then sends compressed data along with relevant metadata to the remote DT manager (DTM).\"}]","Comparison of Statistical and Machine Learning-Based Approaches for Telemetry Data Size Reduction - read | PDF",1785935764,10,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"comparison-of-statistical-and-machine-learning-based-approaches-for-telemetry-data-size-reduction-read","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":21},"https://docshare.wps.com/document/comparison-of-statistical-and-machine-learning-based-approaches-for-telemetry-data-size-reduction-read/126936/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is telemetry data size reduction important in beyond 5G Digital Twin use cases?","Question",{"text":74,"@type":75},"Digital Twin applications require high-bandwidth sensor telemetry, so reducing data volume helps prevent overwhelming the transport layer and lowers network operation cost and complexity while supporting reliable system operation.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What are the two compression approaches compared in the document?",{"text":79,"@type":75},"The document compares a statistical similarity-based approach called Zoom-In Zoom-Out (ZIZO) with algorithms such as index bit encoding and sensing rate adaptation, and a machine learning approach called Adaptive AE-based Compression (AAC) using autoencoders to transmit latent features.",{"name":81,"@type":72,"acceptedAnswer":82},"What is the role of the device-side architecture in the proposed compression scheme?",{"text":83,"@type":75},"A Device Agent (DA) runs at the sensing/monitoring device layer to perform telemetry data processing and compression, then sends compressed data along with relevant metadata to the remote DT manager (DTM).","https://schema.org",{"og:url":52,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]