[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121553-en":3,"doc-seo-121553-105":30,"detail-sidebar-cat-0-en-105":91},{"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},121553,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Minimizing the Carbon Footprint in LoRa-Based IoT Networks - A Machine Learning Perspective on Gateway Positioning","The Internet of Things (IoT) enables seamless connectivity and data exchange, yet network deployment requires configurations tailored to diverse application needs. Limited research has addressed the carbon footprint (CF) produced by these deployments. This study introduces a machine learning optimization framework that minimizes CF in IoT multi-hop networks by varying gateway placement, and compares the results against an integer linear programming (ILP) approach. Neural networks achieve up to 14% CF reduction on simple networks without optimization, while ILP reaches 16.6% but with over 250× higher computation and an added environmental cost, highlighting scalability benefits for larger networks.","Received 5 February 2025; revised 20 March 2025; accepted 7 April 2025. Date of publication 9 April 2025;  \ndate of current version 30 April 2025. The review of this article was arranged by Associate Editor Jingcai Guo.  \nDigital Object Identifier 10.1109/OJCS.2025.3559331  \nMinimizing the Carbon Footprint in LoRa-Based IoT Networks: A Machine Learning Perspective on Gateway Positioning  \nFRANCISCO-JOSE ALVARADO-ALCON , RAFAEL ASOREY-CACHEDA  (Senior Member, IEEE), ANTONIO-JAVIER GARCIA-SANCHEZ , AND JOAN GARCIA-HARO  (Member, IEEE)  \nDepartment of Information and Communication Technologies, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain  \nCORRESPONDING AUTHOR: RAFAEL ASOREY-CACHEDA (e-mail: [rafael.asorey@upct.es](rafael.asorey@upct.es)).  \nThis work was supported in part by MICIU/AEI/10.13039/501100011033 and FEDER, EU, under Grant PID2023-148214OB-C21, in part by MCIN/AEI/10.13039/501100011033 and the European Union NextGenerationEU/PRTR under Grant TED2021-129336B-I00, and in part by Fundación Séneca under Grant 22236/PDC/23 . The work of Francisco-Jose Alvarado-Alcon was supported by the Spain’s Ministry of Universities under Grant FPU22/00316 .  \nABSTRACT The Internet of Things (IoT) is gaining significant attention for its ability to digitally transform various sectors by enabling seamless connectivity and data exchange. However, deploying these networks is challenging due to the need to tailor configurations to diverse application requirements. To date, there has been limited focus on examining and enhancing the carbon footprint (CF) associated with these network deployments. In this study, we present an optimization framework leveraging machine learning techniques to minimize the CF associated with IoT multi-hop network deployments by varying the placement of the required gateways. Additionally, we establish a direct comparison between our proposed machine learning method and the integer linear program (ILP) approach. Our findings reveal that placing gateways using neural networks can achieve a 14% reduction in the CF for simple networks compared to those not using optimization for gateway placement. The ILP method could reduce the CF by 16.6% for identical networks, although it incurs a computational cost more than 250 times higher, which has its own environmental impact. Furthermore, we highlight the superior scalability of machine learning techniques, particularly advantageous for larger networks, as discussed in our concluding remarks.  \nINDEX TERMS Carbon footprint (CF), Internet of Things (IoT) networks, LPWAN, multilayer perceptrons, neural networks.  \nI. INTRODUCTION  \nAs the world transitions to an increasingly interconnected era, the IoT has emerged as the cornerstone of future technological advancements. The deployment of a wireless IoT network entails distributing numerous autonomous, cost-effective devices, referred to as end devices or nodes, across a designated area. These end devices are tasked with monitoring various environmental parameters and transmitting collected data wirelessly to one or more gateways, also known as sink nodes. Subsequently, the gateways relay this information to network servers for further processing tailored to specific applications, spanning domains like precision agriculture, home automation, smart cities, e-health, and Industry 4.0, among many  \nothers. Extensive research has focused on evaluating the overall performance of this architecture, encompassing metrics such as economic cost [1], [2], [3], maximum lifetime [4],[5], packet loss [2], [3], [6], energy efficiency [1], [5], [6],[7], and the Human Toxicity Parameter [1] . However, the planning phase of IoT networks before deployment is crucial to determining the performance and functionality of the end application. This task is extremely intricate given the myriad of configurations and scenarios that can be envisioned based on the desired objectives.  \nIt is imperative to acknowledge the substantial environmental","cbCaisOAxiAVijYc","https://ap.wps.com/l/cbCaisOAxiAVijYc","pdf",1956822,1,12,"English","en",105,"# Abstract\n# Introduction\n## IoT network architecture and deployment planning\n## Environmental impact and carbon footprint definition\n## Motivation for scalable machine learning optimization","[{\"question\":\"How does the proposed method reduce carbon footprint in LoRa-based IoT multi-hop networks?\",\"answer\":\"It minimizes CF by optimizing required gateway placement, using machine learning to vary gateway locations and improve deployment efficiency.\"},{\"question\":\"How does the machine learning approach compare with the ILP method?\",\"answer\":\"The study reports that neural networks can reduce CF by about 14% for simple networks versus no gateway-placement optimization, while ILP can reduce CF by 16.6% but requires more than 250× higher computation.\"},{\"question\":\"Why is scalability a key advantage of machine learning in this context?\",\"answer\":\"The document explains that continuous growth in network size and complexity makes other optimization approaches less effective, while machine learning is presented as more scalable and adaptable, especially for larger networks.\"}]","Minimizing the Carbon Footprint in LoRa-Based IoT Networks - A Machine Learning Perspective on Gateway Positioning | PDF",1785736218,30,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"minimizing-the-carbon-footprint-in-lora-based-iot-networks-a-machine-learning-perspective-on-gateway-positioning","",{"@graph":36,"@context":85},[37,54,68],{"@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":53},"https://docshare.wps.com/document/minimizing-the-carbon-footprint-in-lora-based-iot-networks-a-machine-learning-perspective-on-gateway-positioning/121553/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the proposed method reduce carbon footprint in LoRa-based IoT multi-hop networks?","Question",{"text":75,"@type":76},"It minimizes CF by optimizing required gateway placement, using machine learning to vary gateway locations and improve deployment efficiency.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the machine learning approach compare with the ILP method?",{"text":80,"@type":76},"The study reports that neural networks can reduce CF by about 14% for simple networks versus no gateway-placement optimization, while ILP can reduce CF by 16.6% but requires more than 250× higher computation.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is scalability a key advantage of machine learning in this context?",{"text":84,"@type":76},"The document explains that continuous growth in network size and complexity makes other optimization approaches less effective, while machine learning is presented as more scalable and adaptable, especially for larger networks.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"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":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]