AI-Driven On-Site Energy Utilization and Green Optimization of Telecommunication Base Stations in Hybrid Power Networks: A Case of Western Uganda

AI-Driven On-Site Energy Utilization and Green Optimization of Telecommunication Base Stations in Hybrid Power Networks: A Case of Western Uganda | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article AI-Driven On-Site Energy Utilization and Green Optimization of Telecommunication Base Stations in Hybrid Power Networks: A Case of Western Uganda Kelechi Ukagwu, Obinna Onyebuchi Barah, Val Hyginus Udoka Eze, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9419094/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract The rapid evolution of 5G networks, edge computing, and emerging 6G paradigms has significantly increased the energy intensity of telecommunication base stations (BSs), particularly in regions with unstable grid infrastructure such as sub-Saharan Africa. This study presents an updated investigation into on-site energy utilization dynamics of multi-technology base stations in Western Uganda, incorporating traffic-aware energy profiling, AI-assisted regression modeling, and hybrid energy system considerations. Unlike traditional studies that rely solely on linear regression between traffic load and power consumption, this work introduces a data-driven hybrid modeling approach combining statistical regression with machine learning-assisted trend correction to capture non-linearities under low-traffic and transitional load conditions. Measurements were conducted over 28 consecutive days across six rural and urban base stations using IoT-enabled sensing instruments. Results reveal that energy consumption is strongly influenced not only by traffic load and transceiver density but also by dynamic energy state switching of modern radio units, partial sleep modes, and load-dependent power scaling mechanisms introduced in 5G-ready infrastructure. The study further highlights that AI-enhanced predictive energy models outperform classical linear regression by improving prediction stability under low-traffic regimes by up to 18–25%, making them suitable for smart telecom energy management systems. Green telecom AI-based energy optimization 5G/6G base stations hybrid energy systems edge intelligence IoT monitoring traffic-aware power modeling sustainable networks smart grids Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 16 May, 2026 Reviews received at journal 05 May, 2026 Reviewers agreed at journal 29 Apr, 2026 Reviewers agreed at journal 28 Apr, 2026 Reviewers agreed at journal 27 Apr, 2026 Reviewers agreed at journal 27 Apr, 2026 Reviewers invited by journal 27 Apr, 2026 Editor invited by journal 25 Apr, 2026 Editor assigned by journal 18 Apr, 2026 Submission checks completed at journal 18 Apr, 2026 First submitted to journal 14 Apr, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9419094","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":631618477,"identity":"91132441-5094-4b48-a130-98a0e16571e6","order_by":0,"name":"Kelechi Ukagwu","email":"","orcid":"","institution":"Kampala International University","correspondingAuthor":false,"prefix":"","firstName":"Kelechi","middleName":"","lastName":"Ukagwu","suffix":""},{"id":631618478,"identity":"60d4adc6-1ff2-477b-a7f5-0d1d13294729","order_by":1,"name":"Obinna Onyebuchi Barah","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYDACCcYGEJUAxGwMHw5IkKiFcQZxWiAUWAszzwEidPBLN7c9LqhhyOOfffjZY5szFokN7IcfMPP8wq1Fcs7BduMZxxiKJc6lmRvn3JBIbOBJM2Dm7cOtxeBGYps0DxtDYsMZBjPpnA9ALQw5DMy8PYS0/GNInH+G/Zu0BUgL/xsitPC2MSRuOMNjJs0AcpgE0BaeH3j9AtTSJ1FseIanTLLnjIRxm8Qzg4NzG3Br4ZdufybN880mT+4M+zaJH8fqZPv5kx8+ePMHtxYoQIpBNiA+wNhGUAsGIGzLKBgFo2AUjBwAAL2VTRhYgqQVAAAAAElFTkSuQmCC","orcid":"","institution":"Kampala International University","correspondingAuthor":true,"prefix":"","firstName":"Obinna","middleName":"Onyebuchi","lastName":"Barah","suffix":""},{"id":631618480,"identity":"236ddce4-13d2-44f6-9e00-f0d10c2f94d8","order_by":2,"name":"Val Hyginus Udoka Eze","email":"","orcid":"","institution":"Mbarara University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Val","middleName":"Hyginus Udoka","lastName":"Eze","suffix":""},{"id":631618482,"identity":"1a9e4964-70d9-4961-8576-f9b3a813e612","order_by":3,"name":"Pius Erheyovwe Bubu","email":"","orcid":"","institution":"Kampala International University","correspondingAuthor":false,"prefix":"","firstName":"Pius","middleName":"Erheyovwe","lastName":"Bubu","suffix":""}],"badges":[],"createdAt":"2026-04-14 19:23:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9419094/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9419094/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108804299,"identity":"ed2fed1b-c0af-447c-add2-5e918c1e4027","added_by":"auto","created_at":"2026-05-08 15:19:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":549027,"visible":true,"origin":"","legend":"","description":"","filename":"AIDrivenOnSiteEnergy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9419094/v1_covered_c14bfcb5-6ee7-4c63-8457-f48313091332.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AI-Driven On-Site Energy Utilization and Green Optimization of Telecommunication Base Stations in Hybrid Power Networks: A Case of Western Uganda","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Green telecom, AI-based energy optimization, 5G/6G base stations, hybrid energy systems, edge intelligence, IoT monitoring, traffic-aware power modeling, sustainable networks, smart grids","lastPublishedDoi":"10.21203/rs.3.rs-9419094/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9419094/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe rapid evolution of 5G networks, edge computing, and emerging 6G paradigms has significantly increased the energy intensity of telecommunication base stations (BSs), particularly in regions with unstable grid infrastructure such as sub-Saharan Africa. This study presents an updated investigation into on-site energy utilization dynamics of multi-technology base stations in Western Uganda, incorporating traffic-aware energy profiling, AI-assisted regression modeling, and hybrid energy system considerations. Unlike traditional studies that rely solely on linear regression between traffic load and power consumption, this work introduces a data-driven hybrid modeling approach combining statistical regression with machine learning-assisted trend correction to capture non-linearities under low-traffic and transitional load conditions. Measurements were conducted over 28 consecutive days across six rural and urban base stations using IoT-enabled sensing instruments. Results reveal that energy consumption is strongly influenced not only by traffic load and transceiver density but also by dynamic energy state switching of modern radio units, partial sleep modes, and load-dependent power scaling mechanisms introduced in 5G-ready infrastructure. The study further highlights that AI-enhanced predictive energy models outperform classical linear regression by improving prediction stability under low-traffic regimes by up to 18–25%, making them suitable for smart telecom energy management systems.\u003c/p\u003e","manuscriptTitle":"AI-Driven On-Site Energy Utilization and Green Optimization of Telecommunication Base Stations in Hybrid Power Networks: A Case of Western Uganda","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-05 23:10:33","doi":"10.21203/rs.3.rs-9419094/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-16T12:19:16+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T15:30:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"96721929288245805494164469580985245590","date":"2026-04-29T08:56:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"183812765536964292168782728742041635696","date":"2026-04-28T04:11:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"96024486638652268075610721001306126995","date":"2026-04-27T23:52:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"21394136923376691825964508866603203811","date":"2026-04-27T11:29:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-27T08:41:10+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-25T06:24:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-18T06:46:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-18T06:45:13+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Computing","date":"2026-04-14T19:15:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"30311347-00cd-48e6-82e5-d02090733b81","owner":[],"postedDate":"May 5th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-16T12:19:16+00:00","index":28,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-05T15:30:12+00:00","index":27,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-05T23:10:33+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-05 23:10:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9419094","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9419094","identity":"rs-9419094","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}