A Novel Artificial Intelligence Based Dynamic Task Scheduling and Load Awareness

A Novel Artificial Intelligence Based Dynamic Task Scheduling and Load Awareness | 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 A Novel Artificial Intelligence Based Dynamic Task Scheduling and Load Awareness Hamed Altalhoni, Noraida Haji Ali, Farizah Yunus, Saleh Atiewi, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7465771/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 15 You are reading this latest preprint version Abstract Fog computing has emerged as a solution to the latency and bandwidth constraints of cloud-centric architecture yet efficiently scheduling heterogeneous IoT workloads while minimizing energy use and Service Level Agreement (SLA) violations remain challenging. The proposed framework integrates four complementary algorithms to enhance dynamic task scheduling in fog computing environments. First, a task classification module distinguishes IoT workloads as resource-intensive or non-resource-intensive based on task length, resource requirements, user preferences, and delay constraints. Second, a task prioritization module assigns tasks to major, middle, or minor priority levels using an emergency degree metric derived from waiting time, time-to-live, deadlines, and execution time. Third, the SUPERior-net-aided bipartite Deep Q-Network (SUPER DQNET) employs deep reinforcement learning to schedule non-resource-intensive tasks across fog nodes, optimizing the trade-off between energy consumption and latency. Finally, the Boosted Binary Owl Optimization (BOON) algorithm performs optimal virtual machine (VM) selection for task forwarding by jointly considering CPU utilization, bandwidth, queue length, system load, response time, makespan, energy usage, and SLA compliance. Implemented in iFogSim2, the proposed framework was evaluated against state-of-the-art methods including EEIOMT and EaDO, as well as baseline scheduling strategies such as Random Scheduler, Round Robin (RR), and First-Come, First-Served (FCFS). Experimental results show that our approach achieves up to 35% reduction in energy consumption, about 40% improvement in throughput, and over 40% reduction in SLA violation time, while maintaining low latency. These findings demonstrate the effectiveness of the proposed solution in delivering adaptive, energy-efficient, and SLA-compliant task scheduling for next-generation IoT applications in fog computing environments. Fog computing Task scheduling Deep reinforcement learning Metaheuristic optimization Energy efficiency SLA compliance Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 25 Oct, 2025 Reviews received at journal 24 Oct, 2025 Reviewers agreed at journal 24 Oct, 2025 Reviewers agreed at journal 22 Oct, 2025 Reviewers agreed at journal 21 Oct, 2025 Reviewers agreed at journal 17 Oct, 2025 Reviewers agreed at journal 16 Oct, 2025 Reviews received at journal 10 Sep, 2025 Reviewers agreed at journal 03 Sep, 2025 Reviewers agreed at journal 03 Sep, 2025 Reviewers agreed at journal 03 Sep, 2025 Reviewers invited by journal 03 Sep, 2025 Editor assigned by journal 02 Sep, 2025 Submission checks completed at journal 26 Aug, 2025 First submitted to journal 26 Aug, 2025 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-7465771","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":511014081,"identity":"37ced7b1-f1cd-46b2-ae7b-f3f9e966c4f0","order_by":0,"name":"Hamed Altalhoni","email":"","orcid":"","institution":"Universiti Malaysia Terengganu","correspondingAuthor":false,"prefix":"","firstName":"Hamed","middleName":"","lastName":"Altalhoni","suffix":""},{"id":511014082,"identity":"45cee8bb-d1e6-40cb-8e80-6ee9281a43eb","order_by":1,"name":"Noraida Haji Ali","email":"","orcid":"","institution":"Universiti Malaysia Terengganu","correspondingAuthor":false,"prefix":"","firstName":"Noraida","middleName":"Haji","lastName":"Ali","suffix":""},{"id":511014083,"identity":"65d0286e-c485-488d-a0e8-7a83493c6b1d","order_by":2,"name":"Farizah Yunus","email":"","orcid":"","institution":"Universiti Malaysia Terengganu","correspondingAuthor":false,"prefix":"","firstName":"Farizah","middleName":"","lastName":"Yunus","suffix":""},{"id":511014084,"identity":"dc65dd08-3fd5-4ad6-b602-6bcbe866e3e1","order_by":3,"name":"Saleh Atiewi","email":"","orcid":"","institution":"Universiti Malaysia Terengganu","correspondingAuthor":false,"prefix":"","firstName":"Saleh","middleName":"","lastName":"Atiewi","suffix":""},{"id":511014085,"identity":"a86b17b2-8ca2-4343-b6ba-059798ceb05a","order_by":4,"name":"Amal Alshardan","email":"","orcid":"","institution":"Princess Nourah bint Abdulrahman University","correspondingAuthor":false,"prefix":"","firstName":"Amal","middleName":"","lastName":"Alshardan","suffix":""},{"id":511014086,"identity":"c66ae2be-6b3f-44e9-bf74-af7afeeb4d05","order_by":5,"name":"Muder Almiani","email":"","orcid":"","institution":"Gulf University for Science \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Muder","middleName":"","lastName":"Almiani","suffix":""},{"id":511014087,"identity":"9cda9560-5bb4-45f9-8287-cb618a8d37e7","order_by":6,"name":"SHADI ALZUBI","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIie3QLQvCQBzH8f8YLB2sTlR8Cz8ZWAy+la24YlgSg+FAuCTYLL4Ki/nGgenQF7CFWcxGLeKpxbTNJnjfchfuc09ENttv5kgiyXwzA5FrBllvXqTFvyWE90K3fnlvrcrsJopOeNRIaTaMuaOqj0E+hmyJMxtIDZBOYk77qJq0I8i+UGyQLQFHKEM0qi+2SS4yNiRcMEPuDQjlE8jMEHhPwhsQ5JM044czC7SXItonoah7i7nY9nSdFiN/pXa4zIfdVVDzY595eG7vBc0FueVr8HlzYrPZbH/RA3+3TjdNUmaaAAAAAElFTkSuQmCC","orcid":"","institution":"Al-Zaytoonah University of Jordan","correspondingAuthor":true,"prefix":"","firstName":"SHADI","middleName":"","lastName":"ALZUBI","suffix":""}],"badges":[],"createdAt":"2025-08-26 19:23:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7465771/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7465771/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90949360,"identity":"6b847550-b7ba-49ba-b45e-c15950a63e8d","added_by":"auto","created_at":"2025-09-09 22:45:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6270831,"visible":true,"origin":"","legend":"","description":"","filename":"AILoadAwarenessCLUS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7465771/v1_covered_97a164e3-9cd2-497b-9f97-a1ee28cb0c84.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Novel Artificial Intelligence Based Dynamic Task Scheduling and Load Awareness","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":" Fog computing, Task scheduling, Deep reinforcement learning, Metaheuristic optimization, Energy efficiency, SLA compliance","lastPublishedDoi":"10.21203/rs.3.rs-7465771/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7465771/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Fog computing has emerged as a solution to the latency and bandwidth constraints of cloud-centric architecture yet efficiently scheduling heterogeneous IoT workloads while minimizing energy use and Service Level Agreement (SLA) violations remain challenging. The proposed framework integrates four complementary algorithms to enhance dynamic task scheduling in fog computing environments. First, a task classification module distinguishes IoT workloads as resource-intensive or non-resource-intensive based on task length, resource requirements, user preferences, and delay constraints. Second, a task prioritization module assigns tasks to major, middle, or minor priority levels using an emergency degree metric derived from waiting time, time-to-live, deadlines, and execution time. Third, the SUPERior-net-aided bipartite Deep Q-Network (SUPER DQNET) employs deep reinforcement learning to schedule non-resource-intensive tasks across fog nodes, optimizing the trade-off between energy consumption and latency. Finally, the Boosted Binary Owl Optimization (BOON) algorithm performs optimal virtual machine (VM) selection for task forwarding by jointly considering CPU utilization, bandwidth, queue length, system load, response time, makespan, energy usage, and SLA compliance. Implemented in iFogSim2, the proposed framework was evaluated against state-of-the-art methods including EEIOMT and EaDO, as well as baseline scheduling strategies such as Random Scheduler, Round Robin (RR), and First-Come, First-Served (FCFS). Experimental results show that our approach achieves up to 35\\% reduction in energy consumption, about 40\\% improvement in throughput, and over 40\\% reduction in SLA violation time, while maintaining low latency. These findings demonstrate the effectiveness of the proposed solution in delivering adaptive, energy-efficient, and SLA-compliant task scheduling for next-generation IoT applications in fog computing environments. ","manuscriptTitle":"A Novel Artificial Intelligence Based Dynamic Task Scheduling and Load Awareness","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-09 22:36:53","doi":"10.21203/rs.3.rs-7465771/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-25T11:47:43+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-24T12:46:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"191447480467963439948055043085547383013","date":"2025-10-24T05:36:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"266090457934215064007697407181728217866","date":"2025-10-23T02:31:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"54920999309411554687453605660561029393","date":"2025-10-22T00:20:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"203387551639482671693846071618848228865","date":"2025-10-17T09:44:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"323563104619534869133622828889554887541","date":"2025-10-17T02:58:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-11T00:38:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"110474091229687736622483276879317740678","date":"2025-09-03T12:51:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"250556526203731498106542816953617198955","date":"2025-09-03T11:37:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"88143913663646128744646024172679304735","date":"2025-09-03T11:33:39+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-03T11:18:53+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-02T09:11:08+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-27T01:35:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2025-08-26T19:18:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"1084afb3-4baf-44c9-b1c7-7ab97df961e6","owner":[],"postedDate":"September 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-01-12T20:08:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-09 22:36:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7465771","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7465771","identity":"rs-7465771","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}