Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing
<p dir="ltr">The shift to AI-native 6G networks demands autonomous slicing strategies that can adapt to diverse and evolving edge and IoT service needs. Two paradigms have emerged: Learn to Slice (L2S), where AI optimizes network slicing for general services, and Slice to Learn (S2L)...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1864513524421623808 |
|---|---|
| author | Amr Abo-eleneen (17032284) |
| author2 | Menna Helmy (23073205) Alaa Awad Abdellatif (17151163) Mohamed Abdallah (3073191) Amr Mohamed (3508121) Aiman Erbad (14150589) |
| author2_role | author author author author author |
| author_facet | Amr Abo-eleneen (17032284) Menna Helmy (23073205) Alaa Awad Abdellatif (17151163) Mohamed Abdallah (3073191) Amr Mohamed (3508121) Aiman Erbad (14150589) |
| author_role | author |
| dc.creator.none.fl_str_mv | Amr Abo-eleneen (17032284) Menna Helmy (23073205) Alaa Awad Abdellatif (17151163) Mohamed Abdallah (3073191) Amr Mohamed (3508121) Aiman Erbad (14150589) |
| dc.date.none.fl_str_mv | 2025-10-24T15:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1109/miot.2025.3611516 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Toward_AI-Native_6G_Unveiling_Online_Optimization_and_Deep_Reinforcement_Learning_for_Autonomous_Network_Slicing/31168453 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Engineering Communications engineering Information and computing sciences Artificial intelligence EXP3 DQN slicing AI zero-touch optimization Artificial intelligence Training Resource management Accuracy Adaptation models 6G mobile communication Optimization Internet of Things Computational modeling Data models |
| dc.title.none.fl_str_mv | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">The shift to AI-native 6G networks demands autonomous slicing strategies that can adapt to diverse and evolving edge and IoT service needs. Two paradigms have emerged: Learn to Slice (L2S), where AI optimizes network slicing for general services, and Slice to Learn (S2L), where slices support AI model training, often offloaded from Internet of Things (IoT) devices. Existing S2L approaches typically optimize communication or computation in isolation. This paper presents the first unified framework that jointly optimizes communication resources, computation capacity, and AI hyperparameters to maximize the average accuracy of multiple concurrent AI services. We address the complexity of this joint problem by applying L2S-inspired techniques to enhance S2L, introducing two autonomous agents: EXP3 from online convex optimization and DQN from deep reinforcement learning. Extensive experiments demonstrate and contrast the effectiveness of these agents in maximizing aggregated AI accuracy, supporting knowledge transfer, and sustaining robust performance under adversarial and long-term conditions, thereby enhancing the realization of zero-touch network management for AI services in 6G networks, supporting resource-constrained IoT.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Internet of Things Magazine<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/miot.2025.3611516" target="_blank">https://dx.doi.org/10.1109/miot.2025.3611516</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_c0b82da847997caf956567c46b98c05f |
| identifier_str_mv | 10.1109/miot.2025.3611516 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/31168453 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network SlicingAmr Abo-eleneen (17032284)Menna Helmy (23073205)Alaa Awad Abdellatif (17151163)Mohamed Abdallah (3073191)Amr Mohamed (3508121)Aiman Erbad (14150589)EngineeringCommunications engineeringInformation and computing sciencesArtificial intelligenceEXP3DQNslicingAIzero-touchoptimizationArtificial intelligenceTrainingResource managementAccuracyAdaptation models6G mobile communicationOptimizationInternet of ThingsComputational modelingData models<p dir="ltr">The shift to AI-native 6G networks demands autonomous slicing strategies that can adapt to diverse and evolving edge and IoT service needs. Two paradigms have emerged: Learn to Slice (L2S), where AI optimizes network slicing for general services, and Slice to Learn (S2L), where slices support AI model training, often offloaded from Internet of Things (IoT) devices. Existing S2L approaches typically optimize communication or computation in isolation. This paper presents the first unified framework that jointly optimizes communication resources, computation capacity, and AI hyperparameters to maximize the average accuracy of multiple concurrent AI services. We address the complexity of this joint problem by applying L2S-inspired techniques to enhance S2L, introducing two autonomous agents: EXP3 from online convex optimization and DQN from deep reinforcement learning. Extensive experiments demonstrate and contrast the effectiveness of these agents in maximizing aggregated AI accuracy, supporting knowledge transfer, and sustaining robust performance under adversarial and long-term conditions, thereby enhancing the realization of zero-touch network management for AI services in 6G networks, supporting resource-constrained IoT.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Internet of Things Magazine<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/miot.2025.3611516" target="_blank">https://dx.doi.org/10.1109/miot.2025.3611516</a></p>2025-10-24T15:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/miot.2025.3611516https://figshare.com/articles/journal_contribution/Toward_AI-Native_6G_Unveiling_Online_Optimization_and_Deep_Reinforcement_Learning_for_Autonomous_Network_Slicing/31168453CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/311684532025-10-24T15:00:00Z |
| spellingShingle | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing Amr Abo-eleneen (17032284) Engineering Communications engineering Information and computing sciences Artificial intelligence EXP3 DQN slicing AI zero-touch optimization Artificial intelligence Training Resource management Accuracy Adaptation models 6G mobile communication Optimization Internet of Things Computational modeling Data models |
| status_str | publishedVersion |
| title | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing |
| title_full | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing |
| title_fullStr | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing |
| title_full_unstemmed | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing |
| title_short | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing |
| title_sort | Toward AI-Native 6G: Unveiling Online Optimization and Deep Reinforcement Learning for Autonomous Network Slicing |
| topic | Engineering Communications engineering Information and computing sciences Artificial intelligence EXP3 DQN slicing AI zero-touch optimization Artificial intelligence Training Resource management Accuracy Adaptation models 6G mobile communication Optimization Internet of Things Computational modeling Data models |