Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language Model

Storage resources are essential in heterogeneous multi-cloud environments. In response to the growing demand for efficient storage resource management (SRM) in these environments, this paper proposes an intent-based storage management (IBSM) system powered by a fine-tuned large language model (LLM)....

Full description

Saved in:
Bibliographic Details
Main Authors: Jingya Zheng, Gaofeng Tao, Shuxin Qin, Dan Wang, Zhongjun Ma
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10975014/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712716125569024
author Jingya Zheng
Gaofeng Tao
Shuxin Qin
Dan Wang
Zhongjun Ma
author_facet Jingya Zheng
Gaofeng Tao
Shuxin Qin
Dan Wang
Zhongjun Ma
author_sort Jingya Zheng
collection DOAJ
description Storage resources are essential in heterogeneous multi-cloud environments. In response to the growing demand for efficient storage resource management (SRM) in these environments, this paper proposes an intent-based storage management (IBSM) system powered by a fine-tuned large language model (LLM). To overcome the limitations of existing methods, the IBSM system focuses on enhancing the controllability, completeness, and reliability of SRM in multi-cloud environments. Specifically, the IBSM system employs a dual-phase joint intent classification algorithm, which leverages a fine-tuned LLM to accurately identify user intents across diverse knowledge backgrounds. Additionally, the system constructs a collaborative intent decomposition method, which guarantees the integrity of intents. Furthermore, the system integrates an automated intent deployment mechanism that supports error recovery through checkpoints. Experimental results show that the system achieves a whole end-to-end (E2E) lifecycle for managing user intents. The E2E time is reduced by at least half compared to the manual approach, with an average of 50.14% dedicated to interactive tasks. Performance metrics for intent classification, including accuracy, precision, and recall, all exceed 90%. Moreover, the recovery time is reduced by an average of 30.6%. Therefore, the system provides a valuable solution for the autonomous management of multi-cloud resources.
format Article
id doaj-art-5545372d52f84f0f88e341ec61bd4e56
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5545372d52f84f0f88e341ec61bd4e562025-08-20T03:14:12ZengIEEEIEEE Access2169-35362025-01-0113727367275310.1109/ACCESS.2025.356320010975014Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language ModelJingya Zheng0https://orcid.org/0009-0007-6101-8529Gaofeng Tao1https://orcid.org/0009-0004-5006-6259Shuxin Qin2Dan Wang3Zhongjun Ma4https://orcid.org/0009-0006-5302-9773Shandong Future Network Research Institute, Jinan, ChinaShandong Future Network Research Institute, Jinan, ChinaPurple Mountain Laboratories, Nanjing, ChinaPurple Mountain Laboratories, Nanjing, ChinaShandong Future Network Research Institute, Jinan, ChinaStorage resources are essential in heterogeneous multi-cloud environments. In response to the growing demand for efficient storage resource management (SRM) in these environments, this paper proposes an intent-based storage management (IBSM) system powered by a fine-tuned large language model (LLM). To overcome the limitations of existing methods, the IBSM system focuses on enhancing the controllability, completeness, and reliability of SRM in multi-cloud environments. Specifically, the IBSM system employs a dual-phase joint intent classification algorithm, which leverages a fine-tuned LLM to accurately identify user intents across diverse knowledge backgrounds. Additionally, the system constructs a collaborative intent decomposition method, which guarantees the integrity of intents. Furthermore, the system integrates an automated intent deployment mechanism that supports error recovery through checkpoints. Experimental results show that the system achieves a whole end-to-end (E2E) lifecycle for managing user intents. The E2E time is reduced by at least half compared to the manual approach, with an average of 50.14% dedicated to interactive tasks. Performance metrics for intent classification, including accuracy, precision, and recall, all exceed 90%. Moreover, the recovery time is reduced by an average of 30.6%. Therefore, the system provides a valuable solution for the autonomous management of multi-cloud resources.https://ieeexplore.ieee.org/document/10975014/Autonomous managementcloud computingcloud-network integrationintent-based networkinglarge language modelmulti-cloud
spellingShingle Jingya Zheng
Gaofeng Tao
Shuxin Qin
Dan Wang
Zhongjun Ma
Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language Model
IEEE Access
Autonomous management
cloud computing
cloud-network integration
intent-based networking
large language model
multi-cloud
title Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language Model
title_full Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language Model
title_fullStr Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language Model
title_full_unstemmed Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language Model
title_short Intent-Based Multi-Cloud Storage Management Powered by a Fine-Tuned Large Language Model
title_sort intent based multi cloud storage management powered by a fine tuned large language model
topic Autonomous management
cloud computing
cloud-network integration
intent-based networking
large language model
multi-cloud
url https://ieeexplore.ieee.org/document/10975014/
work_keys_str_mv AT jingyazheng intentbasedmulticloudstoragemanagementpoweredbyafinetunedlargelanguagemodel
AT gaofengtao intentbasedmulticloudstoragemanagementpoweredbyafinetunedlargelanguagemodel
AT shuxinqin intentbasedmulticloudstoragemanagementpoweredbyafinetunedlargelanguagemodel
AT danwang intentbasedmulticloudstoragemanagementpoweredbyafinetunedlargelanguagemodel
AT zhongjunma intentbasedmulticloudstoragemanagementpoweredbyafinetunedlargelanguagemodel