Cloud–Edge Collaborative Model Adaptation Based on Deep Q-Network and Transfer Feature Extraction
With the rapid development of smart devices and the Internet of Things (IoT), the explosive growth of data has placed increasingly higher demands on real-time processing and intelligent decision making. Cloud-edge collaborative computing has emerged as a mainstream architecture to address these chal...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/15/8335 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849770757462163456 |
|---|---|
| author | Jue Chen Xin Cheng Yanjie Jia Shuai Tan |
| author_facet | Jue Chen Xin Cheng Yanjie Jia Shuai Tan |
| author_sort | Jue Chen |
| collection | DOAJ |
| description | With the rapid development of smart devices and the Internet of Things (IoT), the explosive growth of data has placed increasingly higher demands on real-time processing and intelligent decision making. Cloud-edge collaborative computing has emerged as a mainstream architecture to address these challenges. However, in sky-ground integrated systems, the limited computing capacity of edge devices and the inconsistency between cloud-side fusion results and edge-side detection outputs significantly undermine the reliability of edge inference. To overcome these issues, this paper proposes a cloud-edge collaborative model adaptation framework that integrates deep reinforcement learning via Deep Q-Networks (DQN) with local feature transfer. The framework enables category-level dynamic decision making, allowing for selective migration of classification head parameters to achieve on-demand adaptive optimization of the edge model and enhance consistency between cloud and edge results. Extensive experiments conducted on a large-scale multi-view remote sensing aircraft detection dataset demonstrate that the proposed method significantly improves cloud-edge consistency. The detection consistency rate reaches 90%, with some scenarios approaching 100%. Ablation studies further validate the necessity of the DQN-based decision strategy, which clearly outperforms static heuristics. In the model adaptation comparison, the proposed method improves the detection precision of the A321 category from 70.30% to 71.00% and the average precision (AP) from 53.66% to 53.71%. For the A330 category, the precision increases from 32.26% to 39.62%, indicating strong adaptability across different target types. This study offers a novel and effective solution for cloud-edge model adaptation under resource-constrained conditions, enhancing both the consistency of cloud-edge fusion and the robustness of edge-side intelligent inference. |
| format | Article |
| id | doaj-art-20f8e2d76c5844feb3042005fa65b0b0 |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-20f8e2d76c5844feb3042005fa65b0b02025-08-20T03:02:55ZengMDPI AGApplied Sciences2076-34172025-07-011515833510.3390/app15158335Cloud–Edge Collaborative Model Adaptation Based on Deep Q-Network and Transfer Feature ExtractionJue Chen0Xin Cheng1Yanjie Jia2Shuai Tan3Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 200237, ChinaShanghai Aerospace Electronic Technology Institute, Shanghai 201109, ChinaKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 200237, ChinaKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 200237, ChinaWith the rapid development of smart devices and the Internet of Things (IoT), the explosive growth of data has placed increasingly higher demands on real-time processing and intelligent decision making. Cloud-edge collaborative computing has emerged as a mainstream architecture to address these challenges. However, in sky-ground integrated systems, the limited computing capacity of edge devices and the inconsistency between cloud-side fusion results and edge-side detection outputs significantly undermine the reliability of edge inference. To overcome these issues, this paper proposes a cloud-edge collaborative model adaptation framework that integrates deep reinforcement learning via Deep Q-Networks (DQN) with local feature transfer. The framework enables category-level dynamic decision making, allowing for selective migration of classification head parameters to achieve on-demand adaptive optimization of the edge model and enhance consistency between cloud and edge results. Extensive experiments conducted on a large-scale multi-view remote sensing aircraft detection dataset demonstrate that the proposed method significantly improves cloud-edge consistency. The detection consistency rate reaches 90%, with some scenarios approaching 100%. Ablation studies further validate the necessity of the DQN-based decision strategy, which clearly outperforms static heuristics. In the model adaptation comparison, the proposed method improves the detection precision of the A321 category from 70.30% to 71.00% and the average precision (AP) from 53.66% to 53.71%. For the A330 category, the precision increases from 32.26% to 39.62%, indicating strong adaptability across different target types. This study offers a novel and effective solution for cloud-edge model adaptation under resource-constrained conditions, enhancing both the consistency of cloud-edge fusion and the robustness of edge-side intelligent inference.https://www.mdpi.com/2076-3417/15/15/8335reinforcement learningtransfer feature extractionQ-learningobject detectioncloud-edge collaborationmodel adaptation |
| spellingShingle | Jue Chen Xin Cheng Yanjie Jia Shuai Tan Cloud–Edge Collaborative Model Adaptation Based on Deep Q-Network and Transfer Feature Extraction Applied Sciences reinforcement learning transfer feature extraction Q-learning object detection cloud-edge collaboration model adaptation |
| title | Cloud–Edge Collaborative Model Adaptation Based on Deep Q-Network and Transfer Feature Extraction |
| title_full | Cloud–Edge Collaborative Model Adaptation Based on Deep Q-Network and Transfer Feature Extraction |
| title_fullStr | Cloud–Edge Collaborative Model Adaptation Based on Deep Q-Network and Transfer Feature Extraction |
| title_full_unstemmed | Cloud–Edge Collaborative Model Adaptation Based on Deep Q-Network and Transfer Feature Extraction |
| title_short | Cloud–Edge Collaborative Model Adaptation Based on Deep Q-Network and Transfer Feature Extraction |
| title_sort | cloud edge collaborative model adaptation based on deep q network and transfer feature extraction |
| topic | reinforcement learning transfer feature extraction Q-learning object detection cloud-edge collaboration model adaptation |
| url | https://www.mdpi.com/2076-3417/15/15/8335 |
| work_keys_str_mv | AT juechen cloudedgecollaborativemodeladaptationbasedondeepqnetworkandtransferfeatureextraction AT xincheng cloudedgecollaborativemodeladaptationbasedondeepqnetworkandtransferfeatureextraction AT yanjiejia cloudedgecollaborativemodeladaptationbasedondeepqnetworkandtransferfeatureextraction AT shuaitan cloudedgecollaborativemodeladaptationbasedondeepqnetworkandtransferfeatureextraction |