Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks
This paper investigates the computation offloading problem in mobile edge computing (MEC) networks with dynamic weighted tasks. We aim to minimize the system utility of the MEC network by jointly optimizing the offloading decision and bandwidth allocation problems. The optimization of joint offloadi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/11/4088 |
| _version_ | 1797491703402201088 |
|---|---|
| author | Shicheng Yang Gongwei Lee Liang Huang |
| author_facet | Shicheng Yang Gongwei Lee Liang Huang |
| author_sort | Shicheng Yang |
| collection | DOAJ |
| description | This paper investigates the computation offloading problem in mobile edge computing (MEC) networks with dynamic weighted tasks. We aim to minimize the system utility of the MEC network by jointly optimizing the offloading decision and bandwidth allocation problems. The optimization of joint offloading decisions and bandwidth allocation is formulated as a mixed-integer programming (MIP) problem. In general, the problem can be efficiently generated by deep learning-based algorithms for offloading decisions and then solved by using traditional optimization methods. However, these methods are weakly adaptive to new environments and require a large number of training samples to retrain the deep learning model once the environment changes. To overcome this weakness, in this paper, we propose a deep supervised learning-based computational offloading (DSLO) algorithm for dynamic computational tasks in MEC networks. We further introduce batch normalization to speed up the model convergence process and improve the robustness of the model. Numerical results show that DSLO only requires a few training samples and can quickly adapt to new MEC scenarios. Specifically, it can achieve <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99</mn><mo>%</mo></mrow></semantics></math></inline-formula> normalized system utility by using only four training samples per MEC scenario. Therefore, DSLO enables the fast deployment of computation offloading algorithms in future MEC networks. |
| first_indexed | 2024-03-10T00:53:09Z |
| format | Article |
| id | doaj.art-a5493602a26b4de8bb18ccad5f842fba |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:53:09Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a5493602a26b4de8bb18ccad5f842fba2023-11-23T14:48:25ZengMDPI AGSensors1424-82202022-05-012211408810.3390/s22114088Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing NetworksShicheng Yang0Gongwei Lee1Liang Huang2The College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, ChinaThe College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaThe College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaThis paper investigates the computation offloading problem in mobile edge computing (MEC) networks with dynamic weighted tasks. We aim to minimize the system utility of the MEC network by jointly optimizing the offloading decision and bandwidth allocation problems. The optimization of joint offloading decisions and bandwidth allocation is formulated as a mixed-integer programming (MIP) problem. In general, the problem can be efficiently generated by deep learning-based algorithms for offloading decisions and then solved by using traditional optimization methods. However, these methods are weakly adaptive to new environments and require a large number of training samples to retrain the deep learning model once the environment changes. To overcome this weakness, in this paper, we propose a deep supervised learning-based computational offloading (DSLO) algorithm for dynamic computational tasks in MEC networks. We further introduce batch normalization to speed up the model convergence process and improve the robustness of the model. Numerical results show that DSLO only requires a few training samples and can quickly adapt to new MEC scenarios. Specifically, it can achieve <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99</mn><mo>%</mo></mrow></semantics></math></inline-formula> normalized system utility by using only four training samples per MEC scenario. Therefore, DSLO enables the fast deployment of computation offloading algorithms in future MEC networks.https://www.mdpi.com/1424-8220/22/11/4088mobile-edge computingdeep learningcomputation offloading |
| spellingShingle | Shicheng Yang Gongwei Lee Liang Huang Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks Sensors mobile-edge computing deep learning computation offloading |
| title | Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks |
| title_full | Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks |
| title_fullStr | Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks |
| title_full_unstemmed | Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks |
| title_short | Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks |
| title_sort | deep learning based dynamic computation task offloading for mobile edge computing networks |
| topic | mobile-edge computing deep learning computation offloading |
| url | https://www.mdpi.com/1424-8220/22/11/4088 |
| work_keys_str_mv | AT shichengyang deeplearningbaseddynamiccomputationtaskoffloadingformobileedgecomputingnetworks AT gongweilee deeplearningbaseddynamiccomputationtaskoffloadingformobileedgecomputingnetworks AT lianghuang deeplearningbaseddynamiccomputationtaskoffloadingformobileedgecomputingnetworks |