Computation Offloading in a Cognitive Vehicular Networks with Vehicular Cloud Computing and Remote Cloud Computing
To satisfy the explosive growth of computation-intensive vehicular applications, we investigated the computation offloading problem in a cognitive vehicular networks (CVN). Specifically, in our scheme, the vehicular cloud computing (VCC)- and remote cloud computing (RCC)-enabled computation offloadi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/23/6820 |
| _version_ | 1797546307011739648 |
|---|---|
| author | Shilin Xu Caili Guo |
| author_facet | Shilin Xu Caili Guo |
| author_sort | Shilin Xu |
| collection | DOAJ |
| description | To satisfy the explosive growth of computation-intensive vehicular applications, we investigated the computation offloading problem in a cognitive vehicular networks (CVN). Specifically, in our scheme, the vehicular cloud computing (VCC)- and remote cloud computing (RCC)-enabled computation offloading were jointly considered. So far, extensive research has been conducted on RCC-based computation offloading, while the studies on VCC-based computation offloading are relatively rare. In fact, due to the dynamic and uncertainty of on-board resource, the VCC-based computation offloading is more challenging then the RCC one, especially under the vehicular scenario with expensive inter-vehicle communication or poor communication environment. To solve this problem, we propose to leverage the VCC’s computation resource for computation offloading with a perception-exploitation way, which mainly comprise resource discovery and computation offloading two stages. In resource discovery stage, upon the action-observation history, a Long Short-Term Memory (LSTM) model is proposed to predict the on-board resource utilizing status at next time slot. Thereafter, based on the obtained computation resource distribution, a decentralized multi-agent Deep Reinforcement Learning (DRL) algorithm is proposed to solve the collaborative computation offloading with VCC and RCC. Last but not least, the proposed algorithms’ effectiveness is verified with a host of numerical simulation results from different perspectives. |
| first_indexed | 2024-03-10T14:28:42Z |
| format | Article |
| id | doaj.art-fb3c0828350249fa8a485e95f866113c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T14:28:42Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fb3c0828350249fa8a485e95f866113c2023-11-20T22:49:59ZengMDPI AGSensors1424-82202020-11-012023682010.3390/s20236820Computation Offloading in a Cognitive Vehicular Networks with Vehicular Cloud Computing and Remote Cloud ComputingShilin Xu0Caili Guo1Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaBeijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaTo satisfy the explosive growth of computation-intensive vehicular applications, we investigated the computation offloading problem in a cognitive vehicular networks (CVN). Specifically, in our scheme, the vehicular cloud computing (VCC)- and remote cloud computing (RCC)-enabled computation offloading were jointly considered. So far, extensive research has been conducted on RCC-based computation offloading, while the studies on VCC-based computation offloading are relatively rare. In fact, due to the dynamic and uncertainty of on-board resource, the VCC-based computation offloading is more challenging then the RCC one, especially under the vehicular scenario with expensive inter-vehicle communication or poor communication environment. To solve this problem, we propose to leverage the VCC’s computation resource for computation offloading with a perception-exploitation way, which mainly comprise resource discovery and computation offloading two stages. In resource discovery stage, upon the action-observation history, a Long Short-Term Memory (LSTM) model is proposed to predict the on-board resource utilizing status at next time slot. Thereafter, based on the obtained computation resource distribution, a decentralized multi-agent Deep Reinforcement Learning (DRL) algorithm is proposed to solve the collaborative computation offloading with VCC and RCC. Last but not least, the proposed algorithms’ effectiveness is verified with a host of numerical simulation results from different perspectives.https://www.mdpi.com/1424-8220/20/23/6820vehicular cloud computingremote cloud computinglong short term memory networkdeep reinforcement learningcomputation offloadingvehicular network |
| spellingShingle | Shilin Xu Caili Guo Computation Offloading in a Cognitive Vehicular Networks with Vehicular Cloud Computing and Remote Cloud Computing Sensors vehicular cloud computing remote cloud computing long short term memory network deep reinforcement learning computation offloading vehicular network |
| title | Computation Offloading in a Cognitive Vehicular Networks with Vehicular Cloud Computing and Remote Cloud Computing |
| title_full | Computation Offloading in a Cognitive Vehicular Networks with Vehicular Cloud Computing and Remote Cloud Computing |
| title_fullStr | Computation Offloading in a Cognitive Vehicular Networks with Vehicular Cloud Computing and Remote Cloud Computing |
| title_full_unstemmed | Computation Offloading in a Cognitive Vehicular Networks with Vehicular Cloud Computing and Remote Cloud Computing |
| title_short | Computation Offloading in a Cognitive Vehicular Networks with Vehicular Cloud Computing and Remote Cloud Computing |
| title_sort | computation offloading in a cognitive vehicular networks with vehicular cloud computing and remote cloud computing |
| topic | vehicular cloud computing remote cloud computing long short term memory network deep reinforcement learning computation offloading vehicular network |
| url | https://www.mdpi.com/1424-8220/20/23/6820 |
| work_keys_str_mv | AT shilinxu computationoffloadinginacognitivevehicularnetworkswithvehicularcloudcomputingandremotecloudcomputing AT cailiguo computationoffloadinginacognitivevehicularnetworkswithvehicularcloudcomputingandremotecloudcomputing |