Cooperative Overbooking-Based Resource Allocation and Application Placement in UAV-Mounted Edge Computing for Internet of Forestry Things
Due to the high mobility and low cost, unmanned aerial vehicle (UAV)-mounted edge computing (UMEC) provides an efficient way to provision computing offloading services for Internet of Forestry Things (IoFT) applications in forest areas without sufficient infrastructure. Multiple IoFT applications ca...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/1/22 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588634485686272 |
|---|---|
| author | Xiaoyu Li Long Suo Wanguo Jiao Xiaoming Liu Yunfei Liu |
| author_facet | Xiaoyu Li Long Suo Wanguo Jiao Xiaoming Liu Yunfei Liu |
| author_sort | Xiaoyu Li |
| collection | DOAJ |
| description | Due to the high mobility and low cost, unmanned aerial vehicle (UAV)-mounted edge computing (UMEC) provides an efficient way to provision computing offloading services for Internet of Forestry Things (IoFT) applications in forest areas without sufficient infrastructure. Multiple IoFT applications can be consolidated into fewer UAV-mounted servers to improve the resource utilization and reduce deployment costs with the precondition that all applications’ Quality of Service (QoS) can be met. However, most existing application placement schemes in UMEC did not consider the dynamic nature of the aggregated computing resource demand. In this paper, the resource allocation and application placement problem based on fine-grained cooperative overbooking in UMEC is studied. First, for the two-tenant overbooking case, a Two-tenant Cooperative Resource Overbooking (2CROB) scheme is designed, which allows tenants to share resource demand violations (RDVs) in the cooperative overbooking region. In 2CROB, an aggregated-resource-demand minimization problem is modeled, and a bisection search algorithm is designed to obtain the minimized aggregated resource demand. Second, for the multiple-tenant overbooking case, a Proportional Fairness-based Cooperative Resource Overbooking (PF-MCROB) scheme is designed, and a bisection search algorithm is also designed to obtain the corresponding minimized aggregated resource demand. Then, on the basis of PF-MCROB, a First Fit Decreasing-based Cooperative Application Placement (FFD-CAP) scheme is proposed to accommodate applications in as few servers as possible. Simulation results verify that the proposed cooperative resource overbooking schemes can save more computing resource in cases including more tenants with higher or differentiated resource demand violation ratio (RDVR) thresholds, and the FFD-ACP scheme can reduce about one third of necessarily deployed UAVs compared with traditional overbooking. Thus, applying efficient cooperative overbooking in application placement can considerably reduce deployment and maintenance costs and improve onboard computing resource utilization and operating revenues in UMEC-aided IoFT applications. |
| format | Article |
| id | doaj-art-82b26d2d271b4b4087ba2d87a1d79756 |
| institution | Kabale University |
| issn | 2504-446X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-82b26d2d271b4b4087ba2d87a1d797562025-01-24T13:29:40ZengMDPI AGDrones2504-446X2024-12-01912210.3390/drones9010022Cooperative Overbooking-Based Resource Allocation and Application Placement in UAV-Mounted Edge Computing for Internet of Forestry ThingsXiaoyu Li0Long Suo1Wanguo Jiao2Xiaoming Liu3Yunfei Liu4College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaDue to the high mobility and low cost, unmanned aerial vehicle (UAV)-mounted edge computing (UMEC) provides an efficient way to provision computing offloading services for Internet of Forestry Things (IoFT) applications in forest areas without sufficient infrastructure. Multiple IoFT applications can be consolidated into fewer UAV-mounted servers to improve the resource utilization and reduce deployment costs with the precondition that all applications’ Quality of Service (QoS) can be met. However, most existing application placement schemes in UMEC did not consider the dynamic nature of the aggregated computing resource demand. In this paper, the resource allocation and application placement problem based on fine-grained cooperative overbooking in UMEC is studied. First, for the two-tenant overbooking case, a Two-tenant Cooperative Resource Overbooking (2CROB) scheme is designed, which allows tenants to share resource demand violations (RDVs) in the cooperative overbooking region. In 2CROB, an aggregated-resource-demand minimization problem is modeled, and a bisection search algorithm is designed to obtain the minimized aggregated resource demand. Second, for the multiple-tenant overbooking case, a Proportional Fairness-based Cooperative Resource Overbooking (PF-MCROB) scheme is designed, and a bisection search algorithm is also designed to obtain the corresponding minimized aggregated resource demand. Then, on the basis of PF-MCROB, a First Fit Decreasing-based Cooperative Application Placement (FFD-CAP) scheme is proposed to accommodate applications in as few servers as possible. Simulation results verify that the proposed cooperative resource overbooking schemes can save more computing resource in cases including more tenants with higher or differentiated resource demand violation ratio (RDVR) thresholds, and the FFD-ACP scheme can reduce about one third of necessarily deployed UAVs compared with traditional overbooking. Thus, applying efficient cooperative overbooking in application placement can considerably reduce deployment and maintenance costs and improve onboard computing resource utilization and operating revenues in UMEC-aided IoFT applications.https://www.mdpi.com/2504-446X/9/1/22IoToverbookingapplication placementUAVmobile edge computing |
| spellingShingle | Xiaoyu Li Long Suo Wanguo Jiao Xiaoming Liu Yunfei Liu Cooperative Overbooking-Based Resource Allocation and Application Placement in UAV-Mounted Edge Computing for Internet of Forestry Things Drones IoT overbooking application placement UAV mobile edge computing |
| title | Cooperative Overbooking-Based Resource Allocation and Application Placement in UAV-Mounted Edge Computing for Internet of Forestry Things |
| title_full | Cooperative Overbooking-Based Resource Allocation and Application Placement in UAV-Mounted Edge Computing for Internet of Forestry Things |
| title_fullStr | Cooperative Overbooking-Based Resource Allocation and Application Placement in UAV-Mounted Edge Computing for Internet of Forestry Things |
| title_full_unstemmed | Cooperative Overbooking-Based Resource Allocation and Application Placement in UAV-Mounted Edge Computing for Internet of Forestry Things |
| title_short | Cooperative Overbooking-Based Resource Allocation and Application Placement in UAV-Mounted Edge Computing for Internet of Forestry Things |
| title_sort | cooperative overbooking based resource allocation and application placement in uav mounted edge computing for internet of forestry things |
| topic | IoT overbooking application placement UAV mobile edge computing |
| url | https://www.mdpi.com/2504-446X/9/1/22 |
| work_keys_str_mv | AT xiaoyuli cooperativeoverbookingbasedresourceallocationandapplicationplacementinuavmountededgecomputingforinternetofforestrythings AT longsuo cooperativeoverbookingbasedresourceallocationandapplicationplacementinuavmountededgecomputingforinternetofforestrythings AT wanguojiao cooperativeoverbookingbasedresourceallocationandapplicationplacementinuavmountededgecomputingforinternetofforestrythings AT xiaomingliu cooperativeoverbookingbasedresourceallocationandapplicationplacementinuavmountededgecomputingforinternetofforestrythings AT yunfeiliu cooperativeoverbookingbasedresourceallocationandapplicationplacementinuavmountededgecomputingforinternetofforestrythings |