Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement Learning
With the increasing computational demands of Internet of Things (IoT) applications, air-ground integrated networks (AGIN), leveraging the capabilities of Unmanned Aerial Vehicles (UAVs) and High-Altitude Platform (HAP), provides an essential solution to these challenges. In this paper, we propose a...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of Vehicular Technology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10768987/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583133313105920 |
|---|---|
| author | Vitou That Kimchheang Chhea Jung-Ryun Lee |
| author_facet | Vitou That Kimchheang Chhea Jung-Ryun Lee |
| author_sort | Vitou That |
| collection | DOAJ |
| description | With the increasing computational demands of Internet of Things (IoT) applications, air-ground integrated networks (AGIN), leveraging the capabilities of Unmanned Aerial Vehicles (UAVs) and High-Altitude Platform (HAP), provides an essential solution to these challenges. In this paper, we propose a framework that facilitates local computing at IoT devices and offers the flexibility to offload tasks to aerial platforms when necessary. Specifically, we formulate a multi-objective optimization model aiming at simultaneously minimizing energy consumption and reducing task latency by adjusting control variables such as transmit power, offloading decisions, and UAV placement in a distributed network of IoT devices. Our proposed framework employs Deep Deterministic Policy Gradient (DDPG) techniques to dynamically optimize network operations, allowing for efficient real-time adjustments to network conditions and task demands. The performance of the proposed algorithm is compared to traditional algorithms, including the Whale Optimization Algorithm (WOA), Gradient Search with Barrier, and Bayesian Optimization (BO). Simulation results show that this approach significantly minimizes energy consumption and latency, outperforming conventional optimization methods. Additionally, scalability tests confirm that our framework can efficiently integrate an increasing number of IoT devices and UAVs. |
| format | Article |
| id | doaj-art-0160a6c040894c8097e1305ada567a63 |
| institution | Kabale University |
| issn | 2644-1330 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Vehicular Technology |
| spelling | doaj-art-0160a6c040894c8097e1305ada567a632025-01-29T00:01:35ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302025-01-01641242510.1109/OJVT.2024.350728810768987Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement LearningVitou That0https://orcid.org/0009-0006-5221-5945Kimchheang Chhea1https://orcid.org/0000-0002-4389-5233Jung-Ryun Lee2https://orcid.org/0000-0001-7372-5692Department of Intelligent Energy Industry Convergence, Chung-Ang University, Seoul, South KoreaDepartment of Intelligent Energy Industry, Chung-Ang University, Seoul, South KoreaDepartment of Intelligent Energy Industry, Chung-Ang University, Seoul, South KoreaWith the increasing computational demands of Internet of Things (IoT) applications, air-ground integrated networks (AGIN), leveraging the capabilities of Unmanned Aerial Vehicles (UAVs) and High-Altitude Platform (HAP), provides an essential solution to these challenges. In this paper, we propose a framework that facilitates local computing at IoT devices and offers the flexibility to offload tasks to aerial platforms when necessary. Specifically, we formulate a multi-objective optimization model aiming at simultaneously minimizing energy consumption and reducing task latency by adjusting control variables such as transmit power, offloading decisions, and UAV placement in a distributed network of IoT devices. Our proposed framework employs Deep Deterministic Policy Gradient (DDPG) techniques to dynamically optimize network operations, allowing for efficient real-time adjustments to network conditions and task demands. The performance of the proposed algorithm is compared to traditional algorithms, including the Whale Optimization Algorithm (WOA), Gradient Search with Barrier, and Bayesian Optimization (BO). Simulation results show that this approach significantly minimizes energy consumption and latency, outperforming conventional optimization methods. Additionally, scalability tests confirm that our framework can efficiently integrate an increasing number of IoT devices and UAVs.https://ieeexplore.ieee.org/document/10768987/Internet of Things (IoT)air-ground integrated networks (AGIN)edge computingDeep Deterministic Policy Gradient (DDPG)UAV placementsmulti-objective optimization |
| spellingShingle | Vitou That Kimchheang Chhea Jung-Ryun Lee Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement Learning IEEE Open Journal of Vehicular Technology Internet of Things (IoT) air-ground integrated networks (AGIN) edge computing Deep Deterministic Policy Gradient (DDPG) UAV placements multi-objective optimization |
| title | Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement Learning |
| title_full | Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement Learning |
| title_fullStr | Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement Learning |
| title_full_unstemmed | Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement Learning |
| title_short | Optimizing Energy Consumption and Latency in IoT Through Edge Computing in Air–Ground Integrated Network With Deep Reinforcement Learning |
| title_sort | optimizing energy consumption and latency in iot through edge computing in air x2013 ground integrated network with deep reinforcement learning |
| topic | Internet of Things (IoT) air-ground integrated networks (AGIN) edge computing Deep Deterministic Policy Gradient (DDPG) UAV placements multi-objective optimization |
| url | https://ieeexplore.ieee.org/document/10768987/ |
| work_keys_str_mv | AT vitouthat optimizingenergyconsumptionandlatencyiniotthroughedgecomputinginairx2013groundintegratednetworkwithdeepreinforcementlearning AT kimchheangchhea optimizingenergyconsumptionandlatencyiniotthroughedgecomputinginairx2013groundintegratednetworkwithdeepreinforcementlearning AT jungryunlee optimizingenergyconsumptionandlatencyiniotthroughedgecomputinginairx2013groundintegratednetworkwithdeepreinforcementlearning |