Smart City Gnosys
Smart city article details
| Title | Multi-Layer Guided Reinforcement Learning Task Offloading Based On Softmax Policy In Smart Cities |
|---|---|
| ID_Doc | 38241 |
| Authors | Wu B.; Ma L.; Ji Y.; Cong J.; Xu M.; Zhao J.; Yang Y. |
| Year | 2025 |
| Published | Computer Communications, 235 |
| DOI | http://dx.doi.org/10.1016/j.comcom.2025.108105 |
| Abstract | Edge computing is an effective measure for addressing the high demand for computing power on the end-side due to dense task distribution in the mobile Internet. In the case of limited device resources and computing power, how to optimize the task offloading decision has become an important issue for improving computing efficiency. We improve the heuristic algorithm by combining the characteristics of intensive tasks, and optimize the task offloading decision at a lower cost. To overcome the limitation of requiring a large amount of real-time information, we utilize the RL algorithm and design a new reward function to enable the agent to learn from its interactions with the environment. Aiming at the poor performance of the system in the uncertain initial environment, we propose a Q-learning scheme based on the Softmax strategy for the multi-layer agent RL framework. The offloading process is optimized by coordinating agents with different views of the environment between each layer, while balancing the exploration and utilization relationship to improve the performance of the algorithm in a more complex dynamic environment. The experimental results show that in the mobile environment with high device density and diverse tasks, the proposed algorithm achieves significant improvements in key indicators such as task success rate, waiting time, and energy consumption. In particular, it exhibits excellent robustness and efficiency advantages in complex dynamic environments, far exceeding the current benchmark algorithm. © 2025 Elsevier B.V. |
| Author Keywords | Edge computing; Heuristic algorithms; Multi-layer agent; Reinforcement learning; Task offloading |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
38090  | 0.909 | Jiao T.; Feng X.; Guo C.; Wang D.; Song J. | Multi-Agent Deep Reinforcement Learning For Efficient Computation Offloading In Mobile Edge Computing | Computers, Materials and Continua, 76, 3 (2023) |
| 40838 | 0.902 | Liu L.; Xu Z. | Optimizing Lightweight Neural Networks For Efficient Mobile Edge Computing | Scientific Reports, 15, 1 (2025) |
| 15454 | 0.901 | Peng K.; Liu P.; Xu X.; Zhou X. | Computing Offloading Of Multi-Dependent Tasks In Smart Cities; [面向智慧城市的多依赖任务计算迁移研究] | Yingyong Kexue Xuebao/Journal of Applied Sciences, 41, 3 (2023) |
| 54443 | 0.894 | Wu B.; Ma L.; Cong J.; Zhao J.; Yang Y. | Task Offloading Strategy Based On Improved Double Deep Q Network In Smart Cities | Wireless Networks, 31, 5 (2025) |
| 34433 | 0.891 | Yao R.; Liu L.; Zuo X.; Yu L.; Xu J.; Fan Y.; Li W. | Joint Task Offloading And Power Control Optimization For Iot-Enabled Smart Cities: An Energy-Efficient Coordination Via Deep Reinforcement Learning | IEEE Transactions on Consumer Electronics (2025) |
| 54442 | 0.889 | Zhao X.; Liu M.; Li M. | Task Offloading Strategy And Scheduling Optimization For Internet Of Vehicles Based On Deep Reinforcement Learning | Ad Hoc Networks, 147 (2023) |
| 18051 | 0.887 | Agbaje P.; Nwafor E.; Olufowobi H. | Deep Reinforcement Learning For Energy-Efficient Task Offloading In Cooperative Vehicular Edge Networks | IEEE International Conference on Industrial Informatics (INDIN), 2023-July (2023) |
| 34353 | 0.874 | Chen Z.; Xiong B.; Chen X.; Min G.; Li J. | Joint Computation Offloading And Resource Allocation In Multi-Edge Smart Communities With Personalized Federated Deep Reinforcement Learning | IEEE Transactions on Mobile Computing, 23, 12 (2024) |
| 40621 | 0.871 | Hassan M.T.; Hosain M.K. | Optimization Of Computation Offloading In Mobile-Edge Computing Networks With Deep Reinforcement Approach | 2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024 (2024) |
| 21373 | 0.871 | Abdelghany H.M. | Dynamic Resource Management And Task Offloading Framework For Fog Computing | Journal of Grid Computing, 23, 2 (2025) |