EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Objective Balanced Optimization Task Offloading Algorithm Based on Multi-Agent Collaboration

Hui Li, Zhilong Zhu, Wanwei Huang, Bingyan Li, Zhiheng Wang, Guangsheng Wei, Jia Zhang

Future Internet · 30.07.2026 · 18 (8) · 400

DOI: 10.3390/fi18080400 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 30.07.2026. Verfasst von Hui Li und 6 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Henan Science and Technology Department, Shenzhen Science and Technology Innovation Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the development of the Internet of Things and multi-access edge computing, latency-sensitive tasks impose higher requirements on network computing capability and service quality. Existing task offloading methods usually focus on a single performance metric and often adopt time-slot-driven decision mechanisms, which may introduce additional waiting latency and increase system cost. To address these problems, this paper proposes a task-driven offloading algorithm based on Balanced Multi-Agent Deep Deterministic Policy Gradient (BMADDPG). First, a four-layer integrated air–space–ground multi-access edge computing network model is constructed, consisting of ground devices, unmanned aerial vehicles (UAVs), low-Earth-orbit (LEO) satellites, and cloud servers. Multi-level computing node collaboration is used to improve the system computing capability. Second, the task offloading process is modeled as a multi-agent Markov decision process, where ground user devices act as agents. A centralized Critic and distributed Actor structure is adopted for collaborative decision-making. The proposed algorithm uses DDPG to handle continuous action spaces and triggers offloading decisions immediately upon task arrival, thereby avoiding time-slot waiting overhead. Meanwhile, latency, energy consumption, and load balancing constraints are incorporated into the reward function to guide global resource allocation. Simulation results show that BMADDPG converges stably within about 800 training episodes. Compared with DDPG, DQN, PPO, and D3QN, it reduces average task processing latency by approximately 22.67% and decreases total system cost by at least 18.32% under high-load scenarios.

Förderung

  • Henan Science and Technology Department
  • Shenzhen Science and Technology Innovation Commission

Zitieren

APA

Li, H., Zhu, Z., Huang, W., Li, B., Wang, Z., Wei, G., & Zhang, J. (2026). Multi-Objective Balanced Optimization Task Offloading Algorithm Based on Multi-Agent Collaboration. Future Internet, 18(8), 400. https://doi.org/10.3390/fi18080400

Vancouver

Li H, Zhu Z, Huang W, Li B, Wang Z, Wei G, et al. Multi-Objective Balanced Optimization Task Offloading Algorithm Based on Multi-Agent Collaboration. Future Internet. 2026;18(8):400. doi:10.3390/fi18080400

BibTeX
@article{Li2026,
  author = {Li, Hui and Zhu, Zhilong and Huang, Wanwei and Li, Bingyan and Wang, Zhiheng and Wei, Guangsheng and Zhang, Jia},
  title = {Multi-Objective Balanced Optimization Task Offloading Algorithm Based on Multi-Agent Collaboration},
  journal = {Future Internet},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {400},
  doi = {10.3390/fi18080400}
}
Kostenlos starten →