Multi-agent reinforcement learning driven resource game optimization for network slicing in MEC-enabled HetNets
Kai Mao · 2025
Read Multi-agent reinforcement learning driven resource game optimization for network slicing in MEC-enabled HetNets by Kai Mao (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12830975.txt.
Description
Kai Mao, writing in 2025, tackles a hard problem in new mobile networks: how to share edge computing power fairly among competing network slices. Each slice serves a different kind of traffic, and each one wants more resources than the network can give. Mao joins two tools into one scheme. The first lets many software agents learn from trial and error. The second borrows from game theory to track how choices spread and settle.
In the scheme, each tenant acts as an agent that picks how much resource to request. A ranking step focuses attention on the most useful signals, and a credit step scores what each agent adds. In tests built on real data, the scheme beat two rival methods on total value, on meeting service promises, and on how fully resources were used. It also adapted well when conditions changed.
Catalog record
| CREATOR | Kai Mao |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 28 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |