Adversarial Reinforcement Learning-Based Converged Communication Efficiency Improvement Method for Power Distribution Network
In order to satisfy the diversified communication requirements of terminal source nodes in power distribution network, it is necessary to optimize the communication orchestration in power distribution unified communication network. Firstly, we construct the joint optimization problem of data transmi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
State Grid Energy Research Institute
2023-09-01
|
| Series: | Zhongguo dianli |
| Subjects: | |
| Online Access: | https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202210068 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In order to satisfy the diversified communication requirements of terminal source nodes in power distribution network, it is necessary to optimize the communication orchestration in power distribution unified communication network. Firstly, we construct the joint optimization problem of data transmission delay and energy consumption. Then, the joint optimization problem is modeled as a multi-armed bandit problem, and an adversarial reinforcement learning-based communication orchestration algorithm for power distribution unified communication network is proposed, which uses the historical orchestration information and the perceived adversary between source nodes to dynamically learn the communication orchestration strategy. Finally, the superior performance of the proposed algorithm is verified through simulation. |
|---|---|
| ISSN: | 1004-9649 |