DEEP REINFORCEMENT LEARNING-BASED INDUSTRIAL 5G DYNAMIC MULTI-PRIORITY MULTI-ACCESS METHOD | |
Yu HB(于海斌); Liu XY(刘晓宇); Xu C(许驰); Zeng P(曾鹏); Jin X(金曦); Xia CQ(夏长清) | |
2021-11-18 | |
著作权人 | SHENYANG INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES |
国家 | 世界专利组织 |
文献子类 | 发明 |
产权排序 | 1 |
其他题名 | 基于深度强化学习的工业5G动态多优先级多接入方法 |
英文摘要 | The present invention relates to industrial 5G network technology, and specifically relates to a deep reinforcement learning-based industrial 5G dynamic multi-priority multi-access method. The method comprises the following steps: establishing an industrial 5G network model; establishing a deep reinforcement learning-based dynamic multi-priority multi-channel access neural network model; collecting status, action, and reward information of all industrial 5G terminals in the industrial 5G network in multiple time slots as training data; using the collected data to train the neural network model until the packet loss rate and end-to-end delay meet requirements for industrial communication; collecting status information of all industrial 5G terminals in the industrial 5G network in a current time slot and using same as an input of the neural network model for multi-priority channel allocation, and the industrial 5G terminals perform multiple access according to the channel allocation results. The present invention may efficiently perform multi-channel allocation with industrial 5G terminals of different priorities in an industrial 5G network in real time, and ensure large-scale concurrent access. |
申请日期 | 2020-12-25 |
语种 | 英语 |
状态 | 公开 |
内容类型 | 专利 |
源URL | [http://ir.sia.cn/handle/173321/30139] |
专题 | 沈阳自动化研究所_工业控制网络与系统研究室 |
作者单位 | SHENYANG INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES |
推荐引用方式 GB/T 7714 | Yu HB,Liu XY,Xu C,et al. DEEP REINFORCEMENT LEARNING-BASED INDUSTRIAL 5G DYNAMIC MULTI-PRIORITY MULTI-ACCESS METHOD. 2021-11-18. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论