计算机应用与软件2026，Vol.43Issue(6)：155-162,8.DOI:10.3969/j.issn.1000-386x.2026.06.022
融合注意力机制和节点嵌入的FlexE资源分配研究
RESEARCH ON FLEXE RESOURCE ALLOCATION BY INTEGRATING ATTENTION MECHANISM AND NODE EMBEDDING
摘要
Abstract
To address the issue of low accuracy in predicting network traffic for FlexE clients,an attention mechanism that can better capture local contextual information of network traffic sequences is designed.The node embedding method was introduced into the prediction model to extract personalized features of different FlexE clients.To reduce the significant increase in parameter size caused by node embedding,a matrix decomposition method was proposed.We allocated the FlexE calendar slot based on the prediction results and compared the performance of different resource allocation method.The experimental results demonstrate the effectiveness of the proposed method.关键词
灵活以太网/资源分配/流量预测/深度学习Key words
Flexible Ethernet/Resource allocation/Traffic prediction/Deep learning分类
信息技术与安全科学引用本文复制引用
冯宝,姚月月,曲志坚..融合注意力机制和节点嵌入的FlexE资源分配研究[J].计算机应用与软件,2026,43(6):155-162,8.基金项目
国家电网有限公司总部科技项目(5700-202116378A-0-0-00) （5700-202116378A-0-0-00）
山东省高等学校青年创新团队发展计划项目(2019KJN48). （2019KJN48）
