arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.14283cs.NIcs.LG
收藏

MILD:基于意图的网络中面向主动故障预测的多意图学习与歧义消除

MILD: Multi-Intent Learning and Disambiguation for Proactive Failure Prediction in Intent-based Networking

Information and Computer Science Department, King Fahd University of Petroleum and Minerals(信息与计算机科学系,国王法赫德石油与矿物大学);IRC for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals(智能安全系统研究组,国王法赫德石油与矿物大学)

Md. Kamrul Hossain, Walid Aljoby

AI总结:

MILD通过主动故障预测和意图层面的歧义消除,提升了意图基网络中故障修复前置时间及根本原因识别准确性。

摘要:

在多意图意图基网络中,单一故障可能引发共漂移,其中多个意图表现出症状性KPI退化,导致真实根本原因意图的歧义。我们提出了MILD,一个主动框架,将意图保证从反应性漂移检测重新公式化为具有固定时间范围的故障预测,并在意图层面进行歧义消除。MILD使用了教师增强的专家混合模型,其中一个门控歧义模块识别根本原因意图,而每个意图的头部输出校准的风险分数。在具有非线性故障和共漂移的基准测试中,MILD提供了3.8%至92.5%更长的修复前置时间,并在意图层面将根本原因歧义消除准确性提高了9.4%至45.8%相比基线。MILD还提供了每个警报的KPI解释,使可操作的诊断成为可能。

英文摘要:

In multi-intent intent-based networks, a single fault can trigger co-drift where multiple intents exhibit symptomatic KPI degradation, creating ambiguity about the true root-cause intent. We present MILD, a proactive framework that reformulates intent assurance from reactive drift detection to fixed-horizon failure prediction with intent-level disambiguation. MILD uses a teacher-augmented Mixture-of-Experts where a gated disambiguation module identifies the root-cause intent while per-intent heads output calibrated risk scores. On a benchmark with non-linear failures and co-drifts, MILD provides 3.8\%--92.5\% longer remediation lead time and improves intent-level root-cause disambiguation accuracy by 9.4\%--45.8\% over baselines. MILD also provides per-alert KPI explanations, enabling actionable diagnosis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑