In-band Network Telemetry (INT) has emerged as a promising network measurement technology. However, existing network telemetry systems lack the flexibility to meet diverse telemetry requirements and are also difficult to adapt to dynamic network environments. In this paper, we propose AdapINT, a versatile and adaptive in-band network telemetry framework assisted by dual-timescale probes, including long-period auxiliary probes (APs) and short-period dynamic probes (DPs). Technically, the APs collect basic network status information, which is used for the path planning of DPs. To achieve full network coverage, we propose an auxiliary probes path deployment (APPD) algorithm based on the Depth-First-Search (DFS). The DPs collect specific network information for telemetry tasks. To ensure that the DPs can meet diverse telemetry requirements and adapt to dynamic network environments, we apply the deep reinforcement learning (DRL) technique and transfer learning method to design the dynamic probes path deployment (DPPD) algorithm. The evaluation results show that AdapINT can redesign the telemetry system according to telemetry requirements and network environments. AdapINT can reduce telemetry latency by 75\% in online games and video conferencing scenarios. For overhead-aware networks, AdapINT can reduce control overheads by 34\% in cloud computing services.

翻译：带内网络遥测（INT）已成为一种前景广阔的网络测量技术。然而，现有网络遥测系统缺乏满足多样化遥测需求的灵活性，且难以适应动态网络环境。本文提出AdapINT——一种由双时间尺度探针（包括长周期辅助探针AP和短周期动态探针DP）辅助的通用自适应带内网络遥测框架。在技术层面，AP收集基础网络状态信息，用于DP的路径规划。为实现全网覆盖，我们提出基于深度优先搜索（DFS）的辅助探针路径部署（APPD）算法。DP则负责收集遥测任务所需的特定网络信息。为确保DP能应对多样化遥测需求并适应动态网络环境，我们应用深度强化学习（DRL）技术和迁移学习方法设计了动态探针路径部署（DPPD）算法。评估结果表明，AdapINT可根据遥测需求和网络环境重构遥测系统：在在线游戏和视频会议场景中，AdapINT可降低75%的遥测延迟；对于开销敏感型网络，AdapINT在云计算服务中可减少34%的控制开销。