Semantic scheduling of active measurements for meeting network monitoring objectives

Network control and management techniques (e.g., dynamic path switching, on-demand bandwidth provisioning) rely on active measurements of end-to-end network status. These measurements are needed to meet network monitoring objectives such as: (a) intra-domain/inter-domain paths statuschecking, (b) network weather forecasting, (c) anomaly event detection and (d) fault-diagnosis. In this paper, we present a novel semantic scheduling algorithm based on deterministic and heuristic scheduling principles to handle measurement request loads for meeting network monitoring objectives that aid in resource adaptation decisions. The semantic priorities specified to our scheduling algorithm that are based on user-level and resource-level policies allow preferential treatment of measurement requests that supercede typical scheduling priorities based on periodicity and execution time. We evaluate our semantic scheduling algorithm using metrics such as cycle time and satisfaction ratio for increasing measurement request loads. Our semantic scheduling algorithm and evaluation study findings are vital to deploy and manage large-scale measurement infrastructures used for meeting monitoring objectives in support of nextgeneration applications and networks.