Load Reduction for Timely Applications in the Cloud

In many IoT applications, sensor data is sent remotely to be processed, but only the freshest result is of interest. In this letter we investigate a feedback mechanism that aborts the processing of stale data at the remote end to reduce the load and save costs. The process is approximated by an M/M/ $\infty $ queueing system with a feedback loop. We find the exact expression of the average computational time saved and show that with the feedback loop in place the computation time per CPU can be cut up to 25%, making the technique very promising.