Compressed Observability: Collecting a Fraction of Your Metrics and  Reconstructing the Rest with Compressed Sensing

Murali M. Chittabathini, Saketh Gowerneni, Pradeep Kandepaneni, Bhanuprakash Suravarapu, Praneeth Ganta

Compressed Observability: Collecting a Fraction of Your Metrics and Reconstructing the Rest with Compressed Sensing

Authors

Murali M. Chittabathini, Saketh Gowerneni, Pradeep Kandepaneni, Bhanuprakash Suravarapu, Praneeth Ganta

Keywords:

observability, compressed sensing, sparse recovery, telemetry, metrics, l1 minimization, restricted isometry, monitoring cost, time series, reconstruction

Abstract

Observability has a cost problem that nobodyhas solved, only deferred. Teams instrument everything,ship every metric, and pay, in storage, in network, invendor bills, to collect millions of time series, theoverwhelming majority of which are never queried andcarry almost no information beyond what their neighbours already convey. The industry response has been blunt

References

E. J. Candès, J. Romberg, and T. Tao, “Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information,” IEEE Trans. Information Theory, vol. 52, no. 2, pp. 489–509, 2006.

Downloads

Published

2026-06-29

How to Cite

Murali M. Chittabathini, Saketh Gowerneni, Pradeep Kandepaneni, Bhanuprakash Suravarapu, Praneeth Ganta. (2026). Compressed Observability: Collecting a Fraction of Your Metrics and Reconstructing the Rest with Compressed Sensing. Journal of Computational Analysis and Applications (JoCAAA), 35(6), 220–225. Retrieved from https://www.eudoxuspress.com/index.php/pub/article/view/5632