IT Infrastructure Benchmarking for Real-Time Video Analytics Deployment: Edge, Elastic-Container and Centralized Data Center Models

I. INTRODUCTION

Real-time video analytics workloads such as retail footfall counting are often bursty by nature, tied to business hours or events, making elastic, pay-per-use IT infrastructure attractive despite known concerns about cold-start latency for compute-heavy, GPU-dependent inference tasks.

II. METHODOLOGY

An identical YOLOv8-based object detection video analytics pipeline was deployed on two elastic-container platforms and a baseline centralized data center deployment on reserved GPU nodes, and benchmarked under three synthetic traffic patterns, constant load, business-hours load, and bursty event-triggered load, measuring end-to-end frame processing latency, monthly infrastructure cost, and cold-start frequency.

III. RESULTS AND EVALUATION

The centralized baseline achieved the lowest steady-state per-frame latency at 82 milliseconds versus 134 milliseconds and 151 milliseconds for the two elastic-container platforms, but under the bursty event-triggered traffic pattern, the elastic-container platforms reduced monthly cost by 58 percent and 51 percent respectively relative to the always-on centralized baseline, at the cost of an average cold-start penalty of 1.9 seconds affecting the first request after an idle period.

IV. CONCLUSION

The choice between elastic-container and centralized IT infrastructure for real-time video analytics should be driven by traffic pattern: elastic platforms offer substantial cost advantages for bursty workloads that can tolerate occasional cold-start latency, while steady high-throughput workloads remain better served by reserved infrastructure. Future work will evaluate provisioned-concurrency options to mitigate cold-start penalties.

V. REFERENCES