Heartbeat Driven Network Health Assessment
Kristaps Felzenbergs, Linas Bukauskas, Ginta Majore · 2023
We live in a fast-growing digital century where devices such as light bulbs, electrical cords, air refreshers, and other home appliances are becoming part of smart devices, leading to a fast-growing network with less trusted and less predictable computer network ecosystems than ever. This growth poses new threats that could not be easily identified using a common threat assessment and even with industry-leading anomaly-detecting machine learning solutions. Such solutions involve hard manual work on filtering out anomalies as network data patterns change similarly to human behavior. To get a trusted network health measurement, we propose a technique where we attempt to identify commonly known network errors or diseases. Further, we measure the network's heartbeat to see the current stress level, similar to a doctor's visit for a human. Finally, we show results from our experiments, giving an example of what the proposed methodology would output.