Verified Telemetry: A General, Easy to use, Scalable and Robust Fault Detection SDK for IoT Sensors

With the proliferation of IoT sensors, the reliance on sensor telemetry has never been greater. Today numerous applications from smart agriculture to smart buildings and cities, rely on IoT telemetry to provide insights and to take decisions. However, due to the characteristics of these IoT deployments (in the wild, harsh conditions), sensors are prone to failures, leading to the generation of bad/dirty data. Hitherto, data-centric algorithms were used to determine the quality of the sensed data, which has several limitations and relies on additional contextual information or sensor redundancy. Recently, system-centric approaches based on sensor fingerprinting has shown to detect sensor faults reliably without any additional information. However, the sensor fingerprinting approach is validated only for specific sensors, is not robust to real-world conditions, and cannot scale to large-scale deployments. To this end, we propose a general, easy-to-use, scalable, and robust fault detection SDK called Verified Telemetry (VT) SDK. VT SDK builds on the sensor fingerprinting approach and can work with a wide variety of sensors (both analog and digital) and IoT devices with very minimal changes. We propose improved sensor fingerprinting algorithms that are robust to signal variations, sensor circuitry, and real-world conditions. VT SDK is implemented across numerous devices and we show its usage on several practical applications. Finally, VT SDK is made available for the community to address sensor fault detection in IoT deployments (https://aka.ms/verifiedtelemetry).