System and method of validating multi-vendor Internet-of-Things (IoT) devices using reinforcement learning

A system for dynamically configuring Internet-of-Things (IoT) sensors using reinforcement learning, the system comprising:

• a processor;
• and
• a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, causes the processor to:
• generate a matching table for each of a plurality of IoT sensors based on a plurality of sensor attributes extracted from a product data associated with an IoT sensor;
• acquire an identification information and an operational information for each of the plurality of IoT sensors associated with the IoT sensor and a set of neighboring IoT sensors;
• identify an appropriate set of IoT sensors from the plurality of IoT sensors, based on a user requirement, the matching table, the identification information and the operational information, using a Reinforcement Learning (RL) model, wherein the RL model is trained to determine the appropriate set of IoT sensors by rewarding or penalizing a plurality of sets of IoT sensors based on their respective performance scores;
• determine, for each of the appropriate set of IoT sensors, a threshold time to maintain the IoT sensor in an operating mode based on a vendor type;
• acquire time series output data from the IoT sensor while the IoT sensor is working in the operating mode;
• detect a presence and a type of an anomaly based on the time series output data using one of a statistical model or an artificial neural network (ANN) model, wherein the type of the anomaly comprises one of a temporary anomaly, a malicious anomaly, a fake anomaly, or a permanent anomaly;
• verify the presence and the type of the anomaly, based on time series output data from the set of neighboring IoT sensors from the appropriate set of IoT sensors while the IoT sensor is working in the operating mode, using the ANN model;
• validate each of the set of appropriate sensors for which the presence and the type of the anomaly is verified by performing a set of validation tests;
• render a result of the validation based on at least one of a vendor type, a region, a mode of operation, and a result of operation;
• and
• dynamically configure each of the appropriate set of IoT sensors based on the vendor type.

A non-transitory computer-readable medium storing computer-executable instructions for:

• generating a matching table for each of a plurality of IoT sensors, based on a plurality of sensor attributes extracted from a product data associated with an IoT sensor;
• acquiring an identification information and an operational information for each of the plurality of IoT sensors associated with the IoT sensor and a set of neighboring IoT sensors;
• identifying an appropriate set of IoT sensors from the plurality of IoT sensors, based on a user requirement, the matching table, the identification information and the operational information, using a Reinforcement Learning (RL) model, wherein the RL model is trained to determine the appropriate set of IoT sensors by rewarding or penalizing a plurality of sets of IoT sensors based on their respective performance scores;
• determining, for each of the appropriate set of IoT sensors, a threshold time to maintain the IoT sensor in an operating mode based on a vendor type;
• acquiring a time series output data from the IoT sensor while the IoT sensor is working in the operating mode;
• detecting a presence and a type of an anomaly based on the time series output data using one of a statistical model or an artificial neural network (ANN) model, wherein the type of the anomaly comprises one of a temporary anomaly, a malicious anomaly, a fake anomaly, or a permanent anomaly;
• verifying the presence and the type of the anomaly, based on time series output data from the set of neighboring IoT sensors from the appropriate set of IoT sensors while the IoT sensor is working in the operating mode, using the ANN model;
• validating each of the set of appropriate sensors for which the presence and the type of the anomaly is verified by performing a set of validation tests;
• rendering a result of the validation based on at least one of a vendor type, a region, a mode of operation, and a result of operation;
• and
• dynamically configuring each of the appropriate set of IoT sensors based on the vendor type.