Abstract: Aiming at the key link of the digital construction of the new power system, a smart identification method for power internet of things（IoT）terminals based on business baselines is proposed. The method collects flow messages from power IoT terminals, analyzes data distribution characteristics, and defines the business baseline of power IoT terminals. The feature vectors from the terminal devices that need to be identified are extracted, matching them with the business baseline, so as to achieve intelligent identification of power IoT terminal devices that communicate using Modbus RTU protocol. To verify the effectiveness of the method, 10 types of power internet of things terminal devices are collected to receive autonomously constructed Modbus message frames continuously 10 times per unit time, and corresponding response data are returned. The results show that when the threshold is higher than 0.08, the recognition accuracy is high, and the proposed method does not require complex feature extraction, and the recognition accuracy is high.

Key words: electric power internet of things, terminal devices, intelligent recognition, business baseline, feature vectors