The invention discloses a malicious behavior detection method based on non-intrusive power
terminal time sequence monitoring. The method comprises the following steps that S1,
edge computing equipmentconstructs a
database of historical electrical quantities of power
terminal equipment; S2, a
power consumption behavior
data set is constructed for each power terminal device; S3, event detection iscarried out on the electrical quantity
time series of each power terminal, a sample set is obtained after
feature extraction, and a load classifier is trained; S4, event detection is carried out on the
electric power total outlet electric quantity
time series, features are extracted and input into the trained classifier model, and the equipment type to which the
electric power terminal to be detected belongs is determined; S5, the
power consumption information of the to-be-tested power terminal is counted; S6, the
power consumption behavior of the to-be-detected power terminal is detected, andwhether the power consumption equipment is abnormal or not is determined according to the power consumption behavior; and S7, the
edge computing device records and reports an exception. On the basisof non-intrusive power
terminal time sequence monitoring, online detection of malicious behaviors of the power
terminal equipment is realized through comparison with power utilization behaviors formedby the historical power information.