Smart meters with faults or errors can cause economic losses to power grid companies, and the hidden safety hazards can also easily affect the stable operation of the power grid, especially for smart grid systems with complex components. Aiming at this problem, non-intrusive remote detection and location of faulted electricity meters based on a super-state hidden Markov model (SSHMM) is proposed in this paper. This method can not only find the meter which has failed but also estimate the meter which is most likely to fail and provide a reference for the operation and management of the power grid enterprises. Experimental results on real data sets verify the efficiency and stability of the proposed method.
