The IEC 61850 Sampled Measured Values Protocol: Analysis, Threat Identification, and Feasibility of Using NN Forecasters to Detect of Spoofed Packets

As contemporary smart grid operation is expected to be heavily reliant on distributed microprocessor-based control, a strong need arises for interoperability standards to address the heterogeneous nature of the data in the smart grid. With the emergence of IEC 61850 as a strong industry-accepted interoperability standard, electronic instrument transformers and merging units are being utilized to digitize and transmit current and voltage measurements as Sampled Measured Values. Realizing the importance of feedback measurements for the reliable operation of the smart grid, firstly, this paper presents a detailed analysis of the Sampled Measured Values protocol and its benefits, then, it identifies its vulnerabilities and derives the associated cyber threats. Secondly, current security measures are outlined and, thirdly, the feasibility of using neural network forecasters to detect spoofed sampled values is investigated. It was shown that although neural network forecasters have high spoofed data detection accuracy, their performance decreases with the accumulation of forecasting error.