A new method for recognition and classification of power quality disturbances based on IAST and RF

Vigorously developing new energy sources such as wind power and photovoltaics will promote the low-carbon transformation of the power system. With the increase of the penetration rate of distributed energy in the distribution network, many complex and changeable power quality disturbance have been generated, which will seriously affect the stability of the distribution network. This paper presents a new method for effectively identifying and classifying the complex and variable PQDs, which is based on proposed improved adaptive S-transform (IAST) and random forest (RF). The IAST first employs proposed iterative loop filter envelope extremum algorithm which can effectively detect the main frequency points of PQDs, followed by proposed time-frequency resolution optimization improvement method that optimally adjusts the standard deviation σ to adaptively control the Gaussian window width D. In addition, a parameter F is used to make IAST more flexible. Through IAST, various PQDs features can be extracted, and then which will be classified using Random Forest (RF). To demonstrate the effectiveness of the proposed method, extensive tests are conducted on the diverse simulation PQDs and the actual data obtained from the practical power systems. The work in this paper can provide a good choice for the design and development of an intelligent monitoring and analysis system for distribution network disturbances. © 2023 Elsevier B.V.