Power grid fault diagnosis system and method based on multi-source heterogeneous data

The invention discloses a power grid fault diagnosis system and method based on multi-source heterogeneous data, and relates to the field of data processing, and the method comprises the steps: obtaining a power grid network topological structure, a topological position corresponding to a power failure region, and electrical quantity data in the region; respectively loading each type of electrical quantity before and after a fault and at a fault moment into different matrix models, inputting data into the matrix models from eight matrix angles according to a time sequence, supplementing default data, normalizing the matrix models to be the same in size, adjusting each matrix model, executing DTW operation among the matrix models, and obtaining a DTW model; and a DTW distance matrix used for finding a power grid fault line is obtained, a difference degree matrix is calculated, and according to the difference degree matrix, an artificial fish cluster clustering algorithm is adopted to carry out optimization sol