Power grid load prediction method and system based on artificial intelligence

The invention relates to the technical field of artificial intelligence, in particular to a power grid load prediction method and system based on artificial intelligence. The method comprises the following steps: collecting historical load data of a power grid, and performing periodic correlation analysis on the historical load data in different periods; according to a correlation analysis result, utilizing a prediction neural network to obtain a prediction load sequence of the target day in different periods; selecting predicted load sequences of the same target day in different periods, performing fluctuation decomposition on the predicted load sequences, obtaining corresponding trend components, periodic components and random components, further forming a feature sequence, and obtaining an accurate predicted load of the target day by using the feature sequence. According to the embodiment of the invention, power grid load prediction is carried out through the power grid load cross correlation of different