Power load prediction method, system and equipment for eliminating noise and medium

The invention provides a noise-eliminating power load prediction method, system and device and a medium, and the method comprises the steps: constructing a Transform load prediction model with a variable selection network based on a Transform algorithm; and modeling the data to be subjected to power load prediction into a data distribution, and inputting the data distribution as an input variable into the Transform load prediction model to eliminate data noise contained in the data to be subjected to power load prediction. According to the method, the prediction precision and the robustness of the Transform load prediction model are ensured. 本发明提供一种消除噪声的电力负荷预测方法、系统、设备及介质，所述方法包括：基于Transformer算法，构建具有变量选择网络的Transformer负荷预测模型；将待电力负荷预测的数据建模为一个数据分布，并将所述数据分布作为输入变量输入至Transformer负荷预测模型中，以消除待电力负荷预测的数数据中含有的数据噪声。本发明保证了预测的精度和Transformer负荷预测模型的稳健性。