Electricity purchase structure optimization analysis method and system

The invention discloses a power purchase structure optimization analysis method and system, belongs to the technical field of electric power, and solves the problem that power purchase risk factors and risk values in current power purchase data cannot be evaluated when power purchase cost prediction is performed in a machine learning classification model in an existing method. The method comprises the steps of performing normalization processing on multi-source heterogeneous real-time power purchase data to obtain a normalized power purchase vector and a data analysis instruction; the risk assessment model analyzes the normalized power purchase vector, identifies risk factors in the real-time power purchase data, and calculates the comprehensive risk quantity of the risk factors; judging whether the comprehensive risk quantity exceeds a preset risk threshold value or not; according to the embodiment of the invention, by constructing the risk assessment model and the optimization analysis model, the normalized