Artificial intelligence-based microgrid short-term load prediction optimization control method

Abstract

The application discloses a short-term load prediction optimization control method for a micro-grid based on artificial intelligence and belongs to the technical field of micro-grid load prediction control. The method comprises the following steps: acquiring real-time load data, meteorological data and calendar characteristic data of the micro-grid to form a multi-source time series data set; performing empirical mode decomposition processing on the multi-source time series data set to obtain a plurality of intrinsic mode function components and a residual component; constructing a prediction structure based on chaotic phase space reconstruction for each intrinsic mode function component to obtain short-term prediction values of the components; accumulating and reconstructing the short-term prediction values of the components and the prediction value of the residual component to obtain short-term load prediction values of the micro-grid; and generating power scheduling instructions of the micro-grid according to the deviation between the short-term load prediction values and actual loads by using a model prediction control framework and feeding back the power scheduling instructions to a micro-grid control system for execution.