Short-term Load Forecasting Method Based on BIRCH-CNN-GRU Model

Abstract

Residential Short-term load forecasting is an important basis for power department to make dispatching plan reasonably. A short-term load forecasting framework was proposed that is based on Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) clustering algorithm, Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU). In this framework, based on historical load data collected by smart meters, BIRCH clustering algorithm is adopted to cluster users into multiple user groups according to different users’ electricity consumption habits. A multivariate time series dataset composed of load data, time data, and climate data are into the CNN network, which is composed of a one-dimensional convolutional layer and a pooling layer. The CNN network is responsible for extracting the potential relationship and high dimensional characteristics of different variables. After that, the data are input into the GRU network, and the sequence characteristics of the time sequence data are studied. Finally, the short-term load prediction results are output from the full-connected layer. Taking the open dataset provided by the Commission for Energy Regulation (CER) of Ireland as an example, the Mean Absolute Percentage Error (MAPE) of the proposed method reached 2.932 1%. Compared with the prediction efficiency and accuracy of ANN network, CNN network, and CNN-GRU network under the same conditions, the experimental results showed that the proposed method has higher prediction accuracy and higher training efficiency.

Keywords

• short-term load forecasting
• convolutional neural network
• gated recurrent unit
• birch