A CNN-LSTM-Based Model for Predicting Monthly Power Capacity

With the growing demand for electricity and the increasing importance of environmental sustainability, energy efficiency has become a key factor for the sustainable development of power systems. As an effective tool, power forecasting can help power companies and government departments to better plan and manage energy resources and achieve efficient use of energy. In this paper, an improved forecasting model, the hybrid CNN-LSTM model combined with clustering algorithm based on K-means, is proposed to forecast monthly power demand. In the case of insufficient training data, clustering algorithm is used to augment the existing data to improve the prediction accuracy of the hybrid CNN-LSTM model. Experimental results show that the proposed algorithm can indeed improve the prediction accuracy based on the data from agriculture and industry sectors in a province of East China.