Short-Term Load Forecasting and Temperature Load Extraction Based on CEEMDAN and TDIC

Abstract

With the intensification of urbanization in various countries worldwide, the temperature load which is greatly affected by ambient temperature, such as summer cooling loads and winter heating loads, accounts for a rising proportion of the total urban load. It causes an increasing peak-to-valley load difference. However, due to the complex composition and strong randomness of the load, it is necessary to study the multi-scale and multi-period correlation between temperature. Based on this, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to decompose the temperature and load into multi-scale components. The time-dependent intrinsic correlation (TDIC) is proposed to analyze the local correlation between temperature and load in multiple periods under a multi-scale framework, and obtain the dynamic change characteristics of the correlation between temperature and load. Based on the TDIC analysis results, a suitable sample period for short-term load forecasting (STLF) and input temperature data can be selected. Finally, extreme learning machine optimized by particle swarm optimization (PSO-ELM) is used to forecast each component of the load. The proposed STLF method is validated on real-time data from the Pennsylvania-New Jersey-Maryland (PJM) Company in the United States. The proposed method has greatly reduced in both mean absolute percentage error (MAPE) and root mean square error (RMSE) compared with other traditional methods, and the temperature load that fluctuates with temperature in the day to be forecasted is extracted.