Short-term load forecasting method based on multiple meteorological factors and improved TCN-LSTM

Abstract Effective scheduling plans, optimized energy deployment, and grid stability assurance hinge on precisely forecasting short-term power loads. Therefore, this paper introduces an innovative approach to short-term load forecasting that integrates meteorological factors with an enhanced TCN-LSTM methodology. Firstly, the impact of meteorological factors on loads is quantified using Pearson’s phase relationship, facilitating the identification of meteorological input variables for the short-term load forecasting model. Secondly, a novel time-series convolutional neural network (TCN) tailored to power load characteristics is developed. The introduction of a network structure adapted to the characteristics of power loads improves the TCN model, enabling the effective capture of the long-term dependence and short-term fluctuation in load data. Finally, the paper details the construction of the improved TCN-LSTM model for short-term load forecasting. The new vectors, formed based on the load data features extracted by the improved TCN, are used as inputs for LSTM for load forecasting. The proposed short-term load forecasting method is validated using load-meteorological data from a typical period in a specific area, and the results demonstrate a notable enhancement in forecasting.