Short-Term Power Load Forecasting Method Based on Time Convolutional Neural Network for HPLC High Frequency Data Acquisition

Power load forecasting is an important link to improve system reliability, economy and power quality. With the rise of smart grid, the accuracy of load forecasting has been given higher expectations. However, some factors, such as weather, economy and date type, will interfere with load forecasting. In this regard, this paper takes these factors into full consideration in the forecasting process to improve the accuracy of the prediction. By taking advantage of the advantages of time convolutional neural network (TCN) in dealing with nonlinear problems, it establishes a power load forecasting model based on TCN by analyzing the characteristics of load data, and conducts experiments on its short-term load forecasting and ultra-short-term load forecasting respectively. At the same time, the results of short-term load prediction are compared with those of BP neural network model. The results show that TCN can well predict the load data in the next 24 hours, and it is more accurate than BP neural network prediction.