small-area-level ultra-short-term load prediction and visualization method based on a deep LSTM network

Abstract

The invention provides a small area-level ultra-short-term load prediction and visualization method based on a Long Short-Term Memory (LSTM) network, the method comprising: step 1: an input and outputvariable of the model is determined; step 2: The input and output data sets are separately preprocessed; step 3: the depth LSTM load prediction model is constructed and the random search method is used to find the appropriate hyperparameters until the test set prediction error is minimized. step 4: The t-SNE visualization technology is used to visually characterize the network hidden layer vector, and the correlation coefficient heat map is formed according to the hidden layer vector to perform correlation quantitative analysis, thereby reflecting the network's ability to extract feature datafrom the input data. The method aims to utilize the feature extraction capabilities of the deep learning model and the LSTM temporal correlation learning capabilities to achieve higher prediction accuracy than the machine learning model.

Description

technical field [0001] The invention relates to a small area-level ultra-short-term load forecasting method based on a deep long-short-term memory network under the background of big data, and a visual representation of its learning ability. Background technique [0002] Very short term load forecasting (VSTLF) forecasting generally refers to the load forecasting within one hour after the current moment, and is mainly used for making intraday and real-time power generation plans. With the increase of distributed energy sources, the randomness of load changes brings greater challenges to the accuracy of load forecasting. In the competitive environment of the power market, the results of ultra-short-term load forecasting are an important basis for determining the liquidation price in the real-time power market. Excessive forecast errors will cause a surge in operating costs. Therefore, the improvement of the accuracy of ultra-short-term load forecasting is of great significan...

AI Technical Summary

Problems solved by technology

With the increase of distributed energy sources, the randomness of load changes brings greater challenges to the accuracy of load forecasting. In the competitive environment of the power market, the results of ultra-short-term load forecasting are an important basis for determining the liquidation price in the real-time power market. Excessive forecast error will cause a surge in operating costs

Images