Transformer area power load prediction method and prediction device

Abstract

The invention relates to the technical field of power load prediction, and provides a transformer area power load prediction method and prediction device, and the method comprises the steps: collecting transformer area power load data at a first preset moment, and obtaining a first data vector; inputting the first data vector into a trained prediction neural network, so that the prediction neuralnetwork outputs transformer area power load data at a second preset moment, wherein the prediction neural network comprises an encoder and a decoder connected with the encoder, the encoder and the decoder are realized based on a time convolution network, the encoder is used for performing feature extraction on the first data vector to obtain a first feature vector, and the decoder is used for calculating a second data vector according to the first feature vector and taking the second data vector as transformer area power load data at a second preset moment. According to the technical scheme provided by the invention, the power load of the transformer area can be accurately and efficiently predicted.

Description

technical field [0001] The invention relates to the technical field of power load forecasting, in particular to a power load forecasting method for a station area and a power load forecasting device for a station area. Background technique [0002] Deep learning technology is more and more widely used in the prediction of time series data, especially the wide application of recurrent neural network (Recurrent Neural Network, RNN), and the long short-term memory network (Long Short-term Memory Network) on the neural network. The high precision of Term Memory (LSTM) and Gated Recurrent Unit (GRU) makes neural networks more and more popular in the field of power load forecasting. The neural network used to predict the power load of the station area is generally called the forecasting neural network. [0003] However, in the prior art, the stability problem of predictive neural network training has always existed, and the phenomenon of gradient disappearance often occurs. Since...

AI Technical Summary

Problems solved by technology

[0003] However, in the prior art, the stability problem of predictive neural network training has always existed, and the phenomenon of gradient disappearance often occurs. Since all intermediate results need to be saved before the entire training task is completed, the calculation intensity is relatively strong. The system memory capacity consumed by long sequence data for training input is also large

In addition, the existing predictive neural network only reads and parses one value in the input sequence data at a time, and the predictive neural network must wait for the previous value to be processed before processing the next value, which makes large-scale parallel processing difficult. Finish

[0004] The above shortcomings of the existing forecasting neural network lead to inaccurate forecasting of power load in the station area, and the timeliness is not high

Images