Power load prediction method based on modular recurrent neural network

Abstract

The invention relates to a power load prediction method based on a modular recurrent neural network. The method comprises the following steps: 1, constructing a recurrent neural network comprising an input layer, a hidden layer and an output layer, and dividing the hidden layer into a plurality of modules; 2, constructing different modular recurrent neural networks through different combinations of four hidden layer module updating strategies and two recurrent connection pruning strategies; 3, carrying out Z-score standardization processing on the obtained power load data, and dividing the power load data into a training set, a verification set and a test set according to a time sequence; and training the model by using the training set, adjusting parameters by using the verification set, and finally evaluating the performance on the test set. Compared with a gating recurrent neural network which is widely applied at present, the model under the framework can achieve accurate prediction of the power load while effectively reducing the network training parameter quantity. Especially, the performance of the modular recurrent neural network based on the adaptive updating strategy is most outstanding.

Description

technical field [0001] The invention relates to a power load forecasting method based on a modularized cyclic neural network. Background technique [0002] Power load forecasting plays an important role in ensuring the safe, stable and efficient operation of smart grids. From the perspective of power production, accurate forecasting helps to formulate a reasonable production plan to provide sufficient power supply while avoiding waste of resources caused by overproduction. From the perspective of electricity consumption, accurate forecasting is helpful for the rational formulation of real-time electricity prices to encourage off-peak electricity consumption. In recent years, the emergence of various high-precision data acquisition devices (such as smart meters) in smart grids has provided strong support for power load forecasting. Current methods for electric load forecasting can generally be divided into two categories: statistical analysis-based methods and data-driven m...

AI Technical Summary

Problems solved by technology

However, this mechanism creates a complex internal structure of the hidden layer, and its disadvantage is that the network parameters that need to be trained increase sharply

Images