Electric load forecasting method and system based on convolutional long-short-term memory neural network

Abstract

The present disclosure proposes a method and system for forecasting power consumption load based on convolutional long-short-term memory neural network, including the following steps: obtaining historical power consumption data of the power consumption system to be predicted and performing preprocessing; transmitting the preprocessed sample data to The trained multi-layer neural network including the MVCNN model and the ConvLSTM model outputs the prediction results; outputs the power distribution control scheme according to the prediction results. The multi-layer neural network disclosed in this disclosure combines the MVCNN model and the ConvLSTM model. The MVCNN model can not only extract information along the time series, but also extract fusion information between different time series feature data, thereby improving the accuracy of model recognition and reducing data. impact on the model. The ConvLSTM model can further process spatiotemporal information, encode spatial information, improve the feature extraction ability of the model, thereby improving the robustness of the model, and solve the problem of low accuracy of power load forecasting, large errors, sensitivity to data changes, and easy overfitting technical issues.

Description

technical field [0001] The present disclosure relates to the technical field related to intelligent power distribution, and in particular, relates to a method and system for predicting electric load based on a convolutional long-short-term memory neural network. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] With the acceleration of industrialization and electrification, human demand for energy has soared, especially the demand for electric energy, which is showing a rising trend year by year. In large buildings and buildings, short-term power supply and demand imbalances are common. How to effectively alleviate this situation and improve the utilization efficiency of electric energy is a pain point in the industry that needs to be solved urgently. Accurately and efficiently predicting the electricity demand of buildings is of great si...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above problems, this disclosure proposes a power load forecasting method and system based on a convolutional long-short-term memory neural network (Multi-viewConvLSTM Neural Network), which solves the problem of low power load forecasting accuracy, large errors, and sensitivity to data changes. Technical issues that are prone to overfitting

Images