A power load forecasting method, device and storage medium for a distribution network

Abstract

This application discloses the power load prediction method, device and storage medium of the power distribution network.The dataset is performed by the power load prediction to obtain the power load dataset in the target area within the target time period after the current moment;Preset machine learning models and determine the preset machine learning model as the current machine learning model; based on the current machine learning model, the sample dataset operation is performed to obtain the convolutional feature collection; based on the description;Confluing features to determine the loss value; based on the loss value, the power load prediction model is determined.Through the electric load prediction model applied for this application, the power load data of the future in the future can be quickly and accurately predicted.

Description

technical field [0001] The present application relates to the technical field of power load forecasting, in particular to a power load forecasting method, device and storage medium for a distribution network. Background technique [0002] With the continuous development of the energy industry, how to efficiently allocate power resources and reduce energy waste has become an important issue in the energy field. According to the findings of B.F.Hobbs et al., every 1% reduction in the average error percentage of power load demand forecasting can save 10000Mw of power resources. Accurate power load forecasting plays an important role in energy allocation and sustainable development. [0003] Traditional research on power load forecasting is mainly based on models such as regression analysis, time series, and recurrent neural networks. The method of regression analysis is affected by many factors (such as weather, policies, geographical conditions, etc.) in the actual power loa...

AI Technical Summary

Problems solved by technology

The method of regression analysis is affected by many factors (such as weather, policies, geographical conditions, etc.) in the actual power load system, and it is difficult to learn nonlinear and complex changing laws from historical loads, so the prediction results have limitations.

Due to the diversity of influencing factors and the non-stationary characteristics of the power load curve, the time series analysis method makes the forecasting system not robust

In recent years, the recurrent neural network and the long short-term memory recurrent neural network, which have been widely used in the field of electric load, due to the recurrent characteristics of their network structure, make the prediction speed too slow, which is limited in practical applications.

Images