Day-ahead power load prediction method and device based on double-end automatic coding

Abstract

The invention relates to a day-ahead power load prediction method based on double-end automatic coding, and the method comprises the following steps: obtaining influence factor features which need tobe considered and have an influence on a power load, and forming a historical power load and influence factor feature database; constructing an auto-encoder 1, training the auto-encoder 1, and inputting historical power load characteristic data into the trained auto-encoder 1 to obtain a fused data set; constructing a neural network, training the neural network, and inputting the obtained fused data set into the trained neural network for power load prediction; constructing an auto-encoder 2, and training the auto-encoder 2; inputting the obtained power load prediction data into the trained auto-encoder 2; performing reverse normalization on the obtained decoded power load prediction data to obtain final day-ahead power load data. According to the method, the dimension problem in day-aheadload prediction is solved, and the precision of day-ahead load prediction is improved.

Description

technical field [0001] The invention belongs to the technical field of intelligent power distribution and utilization, and in particular relates to a day-ahead power load forecasting method and device based on double-ended automatic coding. Background technique [0002] Load forecasting is an important basic analysis tool for energy management and optimal scheduling of large power grids. It can guide power companies to economically and rationally arrange the start-stop and maintenance plans of generating units, guarantee the normal production and life of the society, effectively reduce power generation costs, and improve economic efficiency. benefits and social benefits. At the same time, load forecasting is also a basic function and an important analysis tool for intelligent power distribution. The development and construction of intelligent power distribution takes safety and reliability, high quality and efficiency, and flexible interaction as the main goals, and puts fo...

AI Technical Summary

Problems solved by technology

[0004] The main problem of day-ahead load forecasting is that the operation of load has a time-dependent relationship, and load changes in the past period of time often have a greater impact on the load of the next day

However, when historical load is used as a feature, its dimension is very high, and the feature redundancy is serious, so it is difficult to model accurately in existing models

In addition, with the increase of power system measurement frequency, day-ahead load forecasting is also facing the challenge of dimension expansion of forecasting results

Images