Multi-wind power plant power day scene generation method with time-space correlation

Abstract

The invention discloses a multi-wind-power-plant power daily scene generation method with time-space correlation. The method comprises the steps: acquiring a daily scene data set of multiple wind power plants; clustering the day scene data set by using a tensor self-organizing mapping neural network; constructing a variational auto-encoder for each cluster, and extracting implicit features from daily scene data; performing random simulation and sampling on the daily scene data of each cluster by using the implicit features to obtain a daily scene implicit variable data set; decoding and reconstructing the daily scene implicit variable data set to obtain reconstructed daily scene data of each cluster; and aggregating the reconstructed daily scene data of each cluster to obtain a reconstructed daily scene data set. According to the method, after the daily scene samples are clustered, dimension reduction and reconstruction are carried out on the samples of all the clusters, the precision of the daily scene data generated through reconstruction is improved, the time-space correlation of the scene data is considered, space and time correlation errors of reconstruction are remarkably reduced, and the feature expression ability of the generated scene is enhanced.

Description

technical field [0001] The invention belongs to the field of renewable energy power generation and comprehensive consumption, and specifically relates to a multi-wind farm power daily scene generation method with time-space correlation. Background technique [0002] Under the strategic goals of carbon peaking and carbon neutrality, wind energy, as a renewable energy source, has the advantages of clean environmental protection and mature technology, and has been developed and applied on a large scale in my country. However, the strong randomness and intermittency of wind power output seriously affect the stable operation and economic dispatch of the power system. How to describe the uncertainty of wind power output is the key issue to overcome these challenges. The scenario analysis method analyzes the uncertainty of the power system by constructing a deterministic scenario, which has become an effective way to solve the planning and optimal operation of the power system with...

AI Technical Summary

Problems solved by technology

These deep learning technologies have achieved certain results in the generation of renewable energy day-to-day scenarios, but the existing methods uniformly transform the spatio-temporal power in the sample scene into a one-dimensional vector model after processing, resulting in the model not being able to accurately reflect the original The true distribution of power in time and space dimensions affects the accuracy of scene generation

Images