TVF-EMD-MCQRNN load probability prediction method based on fuzzy C-means clustering

Abstract

The invention discloses a TVF-EMD-MCQRNN load probability prediction method based on fuzzy C-means clustering. The method comprises the following steps: 1, preprocessing power loads and influence factors thereof, and grouping the preprocessed power loads and influence factors thereof according to a set time interval; 2, dividing the grouped data sets into training sets and test sets, and respectively clustering each group of training sets and test sets by using a fuzzy C-means clustering method; 3, training and testing the TVF-EMD-MCQRNN model by utilizing the various types of training set andtest set sample data to obtain a series of conditional quantiles of the various types of sample data under different quantiles; 4, summing the conditional quantiles of each type of sample data underthe same quantile to obtain each type of prediction result, thereby realizing probability density prediction. According to the method, the accuracy of load prediction can be improved, and therefore more comprehensive and more effective load information is provided for operation planning of a power system.

Description

technical field [0001] The invention belongs to the technical field of short-term power load forecasting, in particular to a TVF-EMD-MCQRNN load probability forecasting method based on fuzzy C-means clustering. Background technique [0002] Electric load forecasting is an important part of power system planning and plays a vital role in the energy distribution and management of modern power systems. High-precision load forecasting is conducive to the power system to formulate a reasonable power generation plan while meeting the electricity demand of users, so as to effectively control the planning and operation costs of the power system. However, as new energy sources, such as wind energy, solar energy and other intermittent energy sources are connected to the grid on a large scale, it brings great challenges to the security, stability and economic operation of the grid. Compared with the general power load point forecasting method, the probabilistic load forecasting method...

AI Technical Summary

Problems solved by technology

[0003] However, with the continuous increase in the scale of power systems and the rapid development of emerging technologies, traditional power load forecasting technology is limited by the current power environment, and it is difficult to adapt to the nonlinear, random and chaotic characteristics of modern power load data for reasonable modeling. , therefore, in order to obtain more accurate load forecasting results, it is necessary to continuously update and optimize the research on load forecasting algorithms to maintain the advanced

In addition, the influencing factors of power load are becoming more and more complex, and the degree of influence of these factors on load accuracy is fuzzy, and a single forecasting model can no longer meet the needs of modern load forecasting

Most of the relevant research is to improve the accuracy of load forecasting by optimizing the intelligent algorithm forecasting model, and does not preprocess these uncertain factors, ignoring the information value of the historical load data itself

At the same time, the analysis of power load data is becoming more and more difficult, and ordinary data preprocessing is difficult to fully tap the value of the data itself

Images