A method for detecting abnormal value of new energy power quality

Abstract

The invention discloses a method for detecting abnormal value of new energy power quality. position and the corresponding optimal fitness value, update the number of iterations until it meets the requirements or reaches the maximum number of iterations, and outputs the optimal individual position and optimal fitness value; after the processing of the optimal individual; according to the data objects in the sample and clustering The Euclidean distance of the centers is the nearest criterion to divide them into the nearest cluster centers; update the cluster centers; judge whether the values ​​of the cluster centers and the objective function have changed. The invention can reduce the influence of noise on the data, and can find the data cluster center point for abnormal value detection even when the data sample is not very large, and has the advantages of fast convergence speed, high data accuracy, good stability and the like.

Description

technical field [0001] The invention relates to a method for detecting abnormal value of new energy power quality based on K-means-IWOA algorithm, and belongs to the technical field of power quality detection and analysis of power grids. Background technique [0002] In recent years, the rapid development of social economy and the continuous improvement of social productivity, the speed of social energy consumption is getting faster and faster, all of which are accelerating people's demand for energy. However, it is accompanied by environmental pollution problems, as well as the limitations of traditional fossil fuel reserves and mining. Accelerates the pace of people's development of clean and renewable energy. Wind energy, as the earliest renewable energy source, has been effectively optimized and improved with years of research and exploration. The wind power generation technology has been widely used in the power supply network. In addition, the rise of photovoltaic po...

AI Technical Summary

Problems solved by technology

However, it is difficult to find an optimal support vector machine kernel function and parameters, so the selection of kernel function and parameters is the key to the problem and directly affects the classification results.

The algorithm of the artificial immune system needs to find a better training method through a large number of training samples, which limits the speed of the algorithm in practical applications.

Existing abnormal data detection methods have problems such as poor adaptability when detecting outliers for such data

Images