Design of Power Quality Steady State Index Evaluation System under the Background of Big Data

Abstract

In order to further optimize the operation mode of China's power grid and improve the
quality of power supply in the grid, in this study, according to the non-periodic and periodic
characteristics of the steady state index of power quality, a power quality steady-state index
evaluation and prediction system based on chaotic system theory and least squares support
vector machine (LSSVM) in large data background is designed. First, Firstly, chaotic
system theory is used to reconstruct the phase space of the historical data of classical power
quality steady-state indices, and to construct a new data information space covering
attractors. Then, the LSSVM is used to train the samples in high-dimensional space, and the
particle swarm optimization (PSO) algorithm is used together to get the best index
evaluation and prediction system model. At the same time, the system is applied to the
actual monitoring of the electric energy treatment capacity of a distribution network in a
certain place. The typical steady-state index of power quality is used to evaluate and
monitor, and the average relative error is less than 7%. Obviously, the result is better than
the traditional back propagation (BP) neural network prediction method, which proves that
the power quality steady-state index evaluation system based on chaotic system theory and
least squares support vector machine under large data can be widely used.