Clustering and neural network-based power quality prediction method for a power distribution network containing a distributed power supply

Abstract

The invention discloses a clustering and neural network-based power quality prediction method for a power distribution network containing a distributed power supply. The method comprises the steps oftraining data acquisition and normalization processing; performing clustering division on the historical input data set; dividing a training set and a verification set; enabling BP neural network prediction to perform model training; Solving an optimal training set division mode; obtaining predicted input variable values and normalizing the predicted input variable values; determining cluster affiliation of the input variable value; performing electric energy quality prediction output and reverse normalization; making a power quality prediction result assessment. The method has the advantagesthat 1, the BP neural network is used for effectively predicting the power quality of the DG-containing power distribution network; 2, a k-means algorithm is used to carry out classification preprocessing on the neural network training set by using a means clustering algorithm, and providing different prediction models for each class, so as to overcome the defect that a BP neural network is easy to fall into a local optimal solution, and obviously reduce the prediction error; and 3, the training set, the verification set division mode and the hidden layer node number N are circularly changed for multiple times, and the probability of obtaining the optimal model is improved.

Description

technical field [0001] The invention relates to a method for predicting the power quality of a distribution network containing distributed power sources based on clustering and neural networks, which belongs to the fields of electrical engineering and power quality. Background technique [0002] The main indicators to measure power quality (Power Quality) are voltage, frequency and waveform. Because the constant 50Hz frequency and sinusoidal waveform of the ideal power system are difficult to achieve in the actual state, excessive deviation will cause electrical equipment to fail or not work properly, which leads to power quality problems. It mainly includes voltage deviation, frequency deviation, voltage fluctuation and flicker, instantaneous or transient overvoltage, three-phase unbalance, waveform distortion, voltage sag, swell, interruption and power supply continuity. Nowadays, the research and application of power quality mainly focus on power quality monitoring, anal...

AI Technical Summary

Problems solved by technology

The patent with the application number 201611063183.7 proposes a method for predicting the fluctuation coefficient of the grid impedance identification error of photovoltaic grid-connected points. The data set after dynamic clustering is input into the neural network prediction model, but the prediction object is the fluctuation coefficient of the impedance identification error, which does not directly affect the electric energy. predictions made by quality

Images