Research and Application of BP Neural Network in Specific Power Harmonic Detection

Abstract

APF (Active Power Filter) is widely used in power system harmonic control and reactive power compensation, has been proven as an effective method to overcome various power quality issues such as unbalanced source current, large reactive power harmonic and neutral currents due to the proliferation of nonlinear loads. Optimizing the performance of APF using conventional ip-iq detection method based on instantaneous reactive power theory is quite difficult because of the complex coordinate conversion, what’s more, the presence of low-pass filter will cause a certain delay. This paper proposes the implementation of BP neural network to extract specific harmonic, it can optimize the APF performance for load compensation under distorted supply voltage condition and sudden load fluctuation. Weight adjustment using the BFGS quasi-Newton algorithm, which can accurately detect the fundamental and harmonic component of the phase amplitude . Matlab simulation results demonstrate that the performance of BP neural network algorithm is superior compared to conventional method, in terms of both convergence rate and solution quality.

Application Research of BP Neural Network Algorithm in Power Line Loss Calculation

“…This is also a new development strategy of artificial neural network model and opens up a new theoretical method for calculating the line loss of distribution system. But in general, the current level is still in the exploratory stage, because neural networks lack general network design methods, they rely on experimental methods used in practice, so they are limited by practical use [2][3][4].…”

“…This is also a new development strategy of artificial neural network model and opens up a new theoretical method for calculating the line loss of distribution system. But in general, the current level is still in the exploratory stage, because neural networks lack general network design methods, they rely on experimental methods used in practice, so they are limited by practical use[2][3][4].In recent years, line calculation and management software has been widely used and evaluated. From previous versions of DOS in the current window: release procedure, from simple line loss calculation to line loss management system, from the line loss management system to the senior DMS and EMS software part, from the application of independence to the network exchange, from network connection from the calculation to network computing, from interactive-to-interactive visual data and graphic integrated management, and is a leap compared to a few years ago.…”

Harmonic Detection for Harmonic/Inter‐Harmonic Based on Improved Glowworm Swarm Optimization and Neural Network

“…The harmonics/inter‐harmonics can be detected by updating and iterating of the network to minimize the performance index [20,21]. After accomplishing the training process, the exact harmonics/inter‐harmonics frequency, amplitude, and phase can be obtained by updating the excitation function parameters and the network weight W .…”