Author:
Zhang Wenhui,Wang Baohua,Wang Dafei,Yu Jiacheng,Zhang Chi
Abstract
Abstract
The steady-state indexes of power quality are obviously nonlinear and non-stationary under the influence of many factors, leading to the existing algorithms not to achieve high-precision prediction for power quality. Considering the excellent performance of Bi-directional Long Short-Term Memory model in time series analysis and the outstanding advantages of Bayesian algorithm in global optimization, a prediction model for power quality based on BiLSTM optimized by Bayesian is proposed. The actual data of power quality are used to test the performance of the model, and the results show that the proposed prediction model has higher accuracy and better applicability.
Subject
General Physics and Astronomy
Reference10 articles.
1. Delta-bar-delta Neural Network (NN) Based Control Approach for Power Quality Improvement of Solar PV Interfaced Distribution System;Shukl;IEEE Transactions on Industrial Informatics,2019
2. Fpga-based Online Power Quality Monitoring System for Electrical Distribution Network;Yildirim;Measurement,2018
3. Analysis and Prediction of Power Quality Trend of Electrified Railway;Gao;Computer & Digital Engineering,2019
4. Mechanism of Power Quality Forecast and Early Warning and Their Application;Ding;Proceedings of the CSU-EPSA,2015
5. Power Quality Prediction Based on Least Squares Method;Lu;Vibroengineering PROCEDIA,2017
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. LSTM-based Network for Current Harmonic Distortion Time Series Forecasting;2023 IEEE International Conference on Environment and Electrical Engineering and 2023 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe);2023-06-06
2. Wine quality prediction by several data mining classification models;Highlights in Science, Engineering and Technology;2023-05-21
3. Bayesian Financial Panel Data Model based on MCMC Sampling Algorithm;2022 Second International Conference on Advanced Technologies in Intelligent Control, Environment, Computing & Communication Engineering (ICATIECE);2022-12-16
4. A Machine-Learning Pipeline for Large-Scale Power-Quality Forecasting in the Mexican Distribution Grid;Applied Sciences;2022-08-24