Dong Dai
Henan Mechanical and Electrical Engineering College

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

The Power Load Prediction Based on Improved Genetic Neural Network Dong Dai; Lin-Chao Ma
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 4: April 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

There exist nonlinear and high redundancy between the power load factors, and the traditional methods in neural network can not eliminate the redundancy in the prediction data and capture the nonlinear characteristics, resulting in lower prediction precision of the power load. In order to improve the prediction precision of the power load, a power load prediction method based on improved genetic algorithm optimization neural network (IGA-BP) is put forward. First, the power load is reconstructed using the correlation function, and then performed the normalization processing. Secondly, the power load training sample is input into the BP neural network for learning, and then the initial connection weights and thresholds of the BP neural network are selected using the improved genetic algorithm. Finally, the power load prediction model is established. Simulation results show that the improved neural network can reflect the trend of complex non-linear power load, achieve higher power load fitting and prediction precision, and is an effective load prediction method for power system. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4302
Algorithm of Multi Sensor Data Fusion based on BP Neural Network and Multi-scale Model Predictive Control Guo Wang; Dong Dai
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 7: July 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i7.pp5316-5323

Abstract

Multi sensor data fusion is the data from multiple sensors and information from the relevant database are combined, which obtained judgment and description that can not achieve the goal, more accurate and complete by any single sensor. BP neural network is a kind of artificial neural network based on error back-propagation algorithm. It adopts adding hidden layer, to estimate the error directly leading layer of output layer by the error output. The paper presents Algorithm of multi sensor data fusion based on BP neural network and multi-scale model predictive control. The multi-scale model predictive control can not only obtain the previous information, and increase the flexibility in modeling and optimal phase.