Dissertation > Excellent graduate degree dissertation topics show

Research and Application on Prediction Method Based on Gray Theory and Neural Network

Author: WengXiaoJie
Tutor: SongZhongShan
School: Central South University for Nationalities
Course: Computer Applications
Keywords: gray system theory GM(1,1) artificial neural network BP neural network power load
CLC: F407.61
Type: Master's thesis
Year: 2009
Downloads: 409
Quote: 15
Read: Download Dissertation

Abstract


Power load forecasting is a complex nonlinear dynamic systems .It is difficult to reflect electricity consumption with trait of more factors, nonlinear and time variety using the traditional timing prediction technology .In real life there are also much similar to the type of power load forecasting problem exist, the forecasting method of traditional power load would not meet the requirement for accurate prediction .It necessary to find a new method to forecast the power load.Firstly this article analyzed gray system theory and artificial neural network theory and their respective advantages and disadvantages .And then made more detailed description of the gray prediction modeling ideal and theory, for the existing problems of gray neural network model, which set up based on the discrete response function, this article made some exploration and study in the initial data smoothing treatment, and background correction treatment and error compensation treatment.This article sufficient made use of the advantages of the gray prediction model required less information and easy, and take advantage of the characteristics, which neural networks have a strong nonlinear mapping ability, using the least square method to determine the initial value of parameters in the gray differential equations, thus get network’s initial weights and thresholds. And also use the optimized combination for the neural network prediction model and gray prediction model, which in order to avoid the risk of low prediction accuracy of a single prediction model. Because of improved gray prediction model and neural network prediction has advantages complement each other, use the combination of these prediction algorithms can improve prediction accuracy at a large extent.Finally, this article elaborated the significance of the power system load forecasting, in view of historical data on electricity consumption in Shanxi Province, Separately use the gray forecasting model, improved gray forecasting model, neural network prediction model, gray theory and neural network combination prediction model predicted the electricity consumption in Shanxi Province, then made analysis and evaluation for the prediction results.

Related Dissertations

  1. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  2. The Development of Soft System for Power Load Management Terminal Testing Device,TP311.52
  3. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  4. Research on Visual Servo System of Mechanical ARM,TP242.6
  5. Municipal tourism land use planning environmental impact assessment,X820.3
  6. Research on the Inteligent System of High Performance Concrete Mix Design in Zhujiang Triangle Area,TU528
  7. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  8. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  9. The Research of Evaluation Method in Connect6 Based on BP-TD Learning,TP18
  10. Analysis on Water Ecological Carrying Capacity of Jiangxi Province,TV213.4
  11. Transfusion gas natural gas pipeline network load research and forecasting,TE973.6
  12. Mixed steel processing operations for resource allocation method,F426.31
  13. Context of Chinese 3G mobile customer relationship and satisfaction evaluation study,F626;F274
  14. Very large crude oil tankers overall energy efficiency design key technology research,U662
  15. Research and Implementation of Computer Game Strategy Based on Reinforcement Learning,TP18
  16. Reacher on the Hydraulic Control System of Roadheader Robot,TD421.5
  17. Controlling and Optimization Research on Concrete Shrinkage Deformation Based on Artificial Neural Network,TP183
  18. Study on Cement Fineness Features Based on the Durability of Road Concrete,TQ172.12
  19. Short - term load forecasting , energy management system based on support vector machines,TM715
  20. Short-term Power Load Forecasting Based on the Particle Swarm Optimization Algorithm,TM715
  21. BP Neural Network Forecasting Model Based on PSO,TP183

CLC: > Economic > Industrial economy > Industrial economic theory > Industrial sector economy > Electrical and electronics industry > Electricity, motor industry
© 2012 www.DissertationTopic.Net  Mobile