Dissertation > Excellent graduate degree dissertation topics show

The Study of Energy Demand Forecasting Based on the Grey-neural Network Theory

Author: ZhangZuo
Tutor: ChenWeiDong
School: Tianjin University
Course: Management Science and Engineering
Keywords: Energy demand forecast Grey Forecasting Artificial Neural Networks Combination Forecasting Model
CLC: F426.2
Type: Master's thesis
Year: 2007
Downloads: 820
Quote: 13
Read: Download Dissertation

Abstract


Energy is an important material basis of human survival , economic development , social progress and modern civilization is indispensable . With the social and economic development , the demand for energy is growing . Therefore, the energy needs of the research has important theoretical and practical significance . In this paper, the system analysis , the method of gray system theory and artificial intelligence theory to the modeling and analysis of China's energy demand . Take a combination of qualitative and quantitative analysis of the impact of economic growth , industrial structure , energy consumption structure , the population , the level of consumption , technological progress and energy prices on energy demand . According to the time series of the total energy consumption and gross domestic product ( GDP ) from 1978 to 2005 , using cointegration analysis and Granger test , verify the cointegration relationship between China's energy consumption and economic growth ; multivariate statistical methods to analyze the the correlation between the influencing factors and energy demand , provide a quantitative prediction of the energy demand . 2 , build a new series gray neural network model of energy demand forecasts . Fewer problems in the long-term forecasts of energy demand data , the time series of the total energy demand in 1978 to 2000 to build three gray differential equations . Combined with the advantages and disadvantages of gray theory and artificial neural network theory prediction algorithm , the predictive value and impact of the gray differential equations the main factors of the energy demand at the same time as the input of the neural network to learn the gray model to predict the results of long-term trends , and to consider the impact of factors on energy demand nonlinear effects , to achieve the best fit of the predicted values ??and the values ??observed . 3 , with the 1978 to 2005 data modeling and inspection . The results show that the improved series gray neural network model to predict the results of the average relative error is 1.19% , and gray artificial neural network model of parallel and series combination forecast results than the traditional relative error of 1.15% and 1.08% . The the improved series gray neural network model to predict the total energy demand in 2010 , 2020 , results were 2.4994 billion tons of standard coal and 4.0184 billion tons of standard coal , the development of energy policy has certain reference value .

Related Dissertations

  1. Predicting Short-term Foreign Exchange Based on Wavelet Neural Network,F224
  2. Calculated and animated simulation of wet stone coal vanadium extraction process,TF841.3
  3. Study on the Water Use and Water Demand of Beijing City,TV213.4
  4. The Rapid Detection of Soil Moisture Based on Near-Infrared Spectroscopy and Machine Vision,S152.7
  5. The Hunan cultural industry competitiveness evaluation studies,F224
  6. Vegetation Factors Extraction and the Mothod of Rapid Determination of Soil and Water Erosion in Red Soil Erosion Area,S157
  7. Typical tunnel geological disaster prediction and early warning method of,P694
  8. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  9. Passenger Line analysis of continuous beam bridge construction control and temperature effects,U445.4
  10. Research of Small and Mediem Sized Enterprises Credit Risk Evaluation System and Model Based on Neural Network and Rough Set Theroy,F276.3
  11. Research of Improved Hopfield Neural Network Algorithm on Single Dynamic Scheduling Problem,F224
  12. Based on wavelet and neural network ECG automatic analysis technique,TN911.6
  13. Research on Siraidia Grosvenrii Features and Spezies Identification Based on Digital Image Processing and Artificial Neural Network,S567.239
  14. An Improved Artificial Neural Network Model,TP183
  15. Research in Traffic Date Fusion for Highway Tunnel,U491
  16. Study on Water Quality Characteristics and Eutrophication Trends Based on Al Method in Xinlicheng Reservoir, Changchun,X524
  17. Empirical Research on Regional Science and Technology Competitiveness,F127
  18. Analysis on Dynamic Change of Land Use Structure and Driving Force in Fuzhou,F224
  19. Audio rhythm analysis and application,TN912.3
  20. Study on the Talent Demand Forecast of Cultural and Creative Industry in Heilongjiang Province in "the Twelfth Five-Year-Plan",G124
  21. Study on Forest Carbon Estimation Method Based on Remote Sensing Data and Ground Plot Information,S718.5

CLC: > Economic > Industrial economy > China Industrial Economy > Industrial sector economy
© 2012 www.DissertationTopic.Net  Mobile