| Abstract | 第4页 |
| 摘要 | 第5-9页 |
| 1. Review and analysis of modern methods and mathematical models to predict electricity consumption | 第9-16页 |
| 1.1 Classification of short-term load forecasting methods | 第9页 |
| 1.2 Statistical methods of forecasting | 第9-10页 |
| 1.2.1 Methods for regression | 第9页 |
| 1.2.2 Time series methods | 第9-10页 |
| 1.2.3 Methods based on wavelet transform of time series | 第10页 |
| 1.3 Methods of artificial intelligence | 第10-11页 |
| 1.3.1 Methods based on neural network models | 第10页 |
| 1.3.2 Methods based on fuzzy logic | 第10页 |
| 1.3.3 Support vector method | 第10-11页 |
| 1.4 Evolutionary algorithms | 第11-12页 |
| 1.5 Requirements for short-term forecasting of electricity consumption | 第12页 |
| 1.6 Main problems of short-term forecasting of electricity consumption | 第12-13页 |
| 1.6.1 Accuracy of the input - output relationship hypothesis | 第12-13页 |
| 1.6.2 Prediction of abnormal days | 第13页 |
| 1.6.3 Inaccurate weather forecast data | 第13页 |
| 1.7 Review of current literature on the problem of short-term power consumption forecasting | 第13-15页 |
| 1.7.1 Models of neural networks | 第13-14页 |
| 1.7.2 Models of neuro-fuzzy networks | 第14页 |
| 1.7.3 Model of wavelet transform | 第14-15页 |
| 1.7.4 Regression models | 第15页 |
| 1.8 Conclusions | 第15-16页 |
| 2. Time series analysis of electricity consumption and its determinants | 第16-28页 |
| 2.1 Characteristics of the electrical load diagrams of the power system | 第16-17页 |
| 2.2 Time series of power consumption and influencing factors | 第17-21页 |
| 2.3 Seasonal and meteorological factors affecting power consumption | 第21-22页 |
| 2.4 Temperature and light: the analysis of their impact on power consumption in the control room operating area | 第22-23页 |
| 2.5 Random disturbances | 第23-27页 |
| 2.6 Conclusions | 第27-28页 |
| 3. Modelling short term future energy consumption based on neural networks and evolutionary algorithms | 第28-45页 |
| 3.1 Short-term load forecasting using artificial neural network | 第28-30页 |
| 3.2 Short-term load forecasting using artificial neural networks and particle swarm optimization algorithm | 第30页 |
| 3.3 Short-term load forecasting using artificial neural networks and particle swarm optimization algorithm | 第30-40页 |
| 3.3.1 Data analysis and pre-processing | 第32页 |
| 3.3.2 The number of layers, neurons and transfer functions | 第32页 |
| 3.3.3 Training of built neural networks | 第32页 |
| 3.3.4 Architecture of the ANN for the operating zone | 第32-34页 |
| 3.3.5 The choice of input variables | 第34页 |
| 3.3.6 Building the structure of neural network | 第34-35页 |
| 3.3.7 Selection of data for training, testing and validation | 第35-37页 |
| 3.3.8 Simulation results | 第37-40页 |
| 3.4 Training the ANN on the basis of self-organization | 第40-44页 |
| 3.4.1 Dataset for the study | 第40-41页 |
| 3.4.2 Training of self-organizing maps | 第41-42页 |
| 3.4.3 The results of clustering and prediction | 第42-43页 |
| 3.4.4 Performance criteria | 第43页 |
| 3.4.5 Simulation results | 第43-44页 |
| 3.5 Conclusions | 第44-45页 |
| 4. Models of future energy consumption based on neural fuzzy network and support vector method | 第45-61页 |
| 4.1 Predicting power consumption using adaptive neural fuzzy network | 第45-49页 |
| 4.1.1 The architecture of neuro-fuzzy model | 第45-46页 |
| 4.1.2 Hybrid algorithm for training neural networks | 第46-47页 |
| 4.1.3 Simulation result | 第47-49页 |
| 4.2 Energy consumption forecasting using support vector | 第49-54页 |
| 4.2.1 Simulation results | 第51-54页 |
| 4.3 Forecasting of power consumption based on the support vector method and particle swarm algorithm | 第54-60页 |
| 4.3.1 Load forecasting steps and processes | 第54-55页 |
| 4.3.2 A set of analysis parameters | 第55-56页 |
| 4.3.3 Simulation results | 第56-60页 |
| 4.4 Conclusions | 第60-61页 |
| Summarize | 第61-62页 |
| Acknowledgement | 第62-63页 |
| References | 第63-67页 |
| Research achievement during working for the degree | 第67页 |
