『Abstract
To improve estimation efficiency for future projections, the
present study has proposed a hybrid algorithm, Particle Swarm
Optimization and Genetic Algorithm optimal Energy Demand Estimating
(PSO-FGA EDE) model, for China. The coefficients of the three
forms of the model (linear, exponential, and quadratic) are optimized
by PSO-GA using factors, such as GDP, population, economic structure,
urbanization rate, and energy consumption structure, that affect
demand. Based on 20-year historical data between 1990 and 2009,
the simulation results of the proposed model have greater accuracy
and reliability than other single optimization methods. Moreover,
it can be used with optimal coefficients for the energy demand
projections of China. The departure coefficient method is applied
to get the weights of the three forms of the model to obtain a
combinational prediction. The energy demand of China is going
to be 4.79, 4.04, and 4.48 billion tce in 2015, and 6.91, 5.03,
and 6.11 billion tce (“standard” tons coal equivalent) in 2020
under three different scenarios. Further, the projection results
are compared with other estimating methods.
Keywords; PSO-GA optimization algorithm; Energy demand estimating;
Scenario analysis』
1. Introduction
2. Literature review
2.1. Econometric models
2.2. Artificial intelligence models
2.3. Hybrid forecasting models
2.4. Grey forecasting model
2.5. LEAP models
3. Methodology
3.1. Three-form estimation model
3.2. PSO-GA Hybrid optimization algorithm
4. Factors affecting demand and data management
4.1. Factors affecting demand of China
4.2. Data management
5. PSO-GA EDE model application
5.1. Coefficient optimization for the current data
5.2. Estimating results
6. Scenario setting and future estimation
6.1. Scenario A (business-as-usual scenario)
6.2. Scenario B (planning and policy scenario)
6.3. Scenario C (middle scenario)
6.4. Future estimating results
7. Conclusions
Acknowledgements
References