| Title |
Forecasting electricity consumption using a novel hybrid model |
| ID_Doc |
76508 |
| Authors |
Fan, GF; Wei, X; Li, YT; Hong, WC |
| Title |
Forecasting electricity consumption using a novel hybrid model |
| Year |
2020 |
| Published |
|
| DOI |
10.1016/j.scs.2020.102320 |
| Abstract |
In recent years, the electricity industry has become increasingly important to social and economic development. For sustainability of the power industrial business, an accurate electricity consumption forecasting model can be used to adjust the production and consumption patterns of electricity, it can also support energy policy decision-making, such as load unit commitment, operational security of plants, and economic load dispatching. Using electricity consumption data to study electricity production and consumption patterns is useful in identifying the regulation of electricity economic development. This paper combines several machine learning approaches (the empirical mode decomposition (EMD) method, the support vector regression (SVR) model, and the particle swarm optimization (PSO) algorithm), thermal reaction dynamics theory, and the econometric model (ARGARCH model), to develop a novel hybrid forecasting model, namely EMD-SVR-PSO-AR-GARCH model, for forecasting electricity consumption. It adopts a new perspective on electricity usage and consuming economic behaviors. Using electricity consumption data from the New South Wales (NSW, Australia) market, the developed model is used to forecast electricity consumption. Then, the Nash equilibrium and Porter's five-force model are used to analyze the complex electricity usage and consuming economic behaviors, to identify the regulation of electricity and economic development, supporting the sustainable development of electricity. |
| Author Keywords |
Electric load forecasting; Electricity economic behavior; Machine learning; Thermal reaction kinetics; Nash equilibrium |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Science Citation Index Expanded (SCI-EXPANDED); Social Science Citation Index (SSCI) |
| EID |
WOS:000573583800008 |
| WoS Category |
Construction & Building Technology; Green & Sustainable Science & Technology; Energy & Fuels |
| Research Area |
Construction & Building Technology; Science & Technology - Other Topics; Energy & Fuels |
| PDF |
|