|
|
 |
| |
|
|
|
Yearly Electricity Consumption Forecasting using a Nonhomogeneous Exponential Model Optimized by PSO Algorithm |
|
|
|
PP: 1063-1069 |
|
|
|
Author(s) |
|
|
|
Xiaomin Xu,
Dongxiao Niu,
Ming Meng,
Huifeng Shi,
|
|
|
|
Abstract |
|
|
| Yearly electricity consumption trends of most developing countries usually exhibit approximately exponential growth
curves. An optimized nonhomogeneous exponential model (ONEM) is proposed as a method of forecasting electricity consumption by
using trend extrapolation. The parameters of the nonhomogeneous exponential equation are obtained by using the inverse accumulated
generating operation, discretizing the differential equation, minimizing the residual sum of squares (RSS), and accumulating the
homogeneous exponential equation. Furthermore, to improve forecasting precision, particle swarm optimization (PSO) algorithm is
used to optimize the equation parameters. To evaluate the forecasting performance for comparison, the said model and two other
traditional methods are used to forecast the yearly electricity consumption of India. Empirical results show that this model is much
better than traditional methods for each error analysis indicator. |
|
|
|
|
|
|
|
