Research Article
A Novel Hybrid Approach Based on BAT Algorithm with Artificial Neural Network to Forecast Iran’s Oil Consumption
Table 5
Comparison of various models introduced in the introduction and present studya.
| Source | Method | Target (country) | Average relative errors (%) |
| Toksarı [12] | Ant colony algorithm | Total energy (Turkey) | 1.07 | Ceylan et al. [11] | Harmony search | Total energy (Turkey) | 21.74 | Harmony search | Total energy (Turkey) | 13.41 | Harmony search | Total energy (Turkey) | 39.32 | Assareh et al. [3] | Genetic algorithm | Oil (Iran) | 2.83 | Genetic algorithm | Oil (Iran) | 1.72 | Particle swarm optimization | Oil (Iran) | 1.4 | Particle swarm optimization | Oil (Iran) | 1.36 | Behrang et al. [4] | Gravitational search algorithm | Oil (Iran) | 1.14 | Gravitational search algorithm | Oil (Iran) | 1.52 | Gravitational search algorithm | Oil (Iran) | 1.43 | Gravitational search algorithm | Oil (Iran) | 3.32 | Gravitational search algorithm | Oil (Iran) | 1.33 | Kıran et al. [9] | Particle swarm optimization | Electricity (Turkey) | 3.99 | Particle swarm optimization | Electricity (Turkey) | 4.406 | Artificial bee colony | Electricity (Turkey) | 3.20 | Artificial bee colony | Electricity (Turkey) | 4.47 | Present study | Hybrid bat algorithm with artificial neural network (BANN) | Oil (Iran) | 0.0037 |
|
|
The average relative errors are separately based on the testing period of each model.
|