Table 4 Models’ parameters for SVR models and BPNN network configuration (SVR models: \(\varepsilon =0.001\))
From: Short-term photovoltaic power production forecasting based on novel hybrid data-driven models
| Â | SSO | PSO | CSO | NNA | ||||
|---|---|---|---|---|---|---|---|---|
\(C\) | \(\upgamma \) | \(C\) | \(\upgamma \) | \(C\) | \(\upgamma \) | \(C\) | \(\upgamma \) | |
\(SV{R}_{RB}\) | 9239.9 | 2.9384 | 9854 | 2.8795 | 9136.8 | 2.85636 | 9203.64 | 2.948563 |
\(SV{R}_{Linear}\) | 138.5539 | – | 0.63188 | – | 4461.461 | – | 64.67852 | – |
| Â | SSO | PSO | CSO | NNA | ||||
|---|---|---|---|---|---|---|---|---|
Hidden | Hidden | Hidden | Hidden | Hidden | Hidden | Hidden | Hidden | |
Layer 1 | Layer 2 | Layer 1 | Layer 2 | Layer 1 | Layer 2 | Layer 1 | Layer 2 | |
\(BPN{N}^{1}\) | 19 | – | 18 | – | 17 | – | 16 | – |
\(BPN{N}^{2}\) | 15 | 7 | 19 | 9 | 19 | 6 | 18 | 10 |