Table 6 Under rainy days, forecasting performance comparison.

From: The development of CC-TF-BiGRU model for enhancing accuracy in photovoltaic power forecasting

Forecasting model

Evaluation index

Different seasons

Spring

Summer

Autumn

Winter

Average

#1

MAE

3.4091

3.4904

2.3322

4.1374

3.3422

RMSE

4.4562

4.5762

3.7386

5.3688

4.5349

R2

0.7369

0.7078

0.7915

0.8318

0.7670

#2

MAE

3.0496

2.6821

2.0999

3.1188

2.7376

RMSE

4.0338

3.4238

3.3018

4.8088

3.8920

R2

0.833

0.9365

0.8231

0.8651

0.8644

#3

MAE

1.9217

2.0371

1.8612

2.5068

2.0817

RMSE

1.6145

2.4012

2.6011

3.7666

2.5958

R2

0.9115

0.9196

0.8756

0.9182

0.9062

#4

MAE

1.3114

1.5308

1.0947

2.2731

1.5525

RMSE

1.946

2.0496

1.9299

2.7673

2.1732

R2

0.9498

0.9463

0.9372

0.9553

0.9471

#5

MAE

1.5915

1.5138

1.1442

1.9831

1.5581

RMSE

2.0294

1.9917

2.1816

3.3464

2.3872

R2

0.9454

0.9485

0.9324

0.9347

0.9402

#6

MAE

2.1954

2.2471

2.3311

2.9857

2.4398

RMSE

3.0307

3.2769

3.0085

3.7643

3.2701

R2

0.8783

0.8502

0.8336

0.9173

0.8698

#7

MAE

1.5549

1.6104

1.6169

1.9249

1.6767

RMSE

2.3769

2.4921

2.2179

3.1169

2.5509

R2

0.9251

0.9134

0.9095

0.9307

0.9196

#8

MAE

2.4179

1.8241

1.6265

4.0795

2.4870

RMSE

2.9538

2.2557

2.6717

4.5716

3.1132

R2

0.8844

0.9291

0.8687

0.8781

0.8900

#9

MAE

1.4659

1.5274

1.2034

2.2731

1.6174

RMSE

2.0626

2.0984

2.3022

2.7673

2.3076

R2

0.942

0.9443

0.9232

0.9453

0.9387

#10

MAE

1.6601

1.0262

0.8951

1.2411

1.2056

RMSE

2.6929

1.6625

1.1504

2.2127

1.9296

R2

0.9702

0.9731

0.9697

0.9714

0.9711

Back to article page