Short-term wind power forecasting using KNN, SVR, and linear regression with high-resolution SCADA data

Selahattin Barış Çelebi

doi:10.1177/0309524X261417206

Short-term wind power forecasting using KNN, SVR, and linear regression with high-resolution SCADA data

2026-01-01

0

PRE

AI

S

Selahattin Barış Çelebi *

A

Ammar Aslan

C

Cafer Yazicioglu

DOI：10.1177/0309524X261417206

Original

Original request for help

Save

Abstract

En 中文

Short-term wind power forecasting supports grid stability despite wind's intermittency, but deep learning (DL) models often require excessive computation, hindering real-time deployment. This study compares three classical regression models, linear regression (LR), k-nearest neighbors (KNNs), and support vector regression (SVR) using 10-minute SCADA data. The data retained raw variability, with only negative power values set to zero. Hyperparameters of KNN and SVR were optimized using GridSearchCV with time series cross-validation. Optimized SVR achieved superior performance (MAE = 183.93 kW, RMSE = 387.64 kW, R2 = 0.91, MAPE = 144.88%, MdAE = 84.44 kW), outperforming KNN (R2 = 0.79) and LR (R2 = 0.91 but higher errors). Scatter plots and residuals highlighted SVR's ability to handle nonlinearities. Results suggest that SVR is a viable candidate SVR for low-resource, real-time forecasting in renewables.

Keywords:

wind power forecasting

renewable energy

computational efficiency

short-term forecasting

real-time forecasting

Short-term wind power forecasting using KNN, SVR, and linear regression with high-resolution SCADA data

Abstract

Journal

Organization

Cited Papers

Citing Papers