Super-resolution perception for wind power forecasting by enhancing historical data

Article Thermodynamics

A high-accuracy hybrid method for short-term wind power forecasting

Sahra Khazaei et al.

Summary: This article proposes a high-accuracy hybrid approach for short-term wind power forecasting using historical data of wind farm and Numerical Weather Prediction (NWP) data, including three stages: wind direction forecasting, wind speed forecasting, and wind power forecasting. The method involves outlier detection, decomposition of time series, feature selection, and prediction using Multilayer Perceptron (MLP) neural network, with evaluation showing very high accuracy when tested with data from the Sotavento wind farm in Spain.

ENERGY (2022)

Add to Collection

Review Energy & Fuels

A review of wind speed and wind power forecasting with deep neural networks

Yun Wang et al.

Summary: This study comprehensively reviews the various deep learning technologies used in wind speed/wind power forecasting, including data processing, feature extraction, and relationship learning stages. The forecasting performance of popular models is evaluated through testing and comparing on two real-world wind datasets.

APPLIED ENERGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Short-term prediction of wind power and its ramp events based on semi-supervised generative adversarial network

Bin Zhou et al.

Summary: This paper introduces a hybrid forecasting model based on semi-supervised generative adversarial network for short-term wind power and ramp event prediction. By decomposing wind energy data time series and employing semi-supervised regression, non-linear and dynamic behaviors are extracted to enhance forecasting accuracy, along with a self-tuning forecasting strategy for improved performance.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2021)

Add to Collection

Article Energy & Fuels

M-SRPCNN: A Fully Convolutional Neural Network Approach for Handling Super Resolution Reconstruction on Monthly Energy Consumption Environments

Ivan de-Paz-Centeno et al.

Summary: M-SRPCNN is a fully convolutional generative deep neural network proposed to recover missing historical hourly data from a sensor based on historic monthly energy consumption. It effectively reconstructs load curves while maintaining overall monthly consumption, surpassing traditional energy apportioning systems.

ENERGIES (2021)

Add to Collection

Article Thermodynamics

Short-term offshore wind speed forecast by seasonal ARIMA-A comparison against GRU and LSTM

Xiaolei Liu et al.

Summary: Offshore wind power is one of the fastest-growing energy sources worldwide, and accurate wind speed forecasts are essential for proper wind energy evaluation. The SARIMA model has shown superior performance in predicting offshore wind speeds compared to other deep learning algorithms, providing higher accuracy and robustness.

ENERGY (2021)

Add to Collection

Article Engineering, Multidisciplinary

Forecasting of solar and wind power using LSTM RNN for load frequency control in isolated microgrid

Dhananjay Kumar et al.

Summary: The study discusses the use of deep learning methods to develop a multi-step forecasting model and the application of Long Short-Term Memory (LSTM) RNN for wind speed and solar irradiance prediction. The forecasted solar and wind power are utilized to analyze load frequency behavior, with a PI controller used to mitigate frequency deviation and ensure stability of the MG power system.

INTERNATIONAL JOURNAL OF MODELLING AND SIMULATION (2021)

Add to Collection

Article Energy & Fuels