Wind Power Prediction across Different Locations using Deep Domain Adaptive Learning

TL;DR

This paper introduces a deep domain adaptive learning method for wind power prediction that improves accuracy across different geographic regions by selectively updating neural network layers, without needing source data during adaptation.

Contribution

It proposes a novel deep neural network approach with layer-specific adaptation for wind power prediction across diverse locations, enhancing robustness and efficiency.

Findings

Achieves 6.14% to 28.44% higher accuracy than traditional methods.

Uses weather feature selection via random forest for improved prediction.

Updates only the last layers of the neural network for faster adaptation.

Abstract

Accurate prediction of wind power is essential for the grid integration of this intermittent renewable source and aiding grid planners in forecasting available wind capacity. Spatial differences lead to discrepancies in climatological data distributions between two geographically dispersed regions, consequently making the prediction task more difficult. Thus, a prediction model that learns from the data of a particular climatic region can suffer from being less robust. A deep neural network (DNN) based domain adaptive approach is proposed to counter this drawback. Effective weather features from a large set of weather parameters are selected using a random forest approach. A pre-trained model from the source domain is utilized to perform the prediction task, assuming no source data is available during target domain prediction. The weights of only the last few layers of the DNN model are updated throughout the task, keeping the rest of the network unchanged, making the model faster compared to the traditional approaches. The proposed approach demonstrates higher accuracy ranging from 6.14% to even 28.44% compared to the traditional non-adaptive method.