Improving LSTM Neural Networks for Better Short-Term Wind Power Predictions

TL;DR

This paper enhances wind power prediction accuracy by integrating weather forecast data into LSTM models and introduces a new performance index to quantify naive behavior.

Contribution

It presents modified LSTM models that incorporate weather data and introduces a novel Naive Ratio index for better model evaluation.

Findings

Weather data improves LSTM prediction accuracy.

Modified LSTMs show reduced naive behavior.

New performance index effectively measures model quality.

Abstract

This paper improves wind power prediction via weather forecast-contextualized Long Short-Term Memory Neural Network (LSTM) models. Initially, only wind power data was fed to a generic LSTM, but this model performed poorly, with erratic and naive behavior observed on even low-variance data sections. To address this issue, weather forecast data was added to better contextualize the power data, and LSTM modifications were made to address specific model shortcomings. These models were tested through both a Normalized Mean Absolute Error and the Naive Ratio (NR), which is a score introduced by this paper to quantify the unwanted presence of naive character in trained models. Results showed an increased accuracy with the addition of weather forecast data on the modified models, as well as a decrease in naive character. Key contributions include making improved LSTM variants, usage of weather forecast data, and the introduction of a new model performance index.