Open Science Research Excellence

Open Science Index

Commenced in January 2007 Frequency: Monthly Edition: International Abstract Count: 63703

Deep Learning for Renewable Power Forecasting: An Approach Using Long Short Term Memory Neural Networks
Load forecasting has become crucial in recent years and become popular in forecasting area. Most traditional forecasting models and artificial intelligence techniques have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Predictive tools are required which can be used to determine sufficiently far in advance how much renewable energy utilized. The goal of this study is to investigate the effectiveness of using LSTM based neural networks for renewable energy load forecasting. This paper presents renewable energy load forecasting methodology based on Deep Neural Networks, specifically Long Short Term Memory (LSTM) algorithms. Deep learning allows models composed of multiple layers to learn representations of data. LSTM algorithms are able to store information for long periods of time. Deep Learning architectures have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather temperature data represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via Deep Neural Networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count, batch size and dropout. For training, ADAM algorithm is used as the gradient based optimizer, instead of SGD (stochastic gradient descent). ADAM outperformed SGD in terms of faster convergence and lower error ratios. Models performance is compared according to MAE (Mean Absolute Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.