Name
Title | ||
|---|---|---|
Forecasting Regional Level Solar Power Generation Using Advanced Deep Learning Approach |
Abstract | ||
|---|---|---|
Reliable integration of solar photovoltaic (PV) power into the electricity grid requires accurate forecasting at the regional level. While previous research has been primarily concerned with forecasting PV power output from a single plant, this research focuses on regional level forecasting which is more beneficial for economic operations of power systems. This paper presents an advanced deep learning-based approach, called CNNs-LSTM Encoder-Decoder (CLED), to predict the regional level aggregated PV power generation for the next day at half-hourly intervals. The proposed approach utilizes the ability of Convolutional Neural Networks (CNNs) to capture and learn the internal representation of intermittent time-series data. It also uses Long Short-Term Memory (LSTM) network for recognizing temporal dependencies in the data. The performance of the CLED model is evaluated using a large data set from the Australian Energy Market Operator (AEMO). Results demonstrate that CLED provides accurate predictions, outperforming baselines and state-of-the-art models in the literature. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/IJCNN52387.2021.9533458 | 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) |
Keywords | DocType | ISSN |
Solar Power Forecasting, Deep Learning, Machine Learning, CNN, LSTM, Time-series | Conference | 2161-4393 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sarah Almaghrabi | 1 | 0 | 0.34 |
| Mashud Rana | 2 | 45 | 8.25 |
| Margaret Hamilton | 3 | 44 | 13.71 |
| Mohammad Saiedur Rahaman | 4 | 15 | 8.41 |