Efficient deterministic renewable energy forecasting guided by multiple-location weather data

Electricity generated from renewable energy sources has been established as an efficient remedy for both energy shortages and the environmental pollution stemming from conventional energy production methods. At current stage, hydropower remains the primary contributor to electricity generation among...

Full description

Saved in:
Bibliographic Details
Published in:Neural computing & applications Vol. 37; no. 17; pp. 10647 - 10674
Main Authors: Symeonidis, Charalampos, Nikolaidis, Nikos
Format: Journal Article
Language:English
Published: London Springer London 01.06.2025
Springer Nature B.V
Subjects:
Alternative energy sources
Artificial Intelligence
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Datasets
Electric power grids
Electricity
Energy resources
Forecasting
Image Processing and Computer Vision
Meteorological data
Power plants
Probability and Statistics in Computer Science
Production methods
Renewable energy sources
Renewable resources
Root-mean-square errors
S.I.: Timely Advances of Deep Learning with applications and Data Driven Modeling
Solar energy
Special Issue on Timely Advances of Deep Learning with applications and Data Driven Modeling
Time series
Weather forecasting
Wind power
Deep learning
Deterministic RES forecasting
Time-series forecasting
ISSN:0941-0643, 1433-3058
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Electricity generated from renewable energy sources has been established as an efficient remedy for both energy shortages and the environmental pollution stemming from conventional energy production methods. At current stage, hydropower remains the primary contributor to electricity generation among renewable energy sources. Nonetheless, solar and wind power are also recognized as dominant and exceptionally promising renewable energy sources. The accurate forecasting of the energy generation of those sources facilitates their integration into electric grids, by minimizing the negative impact of uncertainty regarding their management and operation. This paper proposes a novel methodology for deterministic wind and solar energy generation forecasting for multiple generation sites, utilizing multi-location weather forecasts. The method employs a U-shaped temporal convolutional auto-encoder (UTCAE) architecture for temporal processing of weather-related and energy-related time-series across each site. The multi-sized kernels convolutional spatiotemporal attention (MKST-Attention), inspired by the multi-head scaled dot product attention mechanism, is also proposed aiming to efficiently transfer temporal patterns from weather data to energy data, without a priori knowledge of the locations of the power stations and the locations of provided weather data. The conducted experimental evaluation on a day-ahead solar and wind energy forecasting scenario on five datasets demonstrated that the proposed method achieves top results, outperforming all competitive time-series forecasting state-of-the-art methods. In particular, in the AEMO-H dataset, encompassing hourly wind energy generation data alongside weather data from 22 power stations, the method attained the best mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination ( R 2 ) scores at each station. Additionally, it recorded the highest MAE of 0.098, the highest RMSE of 0.138 and the highest R 2 score of 0.791, averaged across all energy stations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-024-10607-2