Novel Multi-Time Scale Deep Learning Algorithm for Solar Irradiance Forecasting

N. Yogambal Jayalakshmi, R. Shankar, Umashankar Subramaniam, I. Baranilingesan, Alagar Karthick, Balasubramaniam Stalin, Robbi Rahim and Aritra Ghosh
Additional contact information
N. Yogambal Jayalakshmi: Department of Electrical and Electronics Engineering, Dr. Mahalingam College of Engineering and Technology, Coimbatore 642003, India
R. Shankar: Department of Electronics and Communication Engineering, Teegala Krishna Reddy Engineering College, Hyderabad 500097, India
Umashankar Subramaniam: Department of Communications and Networks, Renewable Energy Lab, College of Engineering, Prince Sultan University Riyadh, Riyadh 12435, Saudi Arabia
I. Baranilingesan: Department of Electrical and Electronics Engineering, KPR Institute of Engineering and Technology, Arasur Coimbatore 641047, India
Alagar Karthick: Department of Electrical and Electronics Engineering, KPR Institute of Engineering and Technology, Arasur Coimbatore 641047, India
Balasubramaniam Stalin: Department of Mechanical Engineering, Regional Campus Madurai, Anna University, Madurai 625019, India
Robbi Rahim: Department of Informatics Management, Sekolah Tinggi Ilmu Manajemen Sukma, Medan, Sumatera Utara 20219, Indonesia
Aritra Ghosh: College of Engineering, Mathematics and Physical Sciences, Renewable Energy, University of Exeter, Cornwall TR10 9FE, UK

Energies, 2021, vol. 14, issue 9, 1-23

Abstract: Solar irradiance forecasting is an inevitable and most significant process in grid-connected photovoltaic systems. Solar power is highly non-linear, and thus to manage the grid operation efficiently, with irradiance forecasting for various timescales, such as an hour ahead, a day ahead, and a week ahead, strategies are developed and analysed in this article. However, the single time scale model can perform better for that specific time scale but cannot be employed for other time scale forecasting. Moreover, the data consideration for single time scale forecasting is limited. In this work, a multi-time scale model for solar irradiance forecasting is proposed based on the multi-task learning algorithm. An effective resource sharing scheme between each task is presented. The proposed multi-task learning algorithm is implemented with a long short-term memory (LSTM) neural network model and the performance is investigated for various time scale forecasting. The hyperparameter estimation of the proposed LSTM model is made by a hybrid chicken swarm optimizer based on combining the best features of both the chicken swarm optimization algorithm (CSO) and grey wolf optimization (GWO) algorithm. The proposed model is validated, comparing existing methodologies for single timescale forecasting, and the proposed strategy demonstrated highly consistent performance for all time scale forecasting with improved metric results.

Keywords: solar irradiance forecasting; multi-task learning; multi-time scale prediction; LSTM; hybrid CSO-GWO (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (10)

Downloads: (external link)
https://www.mdpi.com/1996-1073/14/9/2404/pdf (application/pdf)
https://www.mdpi.com/1996-1073/14/9/2404/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:14:y:2021:i:9:p:2404-:d:541995

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().