Single Step Multivariate Solar Power Forecasting using Adaptive Learning Rate LSTM Model with Optimized Window Size

Accurate photovoltaic (PV) power forecasting is crucial for the successful integration of residential PV systems into the electrical grid. It enables grid operators to optimize grid operations, ensure stability, facilitate market operations and trading, and plan for future system expansion. In this...

Full description

Saved in:
Bibliographic Details
Main Authors: Kunalan D., Krishnan P.S., Permal N.
Other Authors: 56395450700
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers Inc. 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-34461
record_format dspace
spelling my.uniten.dspace-344612024-10-14T11:19:56Z Single Step Multivariate Solar Power Forecasting using Adaptive Learning Rate LSTM Model with Optimized Window Size Kunalan D. Krishnan P.S. Permal N. 56395450700 36053261400 56781496300 Adaptive Learning Rate LSTM network Optimized Window Size PV generation Solar Irradiation forecasting Commerce Forecasting Learning algorithms Solar energy Solar power generation Adaptive learning rates Long short-term memory network Memory network Optimized window size Optimized windows Photovoltaic power Photovoltaics generations Solar irradiation Solar irradiation forecasting Window Size Long short-term memory Accurate photovoltaic (PV) power forecasting is crucial for the successful integration of residential PV systems into the electrical grid. It enables grid operators to optimize grid operations, ensure stability, facilitate market operations and trading, and plan for future system expansion. In this study, we propose a new model that combines an adaptive learning rate Long Short-Term Memory (LSTM) with an optimized window size for improved PV power forecasting. The proposed model is trained and tested using historical time series data of projected PV power and weather conditions, considering the GPS location of the PV system. The model's performance is compared against other commonly used forecasting models, including LSTM, Bi-LSTM, LSTM-Transformer, and CNN-LSTM, for single-step size forecasting, specifically predicting PV power for the next hour. The results demonstrate that the proposed model outperforms all other models in terms of accuracy for the single-step forecasting task. The adaptive learning rate LSTM with optimized window size demonstrates superior performance, indicating its effectiveness in capturing the temporal patterns and dependencies in PV power generation. � 2023 IEEE. Final 2024-10-14T03:19:56Z 2024-10-14T03:19:56Z 2023 Conference Paper 10.1109/IES59143.2023.10242461 2-s2.0-85173609732 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85173609732&doi=10.1109%2fIES59143.2023.10242461&partnerID=40&md5=46003f00227e2019a58c441cb1217c0e https://irepository.uniten.edu.my/handle/123456789/34461 70 76 Institute of Electrical and Electronics Engineers Inc. Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
topic Adaptive Learning Rate
LSTM network
Optimized Window Size
PV generation
Solar Irradiation forecasting
Commerce
Forecasting
Learning algorithms
Solar energy
Solar power generation
Adaptive learning rates
Long short-term memory network
Memory network
Optimized window size
Optimized windows
Photovoltaic power
Photovoltaics generations
Solar irradiation
Solar irradiation forecasting
Window Size
Long short-term memory
spellingShingle Adaptive Learning Rate
LSTM network
Optimized Window Size
PV generation
Solar Irradiation forecasting
Commerce
Forecasting
Learning algorithms
Solar energy
Solar power generation
Adaptive learning rates
Long short-term memory network
Memory network
Optimized window size
Optimized windows
Photovoltaic power
Photovoltaics generations
Solar irradiation
Solar irradiation forecasting
Window Size
Long short-term memory
Kunalan D.
Krishnan P.S.
Permal N.
Single Step Multivariate Solar Power Forecasting using Adaptive Learning Rate LSTM Model with Optimized Window Size
description Accurate photovoltaic (PV) power forecasting is crucial for the successful integration of residential PV systems into the electrical grid. It enables grid operators to optimize grid operations, ensure stability, facilitate market operations and trading, and plan for future system expansion. In this study, we propose a new model that combines an adaptive learning rate Long Short-Term Memory (LSTM) with an optimized window size for improved PV power forecasting. The proposed model is trained and tested using historical time series data of projected PV power and weather conditions, considering the GPS location of the PV system. The model's performance is compared against other commonly used forecasting models, including LSTM, Bi-LSTM, LSTM-Transformer, and CNN-LSTM, for single-step size forecasting, specifically predicting PV power for the next hour. The results demonstrate that the proposed model outperforms all other models in terms of accuracy for the single-step forecasting task. The adaptive learning rate LSTM with optimized window size demonstrates superior performance, indicating its effectiveness in capturing the temporal patterns and dependencies in PV power generation. � 2023 IEEE.
author2 56395450700
author_facet 56395450700
Kunalan D.
Krishnan P.S.
Permal N.
format Conference Paper
author Kunalan D.
Krishnan P.S.
Permal N.
author_sort Kunalan D.
title Single Step Multivariate Solar Power Forecasting using Adaptive Learning Rate LSTM Model with Optimized Window Size
title_short Single Step Multivariate Solar Power Forecasting using Adaptive Learning Rate LSTM Model with Optimized Window Size
title_full Single Step Multivariate Solar Power Forecasting using Adaptive Learning Rate LSTM Model with Optimized Window Size
title_fullStr Single Step Multivariate Solar Power Forecasting using Adaptive Learning Rate LSTM Model with Optimized Window Size
title_full_unstemmed Single Step Multivariate Solar Power Forecasting using Adaptive Learning Rate LSTM Model with Optimized Window Size
title_sort single step multivariate solar power forecasting using adaptive learning rate lstm model with optimized window size
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2024
_version_ 1814061121603108864
score 13.209306