環境影響を考慮したLSTMモデルに基づく多結晶太陽光パネルの発電量予測
Electrical Power Prediction of Polycrystalline Solar Panels based on LSTM Model with environmental influence (原題)
Sahrin, Alfin, Utami, Erna, Shoffiana, Nur, Abadi, Imam
🤖 gxceed AI 要約
日本語
本研究はLSTMを用いて多結晶太陽光パネルの発電量を予測するモデルを開発。環境データを入力し、純LSTM、CNN-LSTM、LSTM-AE、GWO-LSTMの各モデルを比較した。GWO-LSTMが最高精度（R²=0.98、MAPE=4.3%）を示し、メタヒューリスティック最適化の有効性を実証。再生可能エネルギーの効率的な管理に貢献する。
English
This study develops LSTM-based models to predict power output of polycrystalline solar panels using environmental data. Comparing pure LSTM, CNN-LSTM, LSTM-AE, and GWO-LSTM, the GWO-LSTM achieves the highest accuracy (R²=0.98, MAPE=4.3%), demonstrating the effectiveness of metaheuristic optimization for reliable PV power prediction and efficient energy management.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本では再生可能エネルギーの導入拡大に伴い、太陽光発電の出力予測精度向上が系統安定化やFIT/FIP制度下での運用効率化に直結する。本研究成果は、日本の気象条件に適応した予測モデル開発の基礎となり得る。
In the global GX context
Globally, accurate PV power prediction is crucial for integrating high shares of solar energy into grids and optimizing energy management systems. This study's comparative analysis of LSTM variants with metaheuristic optimization provides a robust methodology applicable to various regions, supporting the global energy transition.
👥 読者別の含意
🔬研究者:Provides a benchmark for LSTM-based PV prediction with metaheuristic optimization, offering insights into model selection and performance metrics.
🏢実務担当者:Offers a practical approach to improve solar power forecasting for better grid integration and operational efficiency.
🏛政策担当者:Highlights the importance of investing in advanced forecasting technologies to support renewable energy targets and grid stability.
📄 Abstract（原文）
Solar energy is one of the most promising renewable energy sources that can support the sustainable energy transition. However, the electrical power produced by photovoltaic (PV) panels is greatly influenced by environmental conditions such as irradiation, temperature, humidity, and wind speed, making them volatile and difficult to predict. This study aims to develop a prediction model based on Long Short-Term Memory (LSTM) to estimate the power output of polycrystalline panels. Environmental data is collected in real-time, processed through the normalization stage, and then used as input in several model variants, namely pure LSTM, CNN-LSTM, LSTM-Autoencoder, and GWO-LSTM with metaheuristic optimization. Evaluation was conducted using R², RMSE, and MAPE metrics. The results showed that the pure LSTM model provided good accuracy (R² = 0.95; MAPE = 6.2%), while CNN-LSTM and LSTM-AE improved performance with R² reaching 0.97 and 0.96, respectively. The best model is GWO-LSTM, with R² = 0.98, RMSE = 0.31 kW, and MAPE = 4.3%. These findings prove that metaheuristic optimization in LSTM can increase the reliability of PV power prediction and support a more efficient energy management system.
🔗 Provenance — このレコードを発見したソース
- base https://jurnal.polines.ac.id/index.php/jaict/article/view/7061first seen 2026-09-01 12:05:58
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。