Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Journal of Robotics and Control (JRC)
Tjahyadi, Christianto
Unknown Affiliation
Aerospace Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering Mechanical Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Hyperparameter Tuning Impact on Deep Learning Bi-LSTM for Photovoltaic Power Forecasting Sutarna, Nana; Tjahyadi, Christianto; Oktivasari, Prihatin; Dwiyaniti, Murie; Tohazen, Tohazen
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21120

Abstract

Solar energy is one of the most promising renewable energy sources that can reduce greenhouse gas emissions and fossil fuel dependence. However, solar energy production is highly variable and uncertain due to the influence of weather conditions and environmental factors. Accurate forecasting of photovoltaic (PV) power output is essential for optimal planning and operation of PV systems, as well as for integrating them into the power grid. This study develops a deep learning model based on Bidirectional Long Short-Term Memory (Bi-LSTM) to predict short-term PV power output. The main objective is to examine the effect of hyperparameter tuning on the forecasting accuracy and the actual PV output power. The main contribution is identifying the optimal combination of hyperparameters, namely the optimizer, the learning rate, and the activation function, for the PV output. The dataset consists of 143786 observations from sensors measuring solar irradiation, PV surface temperature, ambient temperature, ambient humidity, wind speed, and PV power output for 50 days in Bandung, Indonesia. The data is preprocessed by smoothing and splitting into training (70%, 35 days), validation (15%, 7.5 days), and testing (15%, 7.5 days) sets. The Bi-LSTM model is trained and tested with two optimizers: Adam and RMSprop, and three activation functions: Tanh, ReLU, and Swish, with different learning rates. The results indicate that the optimal performance is obtained by the Bi-LSTM model with Adam optimizer, learning rate of 〖1e〗^(-4), and Tanh activation function. This model has the lowest MAE of 0.002931070979684591, the lowest RMSE of 0.008483537231080387, and the highest R-squared of 0.9988813964105624 when tested with the validation dataset and requires 93 epochs to build. The model also performs well on the test dataset, with the lowest MAE of 0.002717077964916825, the lowest RMSE of 0.007629486798682186, and the highest R-squared of 0.9992563395109665. This study concludes that hyperparameter tuning is a vital step in developing the Bi-LSTM model to improve the accuracy of PV output power prediction.
Optimized BiLSTM-Dense Model for Ultra-Short-Term PV Power Forecasting Tjahyadi, Christianto; Sutarna, Nana; Oktivasari , Prihatin
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 2, May 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i2.2127

Abstract

The growing integration of photovoltaic (PV) systems into power grids poses challenges due to the inherent variability in PV output, particularly during rapid weather changes. While existing forecasting methods often struggle to capture these fluctuations, accurate ultra-short-term PV power prediction is critical for grid stability. The study aims to develop an optimized BiLSTM-Dense model that enhances forecasting accuracy by incorporating an additional dense layer. The model is designed to improve forecasting performance over a 30-second horizon. It utilizes a dataset of solar irradiance, PV output power, surface temperature, ambient temperature, humidity, and wind speed, collected in late 2023. Data preprocessing involved normalization and smoothing techniques to enhance robustness. Hyperparameter optimization was performed using grid search. Evaluation results demonstrate the superiority of the proposed model, achieving an MAE of 0.00271 and an RMSE of 0.00806 when paired with the Adam optimizer and Swish activation function. Compared to standard BiLSTM, the BiLSTM-Dense achieved MAE and RMSE improvements of 0.52% and 2.19%, respectively. It also outperformed the LSTM model with reductions of 4.00% in MAE and 2.65% in RMSE, and significantly surpassed ARIMA, reducing MAE by 98.87% and RMSE by 97.21%. These findings highlight the model’s ability to capture complex, non-linear dependencies in PV output data, outperforming conventional approaches like ARIMA, which rely on linear assumptions, and simpler architectures like LSTM, which lack bidirectional context integration.
Co-Authors MURIE DWIYANITI1 Nana Sutarna Oktivasari , Prihatin Prihatin Oktivasari Tohazen, Tohazen