KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Huang, Zhibin

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Advanced Short-Term Wind Power Forecasting Based on Adaptive Neuro-Fuzzy Inference System and Artificial Neural Network
    (2025-01-01)
    Huang, Zhibin
    ;
    Jiriwibhakorn, Somchat
    Accurate short-term wind power forecasting plays a critical role in maintaining grid stability and enhancing the efficient utilization of renewable energy, particularly as wind energy continues to contribute increasingly to global electricity generation. This study explores and analyzes two forecasting approaches—Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN), aiming to improve predictive accuracy. Both models utilize identical historical wind farm datasets and are trained, tested, and validated using the MATLAB R2023b platform. The research findings demonstrate that both ANN and ANFIS are well-suited for short-term wind power forecasting; however, ANFIS exhibits superior predictive accuracy compared to ANN. Specifically, the coefficient of determination (R<sup>2</sup>) values for ANN and ANFIS are 0.973 and 0.985, respectively. In terms of Root Mean Square Error (RMSE), ANN records 7.82e-03 during training and 7.44e-03 during testing, whereas ANFIS achieves a significantly lower 2.14e-03 in both phases. These results indicate that both models demonstrate a strong fit to actual data, with R² values approaching 1, validating their reliability for short-term forecasting. Furthermore, ANFIS proves to be more effective in handling data nonlinearity and uncertainty, consistently yielding lower RMSE values in both the training and testing phases. Despite achieving higher predictive accuracy, ANFIS requires a longer computational time. While this study confirms ANFIS's superior performance in short-term wind power forecasting, its advantage over ANN is not guaranteed in all scenarios, as the effectiveness of the model remains dependent on the complexity of input data and the choice of training function.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Advanced Short-Term Wind Power Forecasting Based on CNN-BiLSTM - Lightweight Self-Attention (LWSA)
    (2025-01-01)
    Huang, Zhibin
    ;
    Jiriwibhakorn, Somchat
    Accurate short-term wind power forecasting is critical for maintaining grid stability and enhancing energy dispatch. However, the nonlinear, volatile, and uncertain nature of wind power poses significant challenges to traditional and deep learning models. To address this, a hybrid model named CNN-BiLSTM-LWSA is proposed, which integrates Convolutional Neural Networks (CNN) for local pattern extraction, Bidirectional Long Short-Term Memory (BiLSTM) networks for temporal modeling, and a Lightweight Self-Attention (LWSA) mechanism based on Lin-former. The LWSA module applies low-rank projections to reduce attention complexity from O(n²) to O(n), enabling efficient long-sequence learning while preserving global dependencies. Experi-ments were conducted using a full-year dataset (35,040 records at 15-minute intervals) from the Mahuangshan First Wind Farm in Ningxia, China. The model was tested under various input win-dow lengths (1h, 3h, 12h, 24h, and 32h). Results show that CNN-BiLSTM-LWSA consistently out-performs CNN-BiLSTM and CNN-BiLSTM-Attention in both accuracy and efficiency. Under a 24-hour input, it achieves an RMSE of 53.4 kW, MAE of 23.2 kW, and R<sup>2</sup> of 0.955 while reducing training and testing time by 54.8% and 47.1%, respectively, compared to the attention-based base-line. Even with a 32-hour input, the model maintains low prediction errors and stable R<sup>2</sup>, validating its scalability. The experimental results fully confirm that CNN-BiLSTM-LWSA effectively balances forecasting accuracy and computational cost across different temporal settings, offering a robust, efficient, and practical solution for short-term wind power forecasting applications.