KMITL

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

Browse

Search Results

Now showing 1 - 10 of 31

Some of the metrics are blocked by your
consent settings
Comparative Analysis of ANN and ANFIS-Based MPPT for Photovoltaic System
(2025-01-01)
Bi, Chenxing
;
Jiriwibhakorn, Somchat
Eco-friendly and sustainable energy sources, such as solar and wind power, have rapidly integrated into the grid in recent years. Solar power generation is influenced by factors such as radiation intensity and temperature. However, the intermittent nature of solar energy poses challenges for consistent power generation. Intelligent techniques are essential for maximizing power extraction. This study focuses on developing Artificial Intelligence-based Maximum Power Point Tracking (MPPT) methods in solar photovoltaic (PV) systems. Two AI techniques were implemented, and their performance was compared to achieve more efficient results. Real-time data from micro-nano grids in China were utilized to design a feed-forward neural network and an adaptive neural network-based MPPT system. These systems aim to optimize solar energy harvesting and enable integration into nano-grid systems, offering affordable and eco-friendly energy solutions for families in Thailand. The algorithms were developed using MATLAB/Simulink, and both techniques demonstrated excellent performance. Notably, the ANFIS-based MPPT system outperformed, achieving a tracking efficiency of 93% in PV systems.
Some of the metrics are blocked by your
consent settings
Time Series-Based Fault Detection and Classification in IEEE 9-Bus Transmission Lines Using Deep Learning
(2025-01-01)
Jiriwibhakorn, Somchat
;
Kanwal, Shazia
Transmission line faults present a significant threat to the stability of power systems, potentially causing widespread outages. Timely detection of these faults is essential to prevent substantial disruptions in the power supply. This paper explores a time series-based deep learning technique for fault detection and classification in the IEEE 9-bus system. Post asymmetrical fault current and voltage time series data have been used to train a convolutional neural network (CNN), representing normal and faulty conditions, with convolutional and ReLU layers. A fully connected layer is used to detect features without missing critical information of the signal, achieving MSE as zero for fault detection and 0.0149 for fault classification. This demonstrates the effectiveness of CNNs for real-time fault detection and classification in complex power grids. The robustness of the CNN model indicates its potential for deployment in practical applications, enhancing the reliability and resilience of the transmission network. Using deep learning techniques opens opportunities for further improvements in fault detection and location strategies within the power grid.
Some of the metrics are blocked by your
consent settings
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 (R2) 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.
Some of the metrics are blocked by your
consent settings
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 R2 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 R2, 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.
Some of the metrics are blocked by your
consent settings
Design of DC/AC Unidirectional Inverter Based on DSP with Second-Order Switching Sequence Control in Photovoltaic DC Nano-Grids
(2025-01-01)
Bi, Chenxing
;
Jiriwibhakorn, Somchat
Conventional inverters predominantly utilize Pulse-Width Modulation (PWM) control, operating in an intermediate state between the averaged and actual switching models. However, this approach often results in suboptimal output power quality and limited dynamic performance, which can compromise the operational stability of AC load systems. To address these limitations, this paper proposes a second-order Switching Sequence Control (SSC) strategy based on sliding mode theory, offering discrete-time control with enhanced robustness and precision. A comprehensive mathematical model of a single-phase LC inverter is developed and discretized. The SSC control algorithm is implemented using a TMS320F28335 Digital Signal Processor (DSP), with code generated via MATLAB/Simulink to streamline development and ensure real-time execution. Extensive simulations under various conditions demonstrate that the proposed inverter achieves excellent tracking accuracy, strong dynamic response, and reduced Total Harmonic Distortion (THD) is only 0.48%. Compared with conventional PWM, Selective Harmonic Elimination (SHE), and FPGA-based control methods, the SSC strategy significantly improves waveform fidelity and transient performance. These results confirm its suitability for high-performance applications in photovoltaic DC nanogrids, smart energy systems, and critical load support scenarios.
Some of the metrics are blocked by your
consent settings
A Novel Enhancement of the Classical Lambda Iteration Method for Solving Economic Load Dispatch Problem of Cost Function With Integrated Renewables
(2025-01-01)
Jiriwibhakorn, Somchat
;
Wongwut, Kamolwan
This paper presents a novel enhancement to the classical lambda iteration method for solving the economic load dispatch problem under modern power system conditions. The traditional LI method works well for simple cost functions, but it struggles with the complexities caused by valve-point effects and the growing use of renewable energy sources. Unlike metaheuristic methods that can be flexible but usually require a lot of computing power and are sensitive to how their settings are adjusted, the new λ-algorithm keeps the straightforward and predictable features of the original method while making it suitable for complicated situations involving non-convex costs and renewable energy sources. The algorithm incorporates mechanisms to handle non-smooth cost functions and account for variability from wind and solar generation. Its effectiveness is tested using simulations on four standard systems: an IEEE 57-bus system without renewable energy that cost $288,576; a modified IEEE 57-bus system with renewable energy that cost $283,774; a 38-generator system with a smooth cost function that cost $9,417,174.09 and CPU time of 1.3708 seconds; and a 40-generator system with valve-point effects that cost $121,714.07 and CPU time of 235.05 seconds. In all situations, the developed λ-algorithm provides affordable solutions while greatly cutting down on computing time, showing that it could be a useful, easy-to-use, and adaptable option for today’s ELD problems.
Some of the metrics are blocked by your
consent settings
Comparison of YOLOv8 Models for Aircraft Detection in Airport Apron Using Digital Image Processing
(2024-06-01)
Wiangkam, Nitipoom
;
Jiriwibhakorn, Somchat
Airport safety can be improved by efficient air traffic management, which monitors aircraft parking spots and controls their movement into them more efficiently. In addition to emergency situations, it can assist in accurately inspecting airport areas. Management costs can be reduced by reducing the workload of personnel in controlling and helping manage air and ground traffic. This research focuses on comparing the performance of various YOLOv8 models (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8nl, and YOLOv8nx) in an automated aircraft detection system using digital image processing techniques. The methodology involves collecting a dataset of 1,000 airport apron images with parked aircraft, dividing them into 900 training images and 100 testing images. The YOLOv8 models are trained on the training dataset, and their performance is evaluated on the testing dataset using confusion matrices. Experimental results reveal that YOLOv8nx achieves the highest average aircraft detection performance, with a precision of 0.94, recall of 0.74, and f1-score of 0.83. Additionally, YOLOv8n demonstrates the highest processing speed at 0.95 milliseconds. Consequently, YOLOv8n is suitable for applications requiring high-speed processing, while YOLOv8nx is ideal for tasks demanding the utmost performance efficiency.
Some of the metrics are blocked by your
consent settings
Advanced Fault Detection, Classification, and Localization in Transmission Lines: A Comparative Study of ANFIS, Neural Networks, and Hybrid Methods
(2024-01-01)
Kanwal, Shazia
;
Jiriwibhakorn, Somchat
Electric systems are getting more complex with time, and primitive protection methods such as traveling wave and impedance-based methods face limitations and shortcomings. This paper incorporates and presents the applications of an adaptive neuro-fuzzy inference system and compares it with a back propagation neural network, self-organizing map, and hybrid method of discrete wavelet with adaptive neuro-fuzzy inference system for fault detections, classification, and localization in transmission lines. These methods, in comparison with primitive methods, could be capable of detecting, identifying, and predicting the location of the faults more accurately. The IEEE 9-bus system is utilized to obtain data from one end of the transmission line to develop an ANFIS-based model. This system is simulated in MATLAB/Simulink for different fault cases at various locations. The three-phase voltage and current at one end of IEEE 9-bus number seven are taken for training. Three ANFIS models are developed for fault detection, classification, and localization and compared with other models. For verification of the models, mean square error, mean absolute error, and regression analysis have been computed and compared for all the models. All four techniques have performed well for fault classification, detection, and location. However, the percentage error for the ANFIS-based fault model is less compared to backpropagation, self-organizing map, and discrete wavelet transform with ANFIS. Therefore, the proposed ANFIS models can be implemented for deploying in real-time-based protection systems.
Some of the metrics are blocked by your
consent settings
Evaluation of the Power Demand for Economic Load Dispatch Problem Using Adaptive Neuro-Fuzzy Inference System and Artificial Neural Network
(2024-01-01)
Jiriwibhakorn, Somchat
;
Wongwut, Kamolwan
The evaluation of power demand is fundamental in the Economic Load Dispatch problem, ensuring that the generated power meets the needs of consumers reliably and efficiently in planning system operations. This paper presented two approaches using an Adaptive Neuro-Fuzzy Inference System (ANFIS) and an Artificial Neural Network (ANN) to evaluate the power demand. The modified IEEE 57-Bus system is considered the thermal units that incorporate renewables. The ANFIS and ANN are implemented using MATLAB online version R2023b. The results show that the ANN and ANFIS techniques are suitable for evaluating power demand. A comparison of both methods indicates that ANFIS is relatively superior to the ANNs techniques, considering the coefficient of determination of the ANNs and ANFIS were equal. The accuracy of its results in terms of prediction RMSE for the ANN and ANFIS of 10.147e-05 and 5.2177e-05 for the training and 14.639e-05 and 5.2177e-05 for the testing, respectively. Finally, the prediction accuracy of the ANFIS can be observed to be higher than that of the ANN, but the ANFIS takes longer to process. ANFIS is the method that can be appropriately applied to evaluate the power demand in this research. However, it could not guarantee for other research topics that ANFIS would be better than ANN for the RMSE. It depends on input and output data complexity and the training function type.
Some of the metrics are blocked by your
consent settings
Fault Detection in Transmission Lines Using CNN
(2024-01-01)
Kanwal, Shazia
;
Jiriwibhakorn, Somchat
Transmission line faults pose a significant risk to power systems, potentially leading to widespread outages. Detecting these faults using advanced algorithms is crucial for preventing major disruptions in power supply. In this paper, we work on a fault detection technique for the IEEE 9-bus system based on deep learning. By training a Convolutional Neural Network (CNN) on features extracted from both normal and faulty conditions, we achieve an accuracy of 86%. This high accuracy underscores the potential of CNNs for real-world implementation in fault detection systems. The robustness of the CNN approach suggests its viability for deployment in complex, real-time systems, offering improved reliability and resilience against transmission line faults. Additionally, utilizing deep learning techniques opens avenues for further refinement and optimization of fault detection strategies in the power grid.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results