Application of Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference Systems in The Electrical Power System
Keywords:
artificial neural networks, Adaptive Neuro-Fuzzy Inference Systems, transient stability assessment, evaluation of generation system reliability, mid-term load forecastingAbstract
This paper will present the results of the study on the application of artificial neural networks and adaptive neuro-fuzzy inference systems to electrical power systems, which can be considered significant electrical power-related research to determine if it has the capability to enhance efficiency as well as test the accuracy of programs and hardware tests in electrical power systems. Additionally, the results can also be further analyzed for their validity and commercial applications. In this regard, some examples of its uses include: firstly, the assessment of the transient stability with respect to the key parameters of the synchronous generators, turbine control systems, fuel and frequency, automated pressure control systems, as well as the load-specific characteristics. The root mean square error for testing is 0.041. Secondly, the power generation system’s reliability index, through the application of artificial neural networks and adaptive neuro-fuzzy inference systems, learned the relationship between the installed power generation capacity and successfully predicted the power supply index failure as expected. The efficiency has a mean absolute percentage error of the testing results equal to 3.5219% and 4.0133%, respectively. Thirdly, the assessment of the electrical power system’s quality is done by analyzing the electrical reliability and quality of the distribution system in conjunction with the adaptive neuro-fuzzy inference systems by defining the ANFIS’ Power Reliability Index as the input and the Power Quality Index as the output. The power quality indexes selected are SARFl70, SARFl90, and SARFI110, which are the average number of times in which the voltage drops and overvoltage occur, respectively, for use in assessing the quality of the electrical power systems. The results of the experiment can measure accuracy, with the root mean square error being 0.0202 and 0.0038, respectively. Finally, medium-term load forecasting through artificial neural networks and adaptive neuro-fuzzy inference systems. The one-month forecast was conducted with just six sets of data inputs, which included past records of peak power (based on a 12-month, 9-month, 6-month, and 3-month moving average), the month code, and the Quarterly Ggross Domestic Product--QGDP and tested with 2, 3, and 4 hidden layer neural networks. The best results were then compared with the forecast obtained from the adaptive neuro-fuzzy inference systems. The results of both tests gave a mean absolute percentage error of 1.1527% and 3.8739%, respectively. The assessment of the study mentioned above revealed that the experimental results were considerably accurate and reliable and can be used as a guideline for further development and application for other components of the electrical power system.
References
Jang, J.-S. R. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665-685. doi: 10.1109/21.256541.
Jiriwibhakorn, S. (2011). Applications of neural networks in power system. Bangkok: Faculty of Engineering King Mongkut’s Institute of Technology Ladkrabang. (in Thai)
Jiriwibhakorn, S. (2022). Forecasting machines in power systems. Bangkok: Faculty of Engineering King Mongkut’s Institute of Technology Ladkrabang. (in Thai)
Kanas, T., & Phechrphakdee, C. (2022). Tunnel ventilator for electricity production for meat chicken broiler house. EAU Heritage Journal Science and Technology, 16(1), 154–161. Retrieved from https://he01.tci-thaijo.org/index.php/EAUHJSci/article/view/254087. (in Thai)
Katruksa, S. (2013). Facility energy sage modeling and medium term load forecasting with artificial Neural Networks And Adaptive Neuro-Fuzzy Inference Systems: An exploratory Study (Master’s thesis). King Mongkut’s Institute of Technology Ladkrabang. Thailand. (in Thai)
Katruksa, S. (2020). Mid-Term Load Forecasting based on Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference Systems: An exploratory study (Doctoral dissertation). King Mongkut’s Institute of Technology Ladkrabang. Thailand. (in Thai)
Katruksa, S., & Jiriwibhakorn, S. (2015). Facility energy usage modeling and medium term load forecasting with Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference Systems. Kasetsart Engineering Journal, 28(91), 61-69. (in Thai)
Katruksa, S., & Jiriwibhakorn, S. (2019). Application data for electricity load forecasting models. The 5th International Conference on Engineering, Applied Sciences and Technology (pp. 450-453). Luang Prabang, Laos PDR. doi: 10.1109/ICEAST.2019.8802527
Katruksa, S., & Jiriwibhakorn, S. (2020). Evaluation of mid-term load forecasting case study based on Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Networks (ANNs). International Review of Electrical Engineering (I.R.E.E.), 15(4), 283-293. https://doi.org/10.15866/iree.v15i4.17766
Meesut, P. (2009). Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference Systems. Management Information Systems. Bangkok: King Mongkut’s University of Technology North Bangkok. (in Thai)
Phootrakornchai, W., & Jiriwibhakorn, S. (2015). Online critical clearing time estimation using an adaptive neuro-fuzzy inference system (ANFIS). International Journal of Electrical Power and Energy Systems, 73, 170-181. https://doi.org/10.1016/j.ijepes.2015.03.024
Seangsai, A. (2013). Power system quality evaluation using Adaptive Neuro-Fuzzy Inference Systems: An exploratory Study (Master’s thesis). King Mongkut’s Institute of Technology Ladkrabang. Thailand. (in Thai)
The MathWorks Inc. (2023). Molor C. MATLAB & Simulink Release 2023a. Retrieved from https://www.mathworks.com/products/new_products/latest_features.html
Wannakam, K., & Jiriwibhakorn, S. (2018). Evaluation of generation system reliability using Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Networks (ANNs). International Review of Electrical Engineering (I.R.E.E.), 13(3), 204-212. https://doi.org/10.15866/iree.v13i3.13534
