152
VII.
CONCLUSION.
As the results of calculations have shown, in most cases, the calculation error is relatively
small, which indicates a successfully trained and correctly formed
ANN for a specific power
systems schemes.
Comparing the result using the Newton – Raphson method by calculating the values of the
voltage modulus and deflection angle at 6 loads of an electrical system using an artificial neural
network, we can see that the voltage modulus (maximum error is 0.0712% and minimum error is
0.0005%) and the voltage deviation (maximum error is 0.4038% and minimum error is 0.0003%)
. In addition, when we compare the results of the Newton – Raphson method by calculating the
active and reactive power values of 8 power transmission lines of an electrical system using an
artificial neural network, we can see that the active power (maximum error is 0.1596% and
minimum error is 0.0007%).
The demonstrated success of ANN applications in a broad range of problems and the
increasing
interest of researchers, vendors and electric power companies indicate the strength and
applicability of the ANN technology. In fact, power systems computing with neural nets is
considered one of the fastest growing field in power system engineering.
REFERENCES.
1.
Hao Songa, Yu Chena, Ning Zhoua, Genshe Chenb “Electricity
Consumption
Forecasting for Smart Grid using the Multi-Factor Back-Propagation Neural Network” A Dept. of
Electrical & Computer Engineering, Binghamton University, Binghamton, NY 13902 bIntelligent
Fusion Technology, Inc., Germantown, MD, USA, 20876, 2019.
2. Rafael “Artificial Neural Networks In Electric Power Industry” Technical Report of the
ISIS Group at the University of Notre Dame ISIS-94-007 April, 1994.
3. T.Kh. Nasyrov "Foundations of the general theory of normal and emergency modes of
power systems." Fan va Technology Publishing House - 2015, 224 p. (In Russian).
4. Yu H. Advanced Learning Algorithms of Neural Networks: Ph. D. dissertation / H. Yu.
USA: Graduate Faculty of Auburn University, 2011. — 130 p.
5. Hecht-Nielsen R., “Kolmogorov's Mapping Neural Network Existence Theorem”, Proc.
Int. Conf.
Neural Networks, v. III, IEEE Press, New York, 1987, 11–14.
6. Sheela K. G., Deepa S. N., “Review on methods to fix number of hidden neurons in
neural networks”, Mathematical
Problems in Engineering, 2013 (2013), 1–11.
7. Hecht-Nielsen R., “Kolmogorov's Mapping Neural Network Existence Theorem”, Proc.
Int. Conf. Neural Networks, v. III, IEEE Press, New York, 1987, 11–14.
8. Yuan H. C., Xiong F. L., Huai X. Y., “A method for estimating the number of hidden
neurons in feed-forward neural networks based on information entropy”,
Computers and
Electronics in Agriculture, 40:1 (2003), 57–64.
9. Refenes A. N., Chan E. B., “Sound recognition and optimal neural network
design”, Microprocessing and Microprogramming, 35:1 (1992), 783–789.
Do'stlaringiz bilan baham: