Forecasting Stability of Smart Grids using Highway Deep Pyramid Convolutional Neural Network (HPDCNN) Approach
Keywords:
Smart grid, Electricity, Forecasting Stability, Stable, MinMaxScaler, Highway Deep Pyramid Convolutional Neural Network (HPDCNN), VoltageAbstract
This paper proposes the Highway Deep Pyramid Convolutional Neural Network (HPDCNN) technique for smart grid stability forecasting. The objective is to enhance the accuracy and reliability of stability predictions in smart grids. The technique aims to reduce errors and uncertainties associated with stability predictions, thereby improving the overall performance of smart grids. The HPDCNN technique controls the strengths of highway networks and pyramid networks to reduce the impact of noise and irrelevant features in the data. This reduction in noise improves the robustness and accuracy of stability predictions, enhancing the reliability of the technique. The HPDCNN approach effectively captures both temporal and spatial dependencies in smart grid data by combining the strengths of highway networks and pyramid networks. The highway network enables the model to learn long-term dependencies, while the pyramid network facilitates multi-scale feature extraction. Using the HDCNN algorithm, the paper presents a methodology for predicting the stability of smart grids based on various input parameters such as power generation, consumption patterns, weather conditions, and grid infrastructure. The algorithm is trained using labeled data, where each data point is classified as either stable or unstable based on the actual stability status of the corresponding smart grid. Once trained, the HDCNN algorithm can classify new, unseen data points as stable or unstable, providing insights into the current and future stability of the smart grid. By identifying unstable grids, operators and energy management systems can take appropriate actions to prevent potential disruptions or outages, ensuring the reliable and efficient operation of the smart grid system. Experimental results demonstrate that the HPDCNN technique achieves an accuracy rate of over 95%. The proposed schema is evaluated using testing and training values, along with a confusion matrix, to validate its performance. Overall, the proposed HPDCNN technique has the potential to improve the accuracy and reliability of stability predictions, leading to more efficient and sustainable smart grid systems. The Proposed FSSG-HPDCNN approach accuracy value is 99.88% which is higher than other existing methods like FSSG-WHO, FSSG-PSO, and FSSG-HBO methods
Downloads
References
B. Schäfer, M. Matthiae, M. Timme, and D. Witthaut, 2015. Decentral smart grid control. New journal of physics, 17(1), p.015002.
B. Schäfer, C. Grabow, S. Auer, J. Kurths, D. Witthaut, and M. Timme, 2016. Taming instabilities in power grid networks by decentralized control. The European Physical Journal Special Topics, 225, pp.569-582.
J.P. Kleijnen, 2018. Design and analysis of simulation experiments (pp. 3-22). Springer International Publishing.
A. Ulbig, T.S. Borsche, and G. Andersson, 2014. Impact of low rotational inertia on power system stability and operation. IFAC Proceedings Volumes, 47(3), pp.7290-7297.
D. Manik, D. Witthaut, B. Schäfer, M. Matthiae, A. Sorge, M. Rohden, E. Katifori, and M. Timme, 2014. Supply networks: Instabilities without overload. The European Physical Journal Special Topics, 223, pp.2527-2547.
P. Kundur, 1994. „Power System Stability and Control” McGraw.
W.W. Price, C.W. Taylor, and G.J. Rogers, 1995. Standard load models for power flow and dynamic performance simulation. IEEE Transactions on power systems, 10(CONF-940702-).
T. Nishikawa, and A.E. Motter, 2015. Comparative analysis of existing models for power-grid synchronization. New Journal of Physics, 17(1), p.015012.
K. Schmietendorf, J. Peinke, R. Friedrich, and O. Kamps, 2014. Self-organized synchronization and voltage stability in networks of synchronous machines. The European Physical Journal Special Topics, 223, pp.2577-2592.
O. Kamps, 2014. Characterizing the fluctuations of wind power production by multi-time statistics. In Wind Energy-Impact of Turbulence (pp. 67-72). Berlin, Heidelberg: Springer Berlin Heidelberg.
K.C. Budka, J.G. Deshpande, and M. Thottan, 2016. Communication networks for smart grids. Springer London Limited.
S.K. Routray, D. Gopal, A. Pallekonda, A. Javali, and S. Kokkirigadda, 2021, January. Measurement, control and monitoring in smart grids using nbiot. In 2021 6th International Conference on Inventive Computation Technologies (ICICT) (pp. 229-234). IEEE.
A.A. Freitas, 2014. Comprehensible classification models: a position paper. ACM SIGKDD explorations newsletter, 15(1), pp.1-10.
J. Huysmans, K. Dejaeger, C. Mues, J. Vanthienen, and B. Baesens, 2011. An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models. Decision Support Systems, 51(1), pp.141-154.
M.R. Berthold, and K.P. Huber, 1999. Constructing fuzzy graphs from examples. Intelligent Data Analysis, 3(1), pp.37-53.
H. Pierreval, 1996. A metamodeling approach based on neural networks. Int. Journal in Computer Simulation, 6(3), p.365.
T. Yoshida, and S. Nakasuka, 1989, December. A dynamic scheduling for flexible manufacturing systems: hierarchical control and dispatching by heuristics. In Proceedings of the 28th IEEE Conference on Decision and Control, (pp. 846-852). IEEE.
H. Pierreval, and H. Ralambondrainy, 1992. A simulation and learning technique for generating knowledge about manufacturing systems behavior. Artificial Intelligence in Operational Research, pp.239-252.
J.D. McCalley, S. Wang, Q.L. Zhao, G.Z. Zhou, R.T. Treinen, and A.D. Papalexopoulos, 1997. Security boundary visualization for systems operation. IEEE Transactions on Power Systems, 12(2), pp.940-947.
B. Jayasekara, and U.D. Annakkage, 2006. Derivation of an accurate polynomial representation of the transient stability boundary. IEEE transactions on Power Systems, 21(4), pp.1856-1863.
C. Li, 2020. Designing a short-term load forecasting model in the urban smart grid system. Applied Energy, 266, p.114850.
T. Alquthami, M. Zulfiqar, M. Kamran, A.H. Milyani, and M.B. Rasheed, 2022. A performance comparison of machine learning algorithms for load forecasting in smart grid. IEEE Access, 10, pp.48419-48433.
G. Hafeez, I. Khan, S. Jan, I.A. Shah, F.A. Khan, and A. Derhab, 2021. A novel hybrid load forecasting framework with intelligent feature engineering and optimization algorithm in smart grid. Applied Energy, 299, p.117178.
S.F. Ali, and A. Ramaswamy, 2009. Optimal fuzzy logic control for MDOF structural systems using evolutionary algorithms. Engineering Applications of Artificial Intelligence, 22(3), pp.407-419.
X. Liu, Z. Xiao, R. Zhu, J. Wang, L. Liu, and M. Ma, 2020. Edge sensing data-imaging conversion scheme of load forecasting in smart grid. Sustainable Cities and Society, 62, p.102363.
M. Ali, M. Adnan, and M.Tariq, 2019. Optimum control strategies for short term load forecasting in smart grids. International journal of electrical power & Energy systems, 113, pp.792-806.
M. Zulfiqar, M. Kamran, M.B. Rasheed, T. Alquthami, and A.H. Milyani, 2023. A hybrid framework for short term load forecasting with a navel feature engineering and adaptive grasshopper optimization in smart grid. Applied Energy, 338, p.120829.
F. Zheng, Q. Yan, V.C. Leung, F.R. Yu, and Z. Ming, 2022. HDP-CNN: Highway deep pyramid convolution neural network combining word-level and character-level representations for phishing website detection. Computers & Security, 114, p.102584.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
