SavedAdd your journal

Journals / EMO Bilimsel Dergi / 2023 / Cilt: 13 - Sayı: 1

A Brief Review on the Use of Deep Learning Techniques in Smart Grid Applications

Akıllı Şebeke Uygulamalarında Derin Öğrenme Tekniklerinin Kullanımına İlişkin Kısa Bir İnceleme

Reyhan SAĞ
Zeynep HASIRCI TUĞCU
Pages
41–61
Publication Date
2023-01-23
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This study shows that the applications of DL techniques will be increasingly involved in smart grid systems and will make significant contributions to improving the reliability, security, and durability of the grid.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The smart grid is based on the principle of continuous collection and interpretation of high-dimensional and diverse data from the electricity grid, and optimum management of the processes from the generation of energy to its delivery to the end user.
📊
Key Findings & Data:Therefore, the integration of advanced measurement infrastructure, control technologies, and information & communication technologies (ICT) into the network is a quite crucial issue.
💡
Conclusion & Impact:This study shows that the applications of DL techniques will be increasingly involved in smart grid systems and will make significant contributions to improving the reliability, security, and durability of the grid.
🔬Design:Review & Systematic Survey
📍Scope:Comprehensive Sample
⚙️Variables:akıllı şebeke · yapay zeka · makine öğrenmesi

Abstract

The smart grid is based on the principle of continuous collection and interpretation of high-dimensional and diverse data from the electricity grid, and optimum management of the processes from the generation of energy to its delivery to the end user. Therefore, the integration of advanced measurement infrastructure, control technologies, and information & communication technologies (ICT) into the network is a quite crucial issue. However, traditional modeling, optimization, and control technologies have some limitations in processing data collected over the grid. Therefore, the use of deep learning (AI) techniques in the smart grid is becoming more popular lately. In this study, a brief review of current research on the use of some common DL techniques in smart grids is presented. The review focuses on smart grid problems such as load forecasting and estimation, microgrid, demand response, fault detection and state prediction, power system analysis and control, cyber security and renewable energy generation, and related literature is presented. This study shows that the applications of DL techniques will be increasingly involved in smart grid systems and will make significant contributions to improving the reliability, security, and durability of the grid.

Özet

Akıllı şebeke, elektrik şebekesinden yüksek boyutlu ve çeşitli yapılardaki verilerin sürekli olarak toplanması ve anlamlandırılması ile enerjinin üretiminden son kullanıcıya ulaşmasına kadar olan süreçlerin optimum şekilde yönetilmesi esasına dayanır. Bu nedenle çağın gereklerine uygun gelişmiş ölçüm altyapısının, kontrol teknolojilerinin ve bilgi & iletişim teknolojilerinin (ICT) şebekeye entegrasyonu oldukça önemli bir konudur. Fakat, geleneksel modelleme, optimizasyon ve kontrol teknolojilerinin şebeke üzerinden toplanan verilerin işlenmesinde bazı sınırlamaları bulunmaktadır. Bu nedenle, son zamanlarda akıllı şebekede derin öğrenme (DL) tekniklerinin kullanımı daha popüler hale gelmektedir. Bu çalışmada bazı yaygın DL tekniklerinin akıllı şebekelerdeki kullanımına ilişkin yapılan mevcut araştırmaların yapılandırılmış bir incelemesi sunulmaktadır. İncelemede, özellikle yük tahmini ve kestirimi, mikro şebeke, talep yanıtı, hata tespiti ve durum tahmini, güç sistemi analizi ve kontrolü, siber güvenlik ve yenilenebilir enerji üretimi gibi akıllı şebeke problemlerine odaklanılmış, ve ilgili literatür sunulmuştur. Bu çalışma, DL teknikleri uygulamalarının hem akıllı şebeke sistemlerinde giderek artan oranda yer alacağını hem de şebekenin güvenilirliğini, güvenliğini ve dayanıklılığını iyileştirmede önemli katkılar sağlayacağını göstermektedir.

🔖

Cite This Article

SAĞ, R., TUĞCU, Z. H. (2023). A Brief Review on the Use of Deep Learning Techniques in Smart Grid Applications. EMO Bilimsel Dergi, Cilt: 13 - Sayı: 1, 41–61. https://ajindex.com/articles/878506

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (1)

  1. Smart Grid System Report, U.S. Department of Energy, Çevrimiçi: https://www.energy.gov/sites/prod/files/2019/02/f59/Smart%20Grid%20System%20Report%20November%202018_1.pdf (erişim 25 Eylül 2022). [2] D. Zhang, X. Han and C. Deng, "Review on the research and practice of deep learning and reinforcement learning in smart grids," in CSEE Journal of Power and Energy Systems, vol. 4, no. 3, pp. 362-370, September 2018, doi: 10.17775/CSEEJPES.2018.00520. [3] Q. V. Pham, M. Liyanage, N. Deepa,, M. VVSS, S. Reddy, P. K. R. Maddikunta, and W. J. Hwang, Deep Learning For İntelligent Demand Response And Smart Grids: A Comprehensive Survey, Arxiv Preprint Arxiv:2101.08013, 20 Jan, 2021, doi: https://doi.org/10.48550/arXiv.2101.08013 [4] R. S. Sutton, and A. G. Barto, Reinforcement Learning an Introduction, Cambridge, MA: MIT Press, 1998. [5] X. S. Chen, and Y. M. Yang, “Reinforcement Learning: Survey of Recent Work,” Application Research of Computers, vol. 27, no. 8, pp. 2834–2838, Chinese,August,2010. [6] D. Zhang, X. Han and C. Deng, "Review on the Research and Practice of Deep Learning and Reinforcement Learning in Smart Grids," in CSEE Journal of Power and Energy Systems, vol. 4, no. 3, pp. 362-370, September 2018, doi: 10.17775/CSEEJPES.2018.00520. [7] I. Voynichka, Machine learning for the smart grid, Erişim: http://cs229.stanford.edu/proj2014/Iliana%20Voynichka,%20Machine%20Learning%20for%20the%20Smart%20Grid.pdf. [8] Xishuang Dong, Lijun Qian and Lei Huang, "Short-term load forecasting in smart grid: A combined CNN and K-means clustering approach," 2017 IEEE International Conference on Big Data and Smart Computing (BigComp), 2017, pp. 119-125, doi: 10.1109/BIGCOMP.2017.7881726. [9] Y. He, J. Deng and H. Li, "Short-Term Power Load Forecasting with Deep Belief Network and Copula Models," 2017 9th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2017, pp. 191-194, doi: 10.1109/IHMSC.2017.50. [10] T. Hossen, A. S. Nair, R. A. Chinnathambi and P. Ranganathan, "Residential Load Forecasting Using Deep Neural Networks (DNN)," 2018 North American Power Symposium (NAPS), 2018, pp. 1-5, doi: 10.1109/NAPS.2018.8600549. [11] V. Mnih, H. Larochelle, and G. Hinton, “Conditional restricted Boltzmann machines for structured output prediction,” in Proceedings of the International Conference on Uncertainty in Artificial Intelligence, Barcelona, Spain, Jul. 14–17, 2011. [12] G. W. Taylor, G. E. Hinton, and S. T. Roweis, “Two distributed-sta