Russian Federation
Russian Federation
Russian Federation
Russian Federation
UDK 004.383 Специализированные вычислительные машины
The article explores innovative methods of applying neural networks and deep learning to improve energy efficiency in very large-scale integration (VLSI) circuits. As design complexity increases and energy consumption requirements become more stringent, traditional analytical approaches demonstrate limited effectiveness. Neural network technologies allow for the identification of non-linear dependencies between circuit parameters and their energy consumption, providing a breakthrough in optimization. Key areas include predicting energy consumption at the design stage using regression models, dynamic power management through adaptive voltage/frequency scaling (DVFS), optimizing circuit element topology, and minimizing leakage currents. Experimental data demonstrate a 30-40% reduction in energy consumption compared to classical methods through the use of hybrid architectures with hardware accelerators, dynamic computation precision scaling (8-bit operations instead of 32-bit), and in-memory data processing (pim architectures). special attention is given to methodological aspects: development of adaptive learning algorithms with gradient descent, integration of rnn and lstm networks for temporal analysis, and model verification procedures considering technological parameter variation. The study confirms that neural network approaches provide multi-criteria optimization, balancing performance, energy consumption, and chip area
Neural networks, power consumption, very-large-scale integration (VLSI) circuits, optimization, deep learning, dynamic voltage and frequency scaling (DVFS), power consumption forecasting, adaptive methods, multi-criteria optimization, training algorithms
1. Yang Y, Li D, Wang D. Dynamic Analysis of the Switched-Inductor Buck-Boost Converter Based on the Memristor. Electronics. 2021; 10(4):452. DOI:https://doi.org/10.3390/electronics10040452
2. Brito TM, Colombo DM, Moreno RL, El-Sankary K. CMOS Voltage Reference Using a Self-Cascode Composite Transistor and a Schottky Diode. Electronics. 2019; 8(11):1271. DOI:https://doi.org/10.3390/electronics8111271
3. Novikova E, Doynikova E, Gaifulina D, Kotenko I. Construction and Analysis of Integral User-Oriented Trustworthiness Metrics. Electronics. 2022; 11(2):234. DOI:https://doi.org/10.3390/electronics11020234
4. Yang D, Mai Ngoc K, Shin I, Lee K-H, Hwang M. Ensemble-Based Out-of-Distribution Detection. Electronics. 2021; 10(5):567. DOI:https://doi.org/10.3390/electronics10050567
5. Arti Sahu, Prof. Saima Khan, Prof. Sandip Nemade, & Dr. Divya Jain. Design and Optimization of Low-Power VLSI Circuits for High-Performance Computing. International Journal of Engineering and Computer Science. 2025; 14(02), rr.26804–26813. DOI:https://doi.org/10.18535/ijecs.v14i02.4971
6. G. R. Kumar1 and Dr. Ram Mohan Singh Bhadoria. Power Optimization Techniques in VLSI Circuits for Signal Processing Applications. International Journal of Advanced Research in Science, Communication and Technology (IJARSCT). 2023; 3(2), pp.602-606. DOI:https://doi.org/10.48175/568
7. Zolnikov, V. K. Kompyuternoe modelirovanie rabotosposobnosti elektricheskoy skhemy v sistemakh avtomatizatsii proektirovaniya / V. K. Zolnikov, S. V. Stoyanov, Ye. V. Shmakov, N. N. Litvinov // Modelirovanie sistem i protsessov. – 2024. – T. 17, № 3. – S. 26-36. – DOIhttps://doi.org/10.12737/2219-0767-2024-24-34. – EDN EJJKJP.
8. Rajeshwar B., Dr. Anvesh Thatikonda. Optimizing VLSI Implementation: A Neural Network Approach. International Journal of Intelligent Systems and Applications in Engineering (IJISAE). 2024; 12(21s), rr.2954–2958.
9. Skvortsova, T. V. Formalizatsiya verifikatsii topologii i elektricheskoy skhemy dlya sistem avtomatizirovannogo proektirovaniya / T. V. Skvortsova, K. V. Zolnikov, A. M. Plotnikov, I. V. Skorkin // Modelirovanie sistem i protsessov. – 2024. – T. 17, № 3. – S. 61-70. – DOIhttps://doi.org/10.12737/2219-0767-2024-59-68. – EDN DUYQHJ.
10. Ketan J. Raut, Abhijit V. Chitre, Minal S. Deshmukh and Kiran Magar (2021) Low Power VLSI Design Techniques: A Review. Journal of University of Shanghai for Science and Technology. 2021; 23(11), rr.172-183. DOI:https://doi.org/10.51201/JUSST/21/11881
11. Poluektov, A. V. Povyshenie formalizatsii zadach verifikatsii topologii i elektricheskoy skhemy dlya sistem avtomatizirovannogo proektirovaniya / A. V. Poluektov, K. V. Zolnikov, A. V. Achkasov, Yu. A. Chevychelov // Modelirovanie sistem i protsessov. – 2024. – T. 17, № 1. – S. 102-111. – DOIhttps://doi.org/10.12737/2219-0767-2024-17-1-102-111. – EDN QIKKRO.
12. Clemente A, Ramos GA, Costa-Castelló R. Voltage H∞ Control of a Vanadium Redox Flow Battery. Electronics. 2020; 9(10):1567. DOI:https://doi.org/10.3390/electronics9101567
13. Mochalov, V. P. Algoritm dinamicheskogo raspredeleniya i balansirovki nagruzki v raspredelennykh oblachnykh vychisleniyakh / V. P. Mochalov, N. Yu. Bratchenko, D. V. Gosteva // Modelirovanie sistem i protsessov. – 2024. – T. 17, № 1. – S. 92-102. – DOIhttps://doi.org/10.12737/2219-0767-2024-17-1-92-102. – EDN EWMPYM.
14. Zheng B, Zhang J, Sun G, Ren X. EnGe-CSNet: A Trainable Image Compressed Sensing Model Based on Variational Encoder and Generative Networks. Electronics. 2021; 10(9):1089. DOI:https://doi.org/10.3390/electronics10091089
15. Achkasov, A.V. Osobennosti proektirovaniya mikroskhem, vypolnennykh po gluboko-submikronnym tekhnologiyam / A.V. Achkasov, M.V. Solodilov, N.N. Litvinov, P.A. Chubunov, V.K. Zolnikov, D.V. Shekhovtsov, O.L. Bordyuzha // Modelirovanie sistem i protsessov. – 2022. – T. 15, № 4. – S. 7-17.
16. Kaisheng Ma, Xueqing Li, Huichu Liu, Xiao Sheng, Yiqun Wang, Karthik Swaminathan, Yongpan Liu, Yuan Xie, John Sampson, and Vijaykrishnan Narayanan. Dynamic Power and Energy Management for Energy Harvesting Nonvolatile Processor Systems. ACM Trans. Embed. Comput. Syst. 2017; 16(4):107. DOI:https://doi.org/10.1145/3077575
17. Yagodkin, A.S., Razrabotka algoritmov i programm analiza elektricheskikh kharakteristik BIS / A.S. Yagodkin, V.K. Zolnikov, T.V. Skvortsova, A.V. Achkasov, S.A. Kuznetsov, F.V. Makarenko // Modelirovanie sistem i protsessov. – 2022. – T. 15, № 3. – S. 136-148.
18. Gaur, A.S., & Budakoti, J. Energy Efficient Advanced Low Power CMOS Design to reduce power consumption in Deep Submicron Technologies in CMOS Circuit for VLSI Design. International Journal of Advanced Research in Computer and Communication Engineering. 2014; 3(6), rr.7000-7008
19. Skvortsova, T. V. Formalizatsiya verifikatsii topologii i elektricheskoy skhemy dlya sistem avtomatizirovannogo proektirovaniya / T. V. Skvortsova, K. V. Zolnikov, A. M. Plotnikov, I. V. Skorkin // Modelirovanie sistem i protsessov. – 2024. – T. 17, № 3. – S. 61-70. – DOIhttps://doi.org/10.12737/2219-0767-2024-59-68. – EDN DUYQHJ.
20. Khan FA, Shees MM, Alsharekh MF, Alyahya S, Saleem F, Baghel V, Sarwar A, Islam M, Khan S. Open-Circuit Fault Detection in a Multilevel Inverter Using Sub-Band Wavelet Energy. Electronics. 2022; 11(1):123. DOI:https://doi.org/10.3390/electronics11010123.
