USING DLP TO OPTIMIZE COMPUTER MODELS IN SCADA SYSTEMS
DOI:
https://doi.org/10.34185/1991-7848.itmm.2025.01.038Keywords:
Industry 4.0, SCADA, SIMD, parallel computing, finite difference schemes, vectorization, AVX-256.Abstract
This paper presents a study on the efficiency of applying data-level parallelism using SIMD technology to optimize computer models within SCADA systems. The focus is on implementing computational algorithms based on explicit and implicit finite difference schemes, which are widely used in industrial process modeling. Experimental research demonstrates improved computational performance achieved through the use of modern SIMD instructions, primarily AVX-256, enabling real-time data processing for complex simulation models in industrial control systems. It was found that explicit finite difference schemes exhibit better suitability for vectorization compared to implicit schemes implemented using the Thomas algorithm. The practical significance of the results lies in enhancing the efficiency of SCADA systems through the optimal utilization of modern CPU capabilities, offering tangible benefits for industrial enterprises adopting this technology.
References
Fraccaroli E., Padovani A. M., Quaglia D., Fummi F. Network Synthesis for Industry 4.0. Design, Automation & Test in Europe Conference & Exhibition (DATE). – 2020. P. 1692 – 1697.
Hennessy J. L., Patterson D. A. A new golden age for computer architecture. Communications of the ACM. – 2019. №2(62). P. 48 – 60.
Zhulkovskyi O., Zhulkovska I., Kurliak P., Sadovoi A., Ulianovska Yu., Vokhmianin H. Using asynchronous programming to improve computer simulation performance in energy systems. Energetika. – 2025. №1(71). P. 23 – 33.
Zheng R., Pai S. Efficient execution of graph algorithms on CPU with SIMD extensions. IEEE Access. – 2021. P. 262 – 276.
Zhulkovskyi O. O., Zhulkovska I. I., Vokhmianin H. Ya., Firsov O. D., Riabovolenko V. A. Research of progressive tools of parallel computations with the use of SIMD architecture. Informatics and Mathematical Methods in Simulation. – 2023. №3-4(13). P. 228 – 235.
Zhulkovskyi O., Zhulkovska I., Vokhmianin H., Firsov A., Tykhonenko I. Application of SIMD-instructions to increase the efficiency of numerical methods for solving SLAE. Computer Systems and Information Technologies. – 2024. №4. P. 126 – 133.
Intel® Intrinsics Guide.
URL: https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html (date of access: 05.04.2025).
Vuţă-Popescu D., Antofi I. C., Ciobanu C. B., Kertész C. Z. SIMD extensions - a historical perspective. IEEE Access. – 2024. P. 108 – 115.
