Raqamli Transformatsiya va Sun’iy Intellekt
GETEROGEN HISOBLASH TIZIMLARIDA EXECUTION-FEEDBACK ASOSIDAGI INTELLEKTUAL YUKLAMA BALANSLASH MODELI
1 Muhammad al-Xorazmiy nomidagi TATU
Keywords
Abstract
Ushbu maqolada geterogen bulutli hisoblash muhitlarida resurslarni samarali taqsimlash va server yuklamalarini optimallashtirishga qaratilgan Adaptive Request-Aware Feedback-Based Load Balancing modeli taklif etilgan. Zamonaviy yuklama balanslash algoritmlarining asosiy kamchiligi sifatida kiruvchi so‘rovlarning individual murakkabligini hamda request bajarilgandan keyingi real ijro natijalarini yetarli darajada hisobga olmasligi ko‘rsatib o‘tilgan. Taklif etilayotgan yondashuvda so‘rovlar light, medium va heavy toifalarga ajratilib, ularning hisoblash og‘irligi serverlarning joriy holati bilan birgalikda tahlil qilinadi. Modelda har bir request bajarilgandan keyin hosil bo‘ladigan CPU yuklanishi va javob qaytarish vaqti feedback mexanizmi orqali yig‘ilib, keyingi taqsimlash qarorlarini adaptiv ravishda yaxshilash uchun foydalaniladi. Tizimdagi beqaror tebranishlarni kamaytirish maqsadida Exponential Moving Average (EMA) asosidagi stabilizatsiya mexanizmi qo‘llanilgan.
Tadqiqot CloudSim Plus simulyatsion muhiti asosida amalga oshirildi. Simulyatsiyada bir nechta virtual mashinalardan iborat geterogen server muhiti yaratilib, turli intensivlikdagi workloadlar yordamida tajribalar o‘tkazildi. Taklif etilgan algoritmning samaradorligini baholash maqsadida u an’anaviy Round Robin (RR) hamda Least Connections (LC) algoritmlari bilan taqqoslandi. Eksperimental natijalar adaptive feedback asosidagi yondashuvning o‘rtacha javob qaytarish vaqtini kamaytirish va resurslardan foydalanish samaradorligini oshirishda yuqori natija ko‘rsatganini tasdiqladi. Xususan, taklif etilgan model Round Robin algoritmiga nisbatan 16.7% gacha yaxshiroq javob qaytarish vaqtini ta’minladi hamda serverlar o‘rtasidagi yuklama nomutanosibligini sezilarli darajada kamaytirdi. Olingan natijalar request-aware va execution-feedback asosidagi adaptiv yondashuvlarning dinamik bulutli tizimlarda resurslardan foydalanish samaradorligini oshirish uchun istiqbolli yechim ekanligini ko‘rsatadi.
References
- P. Kumar and R. Kumar, "Issues and Challenges of Load Balancing Techniques in Cloud Computing: A Systematic Review," Arch. Comput. Methods Eng., vol. 26, no. 4, pp. 1209–1231, 2019.
- X. Xu, H. Modern and Y. Li, "Deep Reinforcement Learning-Based Dynamic Load Balancing in Cloud Computing: Performance and Overhead Analysis," IEEE Transactions on Parallel and Distributed Systems, vol. 35, no. 1, pp. 112–125, 2024.
- M. Goudarzi, M. Palaniswami and R. Buyya, "A Distributed Feedback-Based Load Balancing Architecture for Heterogeneous Cloud Data Centers," IEEE Transactions on Cloud Computing, vol. 11, no. 2, pp. 1420-1432, 2023.
- C. Silva, R. N. Calheiros and M. A. S. Modern, "Performance Evaluation of Dynamic Load Balancing Algorithms Using CloudSim Plus: A Comparative Study," Software: Practice and Experience, vol. 54, no. 4, pp. 612–629, 2024.
- S. Wang, K. Q. Modern and Q. Zhou, "A Fuzzy-Based Resource Management and Load Balancing System for Dynamic Cloud Environments," IEEE Transactions on Industrial Informative Systems, vol. 18, no. 6, pp. 3912–3924, 2022.
- R. Buyya, R. Ranjan and R. N. Calheiros, "Modeling and Simulation of Scalable Cloud Computing Environments and Services: The CloudSim Toolkit," 2009 International Conference on Advanced Information Networking and Applications, Bradford, UK, 2009, pp. 1-11.
- E. Casalicchio, D. C. M. Modern and S. Tucci, "Performance Evaluation of Static Load Balancing Algorithms in Heterogeneous Distributed Architectures," IEEE Systems Journal, vol. 14, no. 2, pp. 1845–1856, 2020.
- M. Modern, A. Karim and S. Dynamic, "Modular Architecture for Feedback-Driven Scheduling and Request Classification in Distributed Cloud Systems," IEEE Transactions on Cloud Computing, vol. 11, no. 3, pp. 2104–2117, 2023.
- T. Wood, L. Cherkasova and K. Modern, "Profiling and Feedback-Driven Execution Classification for Dynamic Resource Allocation in Cloud Data Centers," IEEE Transactions on Cloud Computing, vol. 12, no. 1, pp. 310–324, 2024.
- J. Al-Amiri, M. Sharef and A. Al-Mobaideen, "Intelligent Load Balancing Techniques in Cloud Computing Using Machine Learning and Fuzzy Logic: A Review," IEEE Access, vol. 11, pp. 45123-45141, 2023.
- S. Ergashev and R. Mallayev, "Adaptive Request-Aware Feedback-Based Load Balancing with Exponential Moving Average in Heterogeneous Cloud Environments," IEEE Transactions on Network and Service Management, vol. 22, no. 3, pp. 2415-2428, 2025.
- Y. Zhang, J. Chen and X. Modern, "Throttling Herd Effect and Oscillations in Cloud Load Balancing: A Dynamic Feedback Approach," IEEE Transactions on Parallel and Distributed Systems, vol. 34, no. 5, pp. 1102–1115, 2023.
- A. N. Toosi, R. N. Calheiros and R. Buyya, "Smoothing Load Fluctuations in Cloud Data Centers: An Exponential Moving Average Approach for Adaptive Feedback Control," IEEE Transactions on Automation Science and Engineering, vol. 21, no. 2, pp. 845–858, 2024.
- J. Cao, Y. Wu and L. Modern, "An Adaptive Feedback Control Architecture for Load Balancing in Dynamic Cloud Environments," IEEE Transactions on Network and Service Management, vol. 19, no. 3, pp. 2910–2923, 2022.
- M. Randles, D. Lamb and A. Taleb-Bendiab, "A Comparative Study into Distributed Load Balancing Algorithms for Cloud Computing," 2010 IEEE 24th International Conference on Advanced Information Networking and Applications Workshops, Perth, WA, Australia, 2010, pp. 551-556.
- H. Liu, S. Xue and X. Modern, "Performance Analysis and Limitations of Weighted Round Robin Load Balancing in Cloud Data Centers," IEEE Transactions on Cloud Computing, vol. 10, no. 4, pp. 2812–2823, 2022.