NATMOS-WOA: یک رویکرد جدید برای مدیریت ترافیک در شبکه‌های نرم‌افزاری تعریف‌شده با استفاده از الگوریتم بهینه سازی نهنگ
محمدرضا فرقانی
1
(
دانشکده مهندسی کامپیوتر، واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران.
)
شریفه السادات میرخلف
2
(
دانشکده مهندسی کامپیوتر، واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران.
)
کلید واژه: الگوریتم بهینه‌سازی نهنگ, شبکه‌های نرم‌افزار محور, تعادل بار دینامیک, مهندسی ترافیک, مسیریابی هوشمند, کاهش تأخیر.,
چکیده مقاله :
محاسبات ابری به دلیل ارائه عملکرد بالا در پردازش و خدمات‌رسانی به کاربران شبکه، به‌عنوان یک رویکرد کارآمد شناخته می‌شود، اما همچنان با چالش‌هایی مانند تأخیر پردازش بالا مواجه است. ترکیب محاسبات ابری و شبکه‌های نرم‌افزار محور (SDN) می‌تواند به بهبود این محدودیت‌ها کمک کند. در این مقاله، یک روش نوین مبتنی بر الگوریتم بهینه‌سازی نهنگ (WOA) برای انتخاب بهینه ضریب توزیع بار در تخصیص زمان اجرای وظایف ارائه‌شده است که منجر به کاهش تأخیر در شبکه می‌شود. الگوریتم بهینه‌سازی نهنگ در مطالعات متعددی برای بهینه‌سازی تخصیص منابع و تعادل بار در محیط‌های محاسبات ابری به کار گرفته‌شده است. به‌عنوان نمونه، یک استراتژی زمان‌بندی چندهدفه مبتنی بر WOA برای زمان‌بندی وظایف در محاسبات ابری پیشنهاد شده است که هدف آن به حداقل رساندن زمان تکمیل وظایف از طریق استفاده بهینه از منابع ماشین‌های مجازی و حفظ تعادل بار میان آن‌ها است؛ این امر منجر به کاهش هزینه عملیاتی سیستم می‌شود. علاوه بر این، الگوریتم WOA برای تخصیص بهینه وظایف به ماشین‌های مجازی مورداستفاده قرار گرفته است که تعداد مهاجرت‌های ماشین‌های مجازی را کاهش داده و درنتیجه، هزینه مهاجرت و مصرف انرژی را به حداقل می‌رساند. همچنین، این الگوریتم به‌عنوان ابزاری کارآمد برای مقایسه نتایج در زمینه تعادل بار، زمان‌بندی منابع و بهبود بهره‌وری انرژی در سیستم‌های ابری به‌کاررفته شده است.
چکیده انگلیسی :
Cloud computing is recognized as an efficient approach due to its high performance in processing and serving network users. However, this technology still faces challenges such as high processing latency. The integration of cloud computing and software-defined networks (SDN) can help address these limitations. In this paper, a novel method based on the Whale Optimization Algorithm (WOA) is proposed for optimal selection of the load distribution coefficient in task execution time allocation, which leads to reduced network latency. The Whale Optimization Algorithm has been employed in numerous studies for optimizing resource allocation and load balancing in cloud computing environments. For instance, a multi-objective scheduling strategy based on WOA has been proposed for task scheduling in cloud computing, aiming to minimize task completion time by optimally utilizing virtual machine resources and maintaining load balance among them. This results in reduced operational costs of the system. Additionally, the WOA algorithm has been used for optimal task allocation to virtual machines, reducing the number of virtual machine migrations and, consequently, minimizing migration costs and energy consumption. Furthermore, this algorithm has been utilized as an effective tool for comparing results in the areas of load balancing, resource scheduling, and improving energy efficiency in cloud systems.
[1] Y. Li et al., "Enhancing the Internet of Things with Knowledge-Driven Software-Defined Networking Technology: Future Perspectives," (in eng), Sensors (Basel), vol. 20, no. 12, Jun 19 2020, doi: 10.3390/s20123459.
[2] R. Duo, C. Wu, T. Yoshinaga, J. Zhang, and Y. Ji, "SDN-based Handover Scheme in Cellular/IEEE 802.11p Hybrid Vehicular Networks," (in eng), Sensors (Basel), vol. 20, no. 4, Feb 17 2020, doi: 10.3390/s20041082.
[3] M. Forghani, M. Soltanaghaei, and F. Z. Boroujeni, "Dynamic optimization scheme for load balancing and energy efficiency in software-defined networks utilizing the krill herd meta-heuristic algorithm," Computers and Electrical Engineering, vol. 114, p. 109057, 2024.
[4] W. Sun and S. Guan, "A GRU-based traffic situation prediction method in multi-domain software defined network," (in eng), PeerJ Comput Sci, vol. 8, p. e1011, 2022, doi: 10.7717/peerj-cs.1011.
[5] A. Sharma, V. Balasubramanian, and J. Kamruzzaman, "A Temporal Deep Q Learning for Optimal Load Balancing in Software-Defined Networks," (in eng), Sensors (Basel), vol. 24, no. 4, Feb 14 2024, doi: 10.3390/s24041216.
[6] M. Forghani and F. Zamani Boroujeni, "Dynamic Load Balancing Improvement in Software-Defined Networks Using Fuzzy Multi-Objective Programming Algorithms," Journal of Information and Communication Technology, vol. 61, no. 61, p. 55, 2024.
[7] J. Gong and A. Rezaeipanah, "A fuzzy delay-bandwidth guaranteed routing algorithm for video conferencing services over SDN networks," (in eng), Multimed Tools Appl, pp. 1-30, Jan 23 2023, doi: 10.1007/s11042-023-14349-6.
[8] M. Hussain, N. Shah, R. Amin, S. S. Alshamrani, A. Alotaibi, and S. M. Raza, "Software-Defined Networking: Categories, Analysis, and Future Directions," (in eng), Sensors (Basel), vol. 22, no. 15, Jul 25 2022, doi: 10.3390/s22155551.
[9] A. Shafique, G. Cao, M. Aslam, M. Asad, and D. Ye, "Application-Aware SDN-Based Iterative Reconfigurable Routing Protocol for Internet of Things (IoT)," (in eng), Sensors (Basel), vol. 20, no. 12, Jun 22 2020, doi: 10.3390/s20123521.
[10] G. Wassie, J. Ding, and Y. Wondie, "Traffic prediction in SDN for explainable QoS using deep learning approach," (in eng), Sci Rep, vol. 13, no. 1, p. 20607, Nov 23 2023, doi: 10.1038/s41598-023-46471-8.
[11] K. T. Mehmood, S. Atiq, and M. M. Hussain, "Enhancing QoS of Telecom Networks through Server Load Management in Software-Defined Networking (SDN)," (in eng), Sensors (Basel), vol. 23, no. 23, Nov 22 2023, doi: 10.3390/s23239324.
[12] H. Xue, K. T. Kim, and H. Y. Youn, "Dynamic Load Balancing of Software-Defined Networking Based on Genetic-Ant Colony Optimization," (in eng), Sensors (Basel), vol. 19, no. 2, Jan 14 2019, doi: 10.3390/s19020311.
[13] Z. Arefian, M. R. Khayyambashi, and N. Movahhedinia, "Delay reduction in MTC using SDN based offloading in Fog computing," (in eng), PLoS One, vol. 18, no. 5, p. e0286483, 2023, doi: 10.1371/journal.pone.0286483.
[14] R. A. Ammal, S. Pc, and V. Ss, "Termite inspired algorithm for traffic engineering in hybrid software defined networks," (in eng), PeerJ Comput Sci, vol. 6, p. e283, 2020, doi: 10.7717/peerj-cs.283.
[15] R. Perez, M. Rivera, Y. Salgueiro, C. R. Baier, and P. Wheeler, "Moving Microgrid Hierarchical Control to an SDN-Based Kubernetes Cluster: A Framework for Reliable and Flexible Energy Distribution," (in eng), Sensors (Basel), vol. 23, no. 7, Mar 23 2023, doi: 10.3390/s23073395.
[16] J. Chen et al., "AQMDRL: Automatic Quality of Service Architecture Based on Multistep Deep Reinforcement Learning in Software-Defined Networking," (in eng), Sensors (Basel), vol. 23, no. 1, Dec 30 2022, doi: 10.3390/s23010429.
[17] K. Govindarajan and V. S. Kumar, "An intelligent load balancer for software defined networking (SDN) based cloud infrastructure," in 2017 second international conference on electrical, Computer and Communication Technologies (ICECCT), 2017: IEEE, pp. 1-6.
[18] S. Manzoor, X. Hei, and W. Cheng, "A multi-controller load balancing strategy for software defined Wifi networks," in International Conference on Cloud Computing and Security, 2018: Springer, pp. 622-633.
[19] A. A. Ateya et al., "Chaotic salp swarm algorithm for SDN multi-controller networks," Engineering Science and Technology, an International Journal, vol. 22, no. 4, pp. 1001-1012, 2019.
[20] S. P. Sahoo and M. R. Kabat, "The multi-constrained multicast routing improved by hybrid bacteria foraging-particle swarm optimization," Computer Science, vol. 20, no. 2, 2019.
[21] A. Guo and C. Yuan, "Network intelligent control and traffic optimization based on SDN and artificial intelligence," Electronics, vol. 10, no. 6, p. 700, 2021.
[22] Y.-C. Chang, W.-X. Cai, and J.-W. Jhuang, "Bacteria-inspired communication mechanism based on software-defined network," in 2018 27th Wireless and Optical Communication Conference (WOCC), 2018: IEEE, pp. 1-3.
[23] D. Khalili and B. Barekatain, "GAJEL-DSDN: an intelligent hybrid genetic-Jaya-based switch migration algorithm for efficient load balancing in distributed SDNs," The Journal of Supercomputing, vol. 78, no. 16, pp. 18091-18129, 2022.
[24] J. Xie et al., "A survey of machine learning techniques applied to software defined networking (SDN): Research issues and challenges," IEEE Communications Surveys & Tutorials, vol. 21, no. 1, pp. 393-430, 2018.
[25] A. M. Ruelas and C. E. Rothenberg, "A load balancing method based on artificial neural networks for knowledge-defined data center networking," in Proceedings of the 10th Latin America Networking Conference, 2018, pp. 106-109.
[26] S. Patil, "Load balancing approach for finding best path in SDN," in 2018 International conference on inventive research in computing applications (ICIRCA), 2018: IEEE, pp. 612-616.
[27] C.-T. Yang, S.-T. Chen, J.-C. Liu, Y.-W. Su, D. Puthal, and R. Ranjan, "A predictive load balancing technique for software defined networked cloud services," Computing, vol. 101, pp. 211-235, 2019.
[28] C. Yu, Z. Zhao, Y. Zhou, and H. Zhang, "Intelligent optimizing scheme for load balancing in software defined networks," in 2017 IEEE 85th Vehicular Technology Conference (VTC Spring), 2017: IEEE, pp. 1-5.
[29] R. K. Das, F. H. Pohrmen, A. K. Maji, and G. Saha, "FT-SDN: a fault-tolerant distributed architecture for software defined network," Wireless personal communications, vol. 114, pp. 1045-1066, 2020.
[30] H. Babbar and S. Rani, "Software-defined networking based on load balancing using mininet," in Proceedings of the Second International Conference on Information Management and Machine Intelligence: ICIMMI 2020, 2021: Springer, pp. 69-76.
[31] V. D. Chakravarthy and B. Amutha, "A novel software‐defined networking approach for load balancing in data center networks," International journal of communication systems, vol. 35, no. 2, p. e4213, 2022.