{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T02:54:17Z","timestamp":1784948057156,"version":"3.55.0"},"reference-count":36,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Network"],"abstract":"<jats:p>Modern Software-Defined Wide Area Networks (SD-WANs) require adaptive controller placement addressing multi-objective optimization where latency minimization, load balancing, and fault tolerance must be simultaneously optimized. Traditional static approaches fail under dynamic network conditions with evolving traffic patterns and topology changes. This paper presents a novel hybrid framework integrating Gaussian Mixture Model (GMM) clustering with Multi-Agent Reinforcement Learning (MARL) for dynamic controller placement. The approach leverages probabilistic clustering for intelligent MARL initialization, reducing exploration requirements. Centralized Training with Decentralized Execution (CTDE) enables distributed optimization through cooperative agents. Experimental evaluation using real-world topologies demonstrates a noticeable reduction in the latency, improvement in network balance, and significant computational efficiency versus existing methods. Dynamic adaptation experiments confirm superior scalability during network changes. The hybrid architecture achieves linear scalability through problem decomposition while maintaining real-time responsiveness, establishing practical viability.<\/jats:p>","DOI":"10.3390\/network5040052","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T10:56:27Z","timestamp":1762858587000},"page":"52","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Dynamic Multi-Objective Controller Placement in SD-WAN: A GMM-MARL Hybrid Framework"],"prefix":"10.3390","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5605-1390","authenticated-orcid":false,"given":"Abdulrahman M.","family":"Abdulghani","sequence":"first","affiliation":[{"name":"Department of Communication Technology and Network, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia (UPM), Serdang 43400, Selangor, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8321-9259","authenticated-orcid":false,"given":"Azizol","family":"Abdullah","sequence":"additional","affiliation":[{"name":"Department of Communication Technology and Network, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia (UPM), Serdang 43400, Selangor, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. R.","family":"Rahiman","sequence":"additional","affiliation":[{"name":"Department of Communication Technology and Network, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia (UPM), Serdang 43400, Selangor, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nor Asilah Wati","family":"Abdul Hamid","sequence":"additional","affiliation":[{"name":"Department of Communication Technology and Network, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia (UPM), Serdang 43400, Selangor, Malaysia"},{"name":"Institute for Mathematical Research, Universiti Putra Malaysia (UPM), Serdang 43400, Selangor, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0058-052X","authenticated-orcid":false,"given":"Bilal Omar","family":"Akram","sequence":"additional","affiliation":[{"name":"Department of Computer and Communication Systems Engineering, Faculty of Engineering, Universiti Putra Malaysia (UPM), Serdang 43400, Selangor, Malaysia"},{"name":"Wireless and Photonics Networks Research Centre of Excellence (WiPNET), Faculty of Engineering, Universiti Putra Malaysia (UPM), Serdang 43400, Selangor, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"123","DOI":"10.32604\/csse.2024.058314","article-title":"Navigating the Complexities of Controller Placement in SD-WANs: A Multi-Objective Perspective on Current Trends and Future Challenges","volume":"49","author":"Abdulghani","year":"2025","journal-title":"Comput. Syst. Sci. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/s44443-025-00133-z","article-title":"Graph-based reinforcement learning for software-defined networking traffic engineering","volume":"37","author":"Lu","year":"2025","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cunha, J., Ferreira, P., Castro, E.M., Oliveira, P.C., Nicolau, M.J., N\u00fa\u00f1ez, I., Sousa, X.R., and Ser\u00f4dio, C. (2024). Enhancing Network Slicing Security: Machine Learning, Software-Defined Networking, and Network Functions Virtualization-Driven Strategies. Future Internet, 16.","DOI":"10.3390\/fi16070226"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"523","DOI":"10.3390\/network4040026","article-title":"Traffic-Driven Controller-Load-Balancing over Multi-Controller Software-Defined Networking Environment","volume":"4","author":"Sapkota","year":"2024","journal-title":"Network"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1109\/TNSM.2017.2785660","article-title":"An Effective Approach to Controller Placement in Software Defined Wide Area Networks","volume":"15","author":"Wang","year":"2018","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.23919\/transcom.2024EBP3197","article-title":"FPGA-accelerated VXLAN chaining for partially reconfigurable VNFs in heterogeneous data centers","volume":"108","author":"Chang","year":"2025","journal-title":"IEICE Trans. Commun."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Abdulghani, A.M., Abdullah, A., Rahiman, A.R., Hamid, N.A., and Akram, B.O. (2025). Enhancing Healthcare Network Effectiveness Through SD-WAN Innovations. Tech Fusion in Business and Society, Springer.","DOI":"10.1007\/978-3-031-84628-1_10"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Abdulghani, A.M., Abdullah, A., Rahiman, A.R., Abdul Hamid, N.A.W., and Akram, B.O. (2025). Network-Aware Gaussian Mixture Models for Multi-Objective SD-WAN Controller Placement. Electronics, 14.","DOI":"10.3390\/electronics14153044"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2350143","DOI":"10.1142\/S021812662350144X","article-title":"GOKA: A network partition and cluster fusion algorithm for controller placement problem in SDN","volume":"32","author":"Xiao","year":"2023","journal-title":"J. Circuits Syst. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhang, C., Wu, Y., Liu, L., and Long, J. (2025). Adaptive Real-Time Transmission in Large-Scale Satellite Networks Through Software-Defined-Networking-Based Domain Clustering and Random Linear Network Coding. Mathematics, 13.","DOI":"10.3390\/math13071069"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/MCOM.001.1900063","article-title":"Toward Disaggregating the SDN Control Plane","volume":"57","author":"Comer","year":"2019","journal-title":"IEEE Commun. Mag."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"11729","DOI":"10.1007\/s12652-022-03733-z","article-title":"Evaluating heuristic techniques as a solution of controller placement problem in SDN","volume":"14","author":"Singh","year":"2023","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.aej.2023.12.018","article-title":"A novel framework for capacitated SDN controller placement: Balancing Latency and reliability with PSO algorithm","volume":"87","author":"Singh","year":"2024","journal-title":"Alex. Eng. J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"103869","DOI":"10.1016\/j.jnca.2024.103869","article-title":"A stochastic computational graph with ensemble learning model for solving controller placement problem in software-defined wide area networks","volume":"225","author":"Adekoya","year":"2024","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.jnca.2016.12.019","article-title":"Quality of service (QoS) in software defined networking (SDN): A survey","volume":"80","author":"Karakus","year":"2022","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhou, S., Wei, Y., and Leng, S. (2020, January 6\u20139). Deep Reinforcement Learning for Controller Placement in Software Defined Network. Proceedings of the IEEE INFOCOM 2020\u2013IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), Toronto, ON, Canada.","DOI":"10.1109\/INFOCOMWKSHPS50562.2020.9162977"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"104253","DOI":"10.1016\/j.jnca.2025.104253","article-title":"MOOO-RDQN: A deep reinforcement learning based method for multi-objective optimization of controller placement and traffic monitoring in SDN","volume":"242","author":"Chen","year":"2025","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104948","DOI":"10.1016\/j.jpdc.2024.104948","article-title":"Deep reinforcement learning based controller placement and optimal edge selection in SDN-based multi-access edge computing environments","volume":"193","author":"Li","year":"2024","journal-title":"J. Parallel Distrib. Comput."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1109\/TNSM.2020.3047765","article-title":"Dynamic Controller Assignment in Software Defined Internet of Vehicles Through Multi-Agent Deep Reinforcement Learning","volume":"18","author":"Yuan","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103855","DOI":"10.1016\/j.jnca.2024.103855","article-title":"ELA-RCP: An energy-efficient and load balanced algorithm for reliable controller placement in software-defined networks","volume":"225","author":"Bagha","year":"2024","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"110600","DOI":"10.1016\/j.comnet.2024.110600","article-title":"An improved artificial bee colony algorithm to minimum propagation latency and balanced load for controller placement in software defined network","volume":"250","author":"Ma","year":"2024","journal-title":"Comput. Netw."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e2220","DOI":"10.1002\/nem.2220","article-title":"On minimizing flow monitoring costs in large-scale software-defined network networks","volume":"33","author":"Yahyaoui","year":"2023","journal-title":"Int. J. Netw. Manag."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1109\/TNSE.2021.3068975","article-title":"Near-optimal robust virtual controller placement in 5G software defined networks","volume":"8","author":"Tohidi","year":"2021","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"101842","DOI":"10.1016\/j.jksuci.2023.101842","article-title":"Autonomous solution for controller placement problem of software-defined networking using MuZero based intelligent agents","volume":"35","author":"Benoudifa","year":"2023","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_25","first-page":"288","article-title":"Research on multi-controller deployment strategy based on latency and load in software defined network","volume":"44","author":"Huang","year":"2022","journal-title":"J. Electron. Inf. Technol."},{"key":"ref_26","first-page":"902","article-title":"A novel method to find the best path in SDN using firefly algorithm","volume":"31","author":"Obaida","year":"2022","journal-title":"J. Intell. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"159987","DOI":"10.1109\/ACCESS.2021.3130066","article-title":"A Novel Approach for Gaussian Mixture Model Clustering Based on Soft Computing Method","volume":"9","author":"Gogebakan","year":"2021","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"525","DOI":"10.32604\/sdhm.2024.050088","article-title":"Mitigating Urban Heat Island Effects: A Review of Innovative Pavement Technologies and Integrated Solutions","volume":"18","author":"Ismael","year":"2024","journal-title":"Struct. Durab. Health Monit."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Abdulghani, A.M., Abdulghani, M.M., Walters, W.L., and Abed, K.H. (2022, January 14\u201316). Cyber-physical system based data mining and processing toward Autonomous Agricultural Systems. Proceedings of the 2022 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA.","DOI":"10.1109\/CSCI58124.2022.00131"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"108852","DOI":"10.1016\/j.comnet.2022.108852","article-title":"Dynamic clustering of software defined network switches and controller placement using deep reinforcement learning","volume":"207","author":"Bouzidi","year":"2022","journal-title":"Comput. Netw."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1016\/0305-0548(94)00059-H","article-title":"Determining objective weights in multiple criteria problems: The CRITIC method","volume":"22","author":"Diakoulaki","year":"1995","journal-title":"Comput. Oper. Res."},{"key":"ref_32","unstructured":"Amato, C. (2024). An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning. arXiv, Available online: https:\/\/arxiv.org\/abs\/2409.03052."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1109\/JSAC.2011.111002","article-title":"The internet topology zoo","volume":"29","author":"Knight","year":"2011","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"78379","DOI":"10.1109\/ACCESS.2024.3408923","article-title":"Enhancing reliability of time-triggered traffic in joint scheduling and routing optimization within time-sensitive networks","volume":"12","author":"Akram","year":"2024","journal-title":"IEEE Access"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"142764","DOI":"10.1109\/ACCESS.2023.3343409","article-title":"Joint scheduling and routing optimization for deterministic hybrid traffic in time-sensitive networks using constraint programming","volume":"11","author":"Akram","year":"2023","journal-title":"IEEE Access"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"3715086","DOI":"10.1155\/int\/3715086","article-title":"A Resilience Recovery Method for Complex Traffic Network Security Based on Trend Forecasting","volume":"2025","author":"Hong","year":"2025","journal-title":"Int. J. Intell. Syst."}],"container-title":["Network"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2673-8732\/5\/4\/52\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T11:36:18Z","timestamp":1762947378000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2673-8732\/5\/4\/52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":36,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["network5040052"],"URL":"https:\/\/doi.org\/10.3390\/network5040052","relation":{},"ISSN":["2673-8732"],"issn-type":[{"value":"2673-8732","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]}}}