Skip to content
Log in

Similar papers

Conference Jul 2026

Toward Intelligent Routing in Sdn: a Comparative Review of Bio-Inspired Optimization Techniques

Bio-inspired routing algorithms have gained significant attention as effective approaches for solving complex optimization problems in modern communication networks. Drawing inspiration from collective behaviors in nature, these methods have been widely applied in decentralized environments such as wireless sensor and mobile ad hoc networks. However, their adoption within Software-Defined Networks (SDN) remains relatively limited. This paper provides a systematic and comparative review of bio-inspired routing algorithms with an emphasis on their applicability in SDN. A novel taxonomy is proposed to classify these algorithms according to their behavioral characteristics and their suitability for centralized control. In addition, a unified evaluation framework is introduced to enable consistent comparison among key approaches, including Ant Colony Optimization, Particle Swarm Optimization, Bee Colony Optimization, and Grey Wolf Optimization, based on performance criteria such as convergence, scalability, and quality of service. The study also includes an SDN-oriented analysis, examining the impact of centralized control on the behavior and performance of these algorithms. Finally, the paper outlines key research challenges, highlighting the importance of real-time optimization, hybrid methodologies, and integration with intelligent control mechanisms.

Spasimir Varshilov, K. Nikolova · 0 citations
Open access Jul 2026

Optimization of Resource Allocation in 5G MIMO Networks Using Linear Assignment Algorithms

Massive Multiple Input Multiple Output (MIMO) is an essential technology that can significantly improve the performance of 5G wireless networks by using multiple antennas in base stations, improving coverage, reducing interference, and increasing data throughput. In this comprehensive study, we propose and analyze advanced optimization techniques for resource allocation in 5G MIMO networks, focusing on three distinct approaches: simple sorting, Hungarian Algorithm, and Minimum Cost Flow Algorithm. Simulations are performed using the publicly available DeepMIMO dataset, where we evaluate each method under both static and dynamic scenarios, aiming to optimize bandwidth distribution and minimize power consumption. A key contribution of this work is the formulation and comparative evaluation of the resource allocation problem as an assignment-based model, allowing the examined methods to be compared under common DeepMIMO-based static and dynamic scenarios. The technical contribution of this work lies in the common assignment-based formulation and comparative evaluation of simple sorting, Hungarian, and Minimum Cost Flow allocation methods under the same DeepMIMO-based static and dynamic 5G MIMO scenarios. Our comparative analysis shows that, under the evaluated DeepMIMO-based scenarios, the examined assignment-based methods exhibit different trade-offs in throughput, energy-consumption-related performance, bandwidth utilization, and adaptability to varying user demands, offering useful insights for 5G MIMO resource allocation studies.

Nikolaos Prodromos, Damianos Diasakos, V. Kokkinos et al. · 0 citations
Aug 2026

Optimized task offloading and resource allocation framework for edge-assisted IoT applications

This work aims to design an efficient framework by incorporating a novel hybrid metaheuristic algorithm that combines Draco Lizard Optimization (DLO) and Sand Cat Optimization (SCO) for optimal task offloading and resource allocation for IoT applications.

Mukesh Kumar Jha, Mohit Kumar · 0 citations
Open access Aug 2026

An Improved Coati Optimization Algorithm with Urban-Traffic-Inspired Strategies for Global Optimization and Low-Carbon Microgrid Scheduling

The economic scheduling of grid-connected microgrids requires the coordinated dispatch of renewable energy sources, controllable distributed generators, battery energy storage systems, and power exchange with the utility grid while satisfying various operational constraints. Owing to the time-varying nature of renewable generation and load demand, this problem often exhibits strong nonlinearity, temporal coupling, and complex constraint characteristics. To enhance the optimization capability of the original Coati Optimization Algorithm (COA) for such constrained scheduling tasks, this paper proposes an Improved Coati Optimization Algorithm, termed ICOA. Different from the original COA, which mainly depends on random initialization, single-best individual guidance, and simple local perturbation, the proposed ICOA redesigns the search process through several urban-traffic-inspired mechanisms. First, a road-network stratified initialization strategy is employed to improve the spatial coverage and diversity of the initial population. Second, a traffic-signal-guided exploration strategy adaptively adjusts the search direction by considering population congestion and elite information. Third, a lane-changing local exploitation operator is introduced to refine promising solutions with the aid of neighborhood information. Finally, a traffic-rule-based repair mechanism is incorporated to enhance the feasibility of candidate scheduling solutions under operational constraints. The performance of ICOA is first assessed on the CEC2017 benchmark suite with 10-, 30-, 50-, and 100-dimensional test settings. The results obtained from convergence curves, boxplots, Wilcoxon signed-rank tests, and Friedman mean rank tests demonstrate that ICOA achieves competitive performance in terms of convergence accuracy, robustness, and scalability when compared with 11 advanced algorithms. In addition, ICOA is applied to a 24 h grid-connected microgrid economic scheduling case. The simulation results show that ICOA obtains the lowest mean operating cost of 1393.58, which is 13.10% lower than that of the best competing algorithm in terms of mean cost. These results suggest that ICOA is an effective and reliable optimization method for both benchmark function optimization and constrained microgrid scheduling problems.

Wenjie Zhao, Chengpeng Li · 0 citations
Open access Jul 2026

An Intelligent Grey Wolf Optimization Framework for Parameter Adaptation in EAOMDV Routing Protocol

In this paper, a parameter adaption method is suggested for MANET routing efficiency enhancement. It combines the EAOMDV protocol with intelligent Grey Wolf Optimization (GWO). Improving the network's routing patterns through the use of several quality-of-service (QoS) indicators is the main goal. Some of these metrics are the rate of packet delivery (PDR), residual energy, end-to-end delay, and routing overhead. By merging normalized performance measures into a single fitness function, the suggested strategy reframes a weighted single-objective problem as route optimization. In order to automatically optimize routing parameters and choose ideal routes, the suggested system uses GWO, which is modeled after the pack structure and hunting methods used by grey wolves. Better fault tolerance and route stability are achieved by the use of EAOMDV, which guarantees the preservation of multiple loop-free pathways. To avoid optimizing faulty or redundant paths, a method called discrete path validation is used. Many simulations have been run with different node densities and mobility parameters. The proposed GWO-EAOMDV framework outperforms both traditional EAOMDV and alternative optimization-based routing protocols. Reduces end-to-end latency by 15-22% while simultaneously enhancing PDR by 12-18% and improving energy efficiency. The robustness of the proposed model was confirmed by statistical validation employing several simulation runs.

S. Hemasri, R. A · 0 citations