Mohammed Mubark Salih

Background: Software-Defined Networking (SDN) is widely considered a new paradigm shift in today’s telecommunication evolving method of centralized control, program interface, and dynamic resource configuration. Members of such a network can be reached through single-hop or multi-hop communication and is, however, still faced with inexhaustible challenges in scalability, security, energy consumption as well as Quality of Service (QoS). Objective: Specifically, the article will seek to compare both SDN enabled network as well as legacy networks as regards to established parameters like scalability, security, power consumption, traffic control and path finding. The research aims to fill these gaps by employing state-of-art methods and offer useful recommendations of SDN implementation. Methods: Both simulation and analytical modeling were used to evaluate the proposed SDN architectures under different loads. Metrics were assessed with the congestion control based on the neural network, optimization involved the multiple objectives, and security assessment via game theory. Analyses for statistical significance further supported the performance enhancements determined. Results: The results show 44% improved latency, 33% better energy consumption, and better load balancing in SDN-enabled network. Neural network-based mechanisms were able to reroute 95% of the time under low traffic conditions, while distributed controller-based strategy had high scalability and security. Conclusion: This study points to the capacity of SDN to revolutionize the contemporary telecommunication with strong techniques for comprehensive problems. For the future work it is recommended to conduct validations in operational conditions, and include underdevelopment technologies into the system hierarchy to improve its flexibility and operation characteristics.

Background : Security has been a major issue of discussion due to increase in the number and sophistication of Cyber threats in the modern era. Conventional approaches to threat identification might face difficulties in a number of things, namely the relevancy and the ability to process new and constantly evolving threats. Machine learning (ML) and deep learning (DL) based Approaches present AI as a potential solution to the problem of efficient threat detection.   Objective : The article aims to compare the RF, SVM, CNNs, and RNNs models’ performance, computational time, and resilience in identifying potential cyber threats, such as malware, phishing, and DoS attacks.   Methods : The proposed models were trained as well as evaluated on the NSL-KDD and CICIDS 2017 datasets. This was done based on common scheme indicators including accuracy, precision, recollection, F1 measure, detection rate of efficiency, AUC-ROC, False Alarm Rate (FAR), and the stability to adversaries. Rating of computational efficiency was defined by training time and memory consumption.   Results : The findings indicate that the CNNs gave the best accuracy (96%) and resisted perturbation better, and the RF showed good performance with little computational load. RNNs have been proved effective in sequential data analysis and SVM also performed fairly well on binary data classification although there is a problem of scalability.   Conclusion : CNNs used in AI models are the best solutions to protection from the threats in the cybersecurity space. Nevertheless, some of them still require computational optimization in order to make those beneficial in scenarios with a limited usage of computational resources. It is suggested that these findings can be used in the context of subsequent research and practical applications.