A Machine Learning-based SDN Controller Framework for Drone Management

Toward Efficient Protecting Cyber-Physical Systems with Cyber Threat Hunting and Intelligence

“…APTs are highly sophisticated and well-resourced adversaries that target specific information in high-profile organizations and governments, using a variety of methods and tools such as zero-day vulnerabilities, new malware, and social engineering techniques. Tracing the evolving threat landscape and monitoring it closely is crucial in defending against such threats [18,19].…”

A Stochastic Computational Graph with Ensemble Learning Model for Solving Controller Placement Problem in Software-Defined Wide Area Networks

“…These approaches exhibit potential for addressing the CPP, considering real-time network conditions. Yazdinejad et al (2021) propose an SDN controller architecture for drone management, utilizing machine learning techniques. While not explicitly related to CPP, it showcases the integration of SDN and machine learning for optimized network performance.…”

Privacy-Preserving Cloud Computing: Ecosystem, Life Cycle, Layered Architecture and Future Roadmap

“…As opposed to [320] that Neural Ordinary Differential Equations (NODEs) with Recurrent Neural Networks (RNNs) has been studied in order to assimilate image observations that are to say, with this method classifying missing data in cloud cover is possible. In [321] similarly, a new model was presented for detecting cloud, the method has been developed in Deep Neural Network (DNN) [322] technique with the cross-track infrared sounder, and authors have used the cloud information measured from the image to train their model. Moreover, a number of methods in the neural network, which can be in time-series dataset of cloud server power modeling, have been analyzed in [323], also, the authors have studied the advantages and drawbacks of models and their effects.…”