The Near-Real-Time (Near-RT) Radio Access Network (RAN) Intelligent Controller (RIC) in the Open RAN (O-RAN) architecture provides flexibility and programmability, enabling dynamic network management through Machine Learning based applications known as xApps. However, scalability and strict latency requirements hinder the support of numerous xApps. Existing orchestration solutions struggle to efficiently manage large-scale xApp deployments while maintaining latency below one second. Connecting multiple next-generation NodeBs (gNBs) to a single Near-RT RIC risks performance bottlenecks and single points of failure in the O-RAN architecture. To address these challenges, we propose FlexScale, a scalable approach to enhance O-RAN system capacity for extensive xApp deployments. It dynamically scales Near-RT RIC instances connected to gNB modules (E2 Nodes) using Kubernetes-based Horizontal and Vertical Pod Autoscaling (HPA, VPA) and native load balancing. FlexScale optimizes CPU utilization while meeting latency requirements. Simulations show that FlexScale efficiently scales xApps across multiple Near-RT RIC pods, addressing system limitations. Under high E2AP traffic, HPA and VPA autoscaling reduce latency by up to 96% compared to a single Near-RT RIC deployment. Additionally, CPU usage is reduced by approximately 70%, ensuring balanced resource utilization during traffic fluctuations. FlexScale demonstrates its capability to support large-scale xApp deployments while maintaining performance and efficiency.

Abstract The issue of skin cancer has garnered significant attention from the scientific community worldwide, with melanoma being the most lethal and uncommon form of the disease. Melanoma occurs due to the uncontrolled growth of melanocyte cells, which are responsible for imparting color to the skin. If left untreated, melanoma can spread throughout the body and cause death. Early detection of melanoma can lower its mortality rate. In this study, we propose a robust Convolutional Neural Network (CNN)-based method for classifying melanoma images as healthy or non-healthy. To train and test the model, we utilized public datasets from International Skin Imaging Collaboration (ISIC). Additionally, we compared our method with other classification techniques, including Support Vector Machine (SVM), Decision Tree, and K-Nearest Neighbors (K-NN), using the Harris Hawks Optimization algorithm. The results of our method showed superior performance compared to the other approaches.

Abstract The Internet of Things (IoT) has seen significant growth in recent years, impacting various sectors such as smart cities, healthcare, and transportation. However, IoT networks face significant security challenges, particularly from botnets that perform DDoS attacks. Traditional centralized intrusion detection systems struggle with the large traffic volumes in IoT environments. This study proposes a decentralized approach using a fog computing layer with a reptile group intelligence algorithm to reduce network traffic size, followed by analysis in the cloud layer using Apache Spark architecture. Key network traffic features are selected using a chameleon optimization algorithm and a principal component reduction method. Multi-layer artificial neural networks are employed for traffic analysis in the fog layer. Experiments on the NSL-KDD dataset indicate that the proposed method achieves up to 99.65% accuracy in intrusion detection. Additionally, the model outperforms other deep and combined learning methods, such as Bi-LSTM, CNN-BiLSTM, SVM-RBF, and SAE-SVM-RBF, in attack detection. Implementation of decision tree, random forest, and support vector machine algorithms in the cloud layer also demonstrates high accuracy rates of 96.27%, 98.34%, and 96.12%, respectively.