Nowadays, 5G network is considered to be one of the main pillars of various industries, including the Internet of Things (IoT), smart cities, virtual reality, and many more. Unlike previous network generations, 5G utilizes complex digital technologies such as massive Multiple Input Multiple Output (mMIMO) and runs over higher radio frequencies. The introduction of new technologies and advanced features in the 5G network raises new challenges for network operators, and merging Artificial Intelligence (AI) is one of the effective solutions to address these complexities. However, AI-enabled 5G network engenders security concerns and requires improvement to meet the standardization and qualification of the new network generation. To mitigate these dilemmas, Blockchain must be integrated. Blockchain, as a decentralized methodology provides a secure sharing of information and resources among various nodes of 5G environments. Blockchain can support other technologies, such as AI-based 5G, to create smarter, more efficient, and secure cellular networks. In this paper, we present a comprehensive intelligence and secure data analytics framework for 5G networks based on the convergence of Blockchain and AI named “Block5GIntell”. We depict the applications of Blockchain and AI on 5G networks separately and we argue on the support that Blockchain can provide for AI to create smart and secure 5G networks relying on our proposed framework. To support our proposition, we present an energy-saving case study using Blockchain for AI-enabled 5G. The simulation shows an overall 20% decrease in energy consumption at the RAN level.

Nowadays, 5G network infrastructures are being developed for various industrial IoT (Internet of Things) applications worldwide, emerging with the IoT. As such, it is possible to deploy power-optimized technology in a way that promotes the long-term sustainability of networks. Network slicing is a fundamental technology that is implemented to handle load balancing issues within a multi-tenant network system. Separate network slices are formed to process applications having different requirements, such as low latency, high reliability, and high spectral efficiency. Modern IoT applications have dynamic needs, and various systems prioritize assorted types of network resources accordingly. In this paper, we present a new framework for the optimum performance of device applications with optimized network slice resources. Specifically, we propose a Machine Learning-based Network Sub-slicing Framework in a Sustainable 5G Environment in order to optimize network load balancing problems, where each logical slice is divided into a virtualized sub-slice of resources. Each sub-slice provides the application system with different prioritized resources as necessary. One sub-slice focuses on spectral efficiency, whereas the other focuses on providing low latency with reduced power consumption. We identify different connected device application requirements through feature selection using the Support Vector Machine (SVM) algorithm. The K-means algorithm is used to create clusters of sub-slices for the similar grouping of types of application services such as application-based, platform-based, and infrastructure-based services. Latency, load balancing, heterogeneity, and power efficiency are the four primary key considerations for the proposed framework. We evaluate and present a comparative analysis of the proposed framework, which outperforms existing studies based on experimental evaluation.

Understanding complex traffic patterns has become more challenging in the context of rapidly growing city road networks, especially with the rise of Internet of Vehicles (IoV) systems that add further dynamics to traffic flow management. This involves understanding spatial relationships and nonlinear temporal associations. Accurately predicting traffic in these scenarios, particularly for long‐term sequences, is challenging due to the complexity of the data involved in smart city contexts. Traditional ways of predicting traffic flow use a single fixed graph structure based on the location. This structure does not consider possible correlations and cannot fully capture long‐term temporal relationships among traffic flow data, making predictions less accurate. We propose a novel traffic prediction framework called Multi‐scale Attention‐Based Spatio‐Temporal Graph Convolution Recurrent Network (MASTGCNet) to address this challenge. MASTGCNet records changing features of space and time by combining gated recurrent units (GRUs) and graph convolution networks (GCNs). Its design incorporates multiscale feature extraction and dual attention mechanisms, effectively capturing informative patterns at different levels of detail. Furthermore, MASTGCNet employs a resource allocation strategy within edge computing to reduce energy usage during prediction. The attention mechanism helps quickly decide which services are most important. Using this information, smart cities can assign tasks and allocate resources based on priority to ensure high‐quality service. We have tested this method on two different real‐world datasets and found that MASTGCNet predicts significantly better than other methods. This shows that MASTGCNet is a step forward in traffic prediction.

Effective load balancing is critical in contemporary mobile computing environments to ensure optimal resource utilization and adherence to strict deadlines. This study presents a novel framework for deadline-constrained load balancing, termed DCLD-net, which leverages the integration of Graph Convolutional Networks (GCN) and an attention-based Bidirectional Gated Recurrent Unit (BiGRU). The proposed framework utilizes the spatial modeling capabilities of GCNs to capture intricate network topologies, while the temporal dynamics and attention mechanisms of BiGRU enable the identification of critical patterns in traffic flow data. By incorporating key factors such as sticky sessions, load distribution, content-based factors such as videos or file downloads, instance health checks, and other relevant parameters, the DCLD-net model achieves high accuracy in predicting task schedules. These schedules allocate tasks to virtual machines (VMs), enabling dynamic traffic routing through a load balancer that efficiently assigns tasks. Extensive experimental evaluations demonstrate that the proposed attention-based BiGRU-GCN model significantly outperforms traditional methods in both deadline compliance and load balancing efficiency, offering a robust solution to the challenges of modern cloud computing. Experimental results demonstrate that DCLD-net outperforms traditional methods by 27% in deadline compliance and 29.3% in load balancing efficiency.

Nowadays, the designing of cyber-physical systems has a significant role and plays a substantial part in developing a sustainable computing ecosystem for secure and scalable network architecture. The introduction of Cyber Threat Intelligence (CTI) has emerged as a new security system to mitigate existing cyber terrorism for advanced applications. CTI demands a lot of requirements at every step. In particular, data collection is a critical source of information for analysis and sharing; it is highly dependent on the reliability of the data. Although many feeds provide information on threats recently, it is essential to collect reliable data, as the data may be of unknown origin and provide information on unverified threats. Additionally, effective resource management needs to be put in place due to the large volume and diversity of the data. In this paper, we propose a blockchain-based cyber threat intelligence system architecture for sustainable computing in order to address issues such as reliability, privacy, scalability, and sustainability. The proposed system model can cooperate with multiple feeds that collect CTI data, create a reliable dataset, reduce network load, and measure organizations’ contributions to motivate participation. To assess the proposed model’s effectiveness, we perform the experimental analysis, taking into account various measures, including reliability, privacy, scalability, and sustainability. Experimental results of evaluation using the IP of 10 open source intelligence (OSINT) CTI feeds show that the proposed model saves about 15% of storage space compared to total network resources in a limited test environment.