As urban centers evolve into smart cities, sustainable mobility emerges as a cornerstone for ensuring environmental integrity and enhancing quality of life. Autonomous vehicles (AVs) play a pivotal role in this transformation, with the potential to significantly improve efficiency and safety, and reduce environmental impacts. This study introduces a novel Multi-Agent Actor–Critic (MA2C) algorithm tailored for multi-AV lane-changing in mixed-traffic scenarios, a critical component of intelligent transportation systems in smart cities. By incorporating a local reward system that values efficiency, safety, and passenger comfort, and a parameter-sharing scheme that encourages inter-agent collaboration, our MA2C algorithm presents a comprehensive approach to urban traffic management. The MA2C algorithm leverages reinforcement learning to optimize lane-changing decisions, ensuring optimal traffic flow and enhancing both environmental sustainability and urban living standards. The actor–critic architecture is refined to minimize variances in urban traffic conditions, enhancing predictability and safety. The study extends to simulating realistic human-driven vehicle (HDV) behavior using the Intelligent Driver Model (IDM) and the model of Minimizing Overall Braking Induced by Lane changes (MOBIL), contributing to more accurate and effective traffic management strategies. Empirical results indicate that the MA2C algorithm outperforms existing state-of-the-art models in managing lane changes, passenger comfort, and inter-vehicle cooperation, essential for the dynamic environment of smart cities. The success of the MA2C algorithm in facilitating seamless interaction between AVs and HDVs holds promise for more fluid urban traffic conditions, reduced congestion, and lower emissions. This research contributes to the growing body of knowledge on autonomous driving within the framework of sustainable smart cities, focusing on the integration of AVs into the urban fabric. It underscores the potential of machine learning and artificial intelligence in developing transportation systems that are not only efficient and safe but also sustainable, supporting the broader goals of creating resilient, adaptive, and environmentally friendly urban spaces.

Software-Defined Networking (SDN) is a new type of technology that embraces high flexibility and adaptability. The applications in SDN have the ability to manage and control networks while ensuring load balancing, access control, and routing. These are considered the most significant benefits of SDN. However, SDN can be influenced by several types of conflicting flows which may lead to deterioration in network performance in terms of efficiency and optimisation. Besides, SDN conflicts occur due to the impact and adjustment of certain features such as priority and action. Moreover, applying machine learning algorithms in the identification and classification of conflicting flows has limitations. As a result, this paper presents several machine learning algorithms that include Decision Tree (DT), Support Vector Machine (SVM), Extremely Fast Decision Tree (EFDT) and Hybrid (DT-SVM) for detecting and classifying conflicting flows in SDNs. The EFDT and hybrid DT-SVM algorithms were designed and deployed based on DT and SVM algorithms to achieve improved performance. Using a range flows from 1000 to 100000 with an increment of 10000 flows per step in two network topologies namely, Fat Tree and Simple Tree Topologies, that were created using the Mininet simulator and connected to the Ryu controller, the performance of the proposed algorithms was evaluated for efficiency and effectiveness across a variety of evaluation metrics. The experimental results of the detection of conflict flows show that the DT and SVM algorithms achieve accuracies of 99.27% and 98.53% respectively while the EFDT and hybrid DT-SVM algorithms achieve respective accuracies of 99.49% and 99.27%. In addition, the proposed EFDT algorithm achieves 95.73% accuracy on the task of classification between conflict flow types. The proposed EFDT and hybrid DT-SVM algorithms show a high capability of SDN applications to offer fast detection and classification of conflict flows.

Software defined network (SDN) is a network architecture in which the network traffic may be operated and managed dynamically according to user requirements and demands. Issue of security is one of the big challenges of SDN because different attacks may affect performance and these attacks can be classified into different types. One of the famous attacks is distributed denial of service (DDoS). SDN is a new networking approach that is introduced with the goal to simplify the network management by separating the data and control planes. However, the separation leads to the emergence of new types of distributed denial-of-service (DDOS) attacks on SDN networks. The centralized role of the controller in SDN makes it a perfect target for the attackers. Such attacks can easily bring down the entire network by bringing down the controller. This research explains DDoS attacks and the anomaly detection as one of the famous detection techniques for intelligent networks.

IEEE 802.11 Wi-Fi networks are prone to many denial of service (DoS) attacks due to vulnerabilities at the media access control (MAC) layer of the 802.11 protocol. Due to the data transmission nature of the wireless local area network (WLAN) through radio waves, its communication is exposed to the possibility of being attacked by illegitimate users. Moreover, the security design of the wireless structure is vulnerable to versatile attacks. For example, the attacker can imitate genuine features, rendering classification-based methods inaccurate in differentiating between real and false messages. Although many security standards have been proposed over the last decades to overcome many wireless network attacks, effectively detecting such attacks is crucial in today’s real-world applications. This paper presents a novel resource exhaustion attack detection scheme (READS) to detect resource exhaustion attacks effectively. The proposed scheme can differentiate between the genuine and fake management frames in the early stages of the attack such that access points can effectively mitigate the consequences of the attack. The scheme is built through learning from clustered samples using artificial neural networks to identify the genuine and rogue resource exhaustion management frames effectively and efficiently in the WLAN. The proposed scheme consists of four modules which make it capable to alleviates the attack impact more effectively than the related work. The experimental results show the effectiveness of the proposed technique by gaining an 89.11% improvement compared to the existing works in terms of detection.

Recently, there has been an increasing need for new applications and services such as big data, blockchains, vehicle-to-everything (V2X), the Internet of things, 5G, and beyond. Therefore, to maintain quality of service (QoS), accurate network resource planning and forecasting are essential steps for resource allocation. This study proposes a reliable hybrid dynamic bandwidth slice forecasting framework that combines the long short-term memory (LSTM) neural network and local smoothing methods to improve the network forecasting model. Moreover, the proposed framework can dynamically react to all the changes occurring in the data series. Backbone traffic was used to validate the proposed method. As a result, the forecasting accuracy improved significantly with the proposed framework and with minimal data loss from the smoothing process. The results showed that the hybrid moving average LSTM (MLSTM) achieved the most remarkable improvement in the training and testing forecasts, with 28% and 24% for long-term evolution (LTE) time series and with 35% and 32% for the multiprotocol label switching (MPLS) time series, respectively, while robust locally weighted scatter plot smoothing and LSTM (RLWLSTM) achieved the most significant improvement for upstream traffic with 45%; moreover, the dynamic learning framework achieved improvement percentages that can reach up to 100%.

The Mobile Ad-Hoc Network (MANET) has received significant interest from researchers for several applications. In spite of developing and proposing numerous routing protocols for MANET, there are still routing protocols that are too inefficient in terms of sending data and energy consumption, which limits the lifetime of the network for forest fire monitoring. Therefore, this paper presents the development of a Location Aided Routing (LAR) protocol in forest fire detection. The new routing protocol is named the LAR-Based Reliable Routing Protocol (LARRR), which is used to detect a forest fire based on three criteria: the route length between nodes, the temperature sensing, and the number of packets within node buffers (i.e., route busyness). The performance of the LARRR protocol is evaluated by using widely known evaluation measurements, which are the Packet Delivery Ratio (PDR), Energy Consumption (EC), End-to-End Delay (E2E Delay), and Routing Overhead (RO). The simulation results show that the proposed LARRR protocol achieves 70% PDR, 403 joules of EC, 2.733 s of E2E delay, and 43.04 RO. In addition, the performance of the proposed LARRR protocol outperforms its competitors and is able to detect forest fires efficiently.