This paper proposes a novel approach for tuning the parameters of 6th generation (6G) extremely large-scale MIMO (Multiple Input Multiple Output) systems using the Firefly optimization algorithm. The main objective is to achieve accurate estimation of the hybrid field in the MIMO system. The proposed method optimizes MIMO system parameters by minimizing the cost function through a hybrid pre-coding and combining technique. This optimization problem is formulated as a nonlinear programming problem and solved using the Firefly algorithm. Experimental results demonstrate that the proposed approach provides accurate hybrid field estimation with improved system performance compared to existing state-of-the-art methods. The Firefly optimization algorithm proves to be an efficient and effective method for tuning 6G MIMO system parameters, with potential applications in future wireless communication systems. In addition to the Firefly optimization algorithm, this paper introduces a complementary machine learning-assisted resource allocation strategy to optimize network resource utilization. By leveraging machine learning algorithms, dynamic resource allocation based on real-time network conditions is ensured, enhancing overall system performance. The integration of the Firefly optimization algorithm for parameter tuning and machine learning-assisted resource allocation aims to achieve holistic optimization in 6G networks. Experimental results demonstrate that this integrated approach not only refines parameter tuning but also dynamically adapts resource allocation, leading to superior system efficiency and throughput compared to conventional methods. This comprehensive strategy addresses the evolving demands of future wireless communication systems. Results showed that using a sparsity value of 8, with 600 beams and 300 pilots, minimizes the mean square error of estimation to less than -13 dB

An intelligent distributed network system is the Wireless Sensor Network (WSN), which is a strategy required to address security threats as well as energy consumption that has a direct impact on a network’s lifetime. Thus, attempting to identify malicious attacks with a low consumption of data transmission makes a lot of sense. The high energy consumption of nodes due to the transmission of data shortens the lifetime of the network. To overcome these issues, the proposed method is based on the Ordering Points to Identify Cluster Structure (OPTICS) with Bi-directional Long Short Term Memory using Differential evolution (DE-BiLSTM) classifier to detect the threats in WSN for smart building. Initial deployment of the sensor nodes (SN) and formation of the cluster nodes (CN) by employing the OPTICS density-based clustering approach that partitions clusters with different densities. In order to transport data to the base station, the cluster head (CH) nodes are chosen from the CN according to their more energy as well as shorter distance. Then, in order to forecast the threats, the size of the batch and hidden layers are set using the differential evolution method (DE) and the classification of the data is performed using BiLSTM to detect as attack or non-attack. Performance for predicting an attack is measured by network and classification parameters such as Packet Delivery Ratio (PDR), Average Residual Energy (ARE), Throughput, Accuracy and Precision. The results of the performance obtained are 91.78% for PDR, 8.56J for ARE, 2.52mbps for throughput with 100 nodes, then 93.78% for accuracy and 93.04% for precision. Thus, the designed detection of threats in WSN based on OPTICS clustering with DE-BILSTM classifier performs better for malicious attack prediction with low energy consumption sensor nodes. 

This paper proposes a study on systems for the detection and prevention of Denial-of-Service attacks (DoS) in Software-Defined Network (SDN) architectures. After a survey of the characteristics of SDN and DoS attacks, we introduce a system based on several components and the sFlow protocol to detect and react to different types of attacks, both from single and distributed sources. The considered attacks include all the main flooding techniques, besides the slowris approach. Finally, an experimental example of an attack on a SDN controller is presented to highlight the interaction between the components and evaluate their timely mitigation effects against the threat.

A Mobile Ad Hoc Network (MANET) consists of numerous wireless mobile devices. It is a self-organizing network and does not require any pre-established infrastructure. Communication between devices sets up without any dedicated centralized server. A malicious node takes advantage of this vulnerability and attempts to integrate into the network in order to lower its overall performance. In MANET, one of the most dangerous types of attacks is the blackhole node assault. In order to join the route, a node with blackhole assault wrongly sends route information to the source node during the route discovery process and degrades the network performance. In order to address this problem, a novel Blackhole Detection Algorithm (BHDA) has been proposed in this work. To determine the existence of blackhole nodes, the protocol takes into account various factors including number of route request packets (RREQ) received, number of RREQ packets forwarded, and number of route reply packets (RREP) transmitted by nodes throughout the route discovery process. Apart from this, each node maintains a local neighbourhood information and for that all neighbourhood node has to pass the check before becoming a neighbour. The simulation results prove that the proposed technique BHDA shows drastic improvement in network performance under blackhole attack.

The utilization of millimeter waves in 5G technology has led to key differences in the capacities and performance of radio communications. Examining the advantages and challenges of this technology and comparing it with an established technology like 4G can provide a deeper understanding of these changes. Overall, this study conducts examinations to provide the characteristics of 5G and 4G technologies. In this study, the performance of 5G was evaluated and compared to 4G, under fair conditions, by analyzing the effect of increasing the distance of antennas, the number of users, and bandwidth on signal power, delay, throughput, channel quality, and modulation metrics. The analysis demonstrates the superiority of 5G in terms of speed and its ability to support more users compared to 4G. The higher data rates and enhanced capacity of 5G are evident in the results. However, it's worth noting that 4G offers a wider coverage area compared to 5G, making it more suitable for certain scenarios where extended coverage is essential. Additionally, it was observed that 5G signals are more susceptible to noise and obstacles compared to 4G, which can impact signal quality and coverage in certain environments. The presented results suggest that using 5G antennas in geographically limited and densely populated areas, such as rural regions, would be more cost-effective compared to using 4G antennas. This is because fewer antennas are required to serve more users without the need for extensive coverage. Additionally, numerous obstacles in urban areas pose challenges to 5G technology, thus requiring a greater number of antennas to achieve satisfactory accessibility.