Enhance Network Performance Research Articles

A Reinforcement Learning Inspired Approach for Efficient Cognitive Radio Network Routing

Introduction: One fundamental characteristic of Cognitive Radio Networks (CRNs) is their dynamic operating environment, where network conditions, such as the activities of Primary Users (PUs), undergo continuous changes over time. While Secondary Users (SUs) are engaged in communication, if a PU reappears on an SU's channel, the SU is required to vacate the channel and switch to another available channel. Thus, finding a stable route that minimizes frequent channel switches is a challenging task in CRNs. Method: Existing solutions to reduce PU interference often overlook the energy consumption of nodes when forming clusters, focusing solely on the minimum number of common channels in a cluster. Consequently, these schemes suffer from frequent channel switches due to PU appearances. The proposed Cognitive Radio Network Routing (CRNR) approach aims to minimize frequent channel switches by employing a Reinforcement Learning (RL) technique called Q-Learning to select stable routes with channels exhibiting higher OFF-state probabilities. Result: This strategy ensures that selected routes avoid rerouting by prioritizing channels with higher off-state probabilities. Experimental studies demonstrate that the CRNR approach enhances network throughput and reduces interference when compared with existing techniques. CRNR introduces a novel application of AI, use of Q-Learning, a reinforcement learning technique in wireless networks. Conclusion: This bridges the gap between machine learning and network design, showcasing how intelligent algorithms can optimize communication decisions in real-time, which could inspire further exploration of AI-driven techniques in network management and beyond. conclusion: The CRNR approach, through the use of Q-Learning and channel selection based on OFF-state probabilities, provides a more stable routing solution in CRNs. It enhances network performance by reducing rerouting and interference while addressing energy consumption concerns during cluster formation.

Two-Stage GPR Image Inversion Method Based on Multi-Scale Dilated Convolution and Hybrid Attention Gate

Ground penetrating radar (GPR) image inversion is of great significance for interpreting GPR data. In practical applications, the complexity and nonuniformity of underground structures bring noise and clutter interference, making GPR inversion problems more challenging. To address these issues, this study proposes a two-stage GPR image inversion network called MHInvNet based on multi-scale dilated convolution (MSDC) and hybrid attention gate (HAG). This method first denoises the B-scan through the first network MHInvNet1, then combines the denoised B-scan from MHInvNet1 with the undenoised B-scan as input to the second network MHInvNet2 for inversion to reconstruct the distribution of the permittivity of underground targets. To further enhance network performance, the MSDC and HAG modules are simultaneously introduced to both networks. Experimental results from simulated and actual measurement data show that MHInvNet can accurately invert the position, shape, size, and permittivity of underground targets. A comparison with existing methods demonstrates the superior inversion performance of MHInvNet.

A Novel 5G Fronthaul Architecture Based on Quantum Security Protection

In the digital age, 5G technology has significantly enhanced global communication capabilities, providing strong support for various industries. However, 5G falls short of achieving comprehensive intelligence within the Internet of Things (IoT), propelling the development of 6G technology. 6G is expected to further enhance network performance by integrating advanced technologies such as AI and quantum communication, while expanding application scenarios to include communication in extreme environments for comprehensive global connectivity. This paper proposes an innovative fronthaul architecture that applies Quantum Key Distribution (QKD) technology to the 5G fronthaul, leveraging its unconditionally secure key generation and distribution mechanism. In this design, costlier Alice devices are placed on the AAU side, while less expensive Bob devices are positioned on the DU side, optimizing deployment to reduce engineering costs and lower deployment barriers. The feasibility of this architecture is demonstrated by calculating the secure key rate. Comparative analysis with existing research is performed to clarify future research directions. These innovations not only enhance 5G network security but also offer new solutions for the security requirements of 6G networks, such as data security, network resilience, and algorithm transparency. Our research offers strategic value for future network security, laying the groundwork for reliable networks.

GTD‐CER: Game‐Theoretic Dynamic Clustering for Enhanced Efficiency and Reliability in Wireless Sensor Networks

ABSTRACTEfficient cluster formation is a significant issue in wireless sensor networks (WSNs) for optimizing energy consumption, enhancing data reliability, and prolonging network lifetime. This paper proposes a dynamic cluster formation scheme modeled as a noncooperative game, where each sensor node acts as a player making strategic decisions on whether to become a cluster head (CH) or remain a member node (MN). In this role selection decision‐making phase, nodes evaluate their potential utility function, which incorporates energy consumption, data reliability, and data forwarding efficiency. Nodes dynamically switch roles based on their utility to achieve an optimal network configuration. Simulations conducted using the NS‐3 network simulator demonstrate that the proposed game theory‐based clustering scheme significantly improves network performance. We analyze key measures like energy consumption, packet delivery ratio (PDR), and data forwarding, and the results shows that the proposed scheme reduces energy consumption by 25%, improves PDR by 15%, and extends the network lifetime by 20%, compared to traditional methods. The dynamic role‐switching mechanism prolongs network lifetime by preventing the rapid depletion of node energy, ensuring stable and efficient network operations. It significantly enhances network performance, stability, and longevity.

High Resolution Medical Image Inpainting Based on Super Resolution

Introduction: Image inpainting techniques and patents have made great progress in recent years. However, with higher image resolution, the large amount of computation and memory requirements cause great difficulties for training. Method: We propose a medical image inpainting model that utilizes super-resolution techniques to enhance the resolution of images during the repair process. Moreover, to maximize the utilization of semantic information and enhance network performance, we incorporate multi-scale dense residual blocks for feature extraction from the image. Results: Meanwhile, we utilize structural similarity as a loss function to encourage the network to synthesize more meaningful structural textures. Experimental results demonstrate that HRMII can effectively reduce the computation and memory occupation of the high-resolution image inpainting model, and obtain satisfactory inpainting results. Conclusion: Additionally, ablation studies have substantiated the efficacy of diverse modules within the network.

Optimizing Cloud Traffic Offloading and Cloudlet Resource Usage in Cloud-Integrated WOBAN (CIW)

Background: Integration of cloud components in a wireless mesh network of Wireless- Optical Broadband Access Network (WOBAN) contributes to enhancing network performance. Aim: This study aims to deploy the minimum cloudlets at the optimum location and to offload excess traffic from overloaded cloudlets to underloaded ones. Objective: The objective of this study is to optimize cloudlet positioning and traffic offloading for cost-effective deployment, better resource utilization, reduced blocking probability, and lower delays. Method: The proposed methodology introduces a Cluster-Based Heuristic Approach (CBHA) for efficient cloudlet placement along with a traffic offloading mechanism using a Customized Donkey- Smuggler Optimization (CDSO) to enhance the overall network performance. Result: Simulations show the effectiveness of the proposed approach for resource utilization, blocking probability, delay, and cost. Conclusion: The problem in position optimization of the cloudlet, along with traffic offloading, is solved using the proposed approaches to get better network performance in a cost-efficient manner.

Enhancing Network Performance in Wireless Sensor and Anonymous Networks

Enhancing Network Performance in Wireless Sensor and Anonymous Networks

Implementation and Performance Analysis of Internet Networks for RT/RW Using MikroTik and OpenWRT in Simalidu Koto Salak Dhamasraya

This research analyzes the implementation and performance of RT/RW Net Internet networks utilizing MikroTik and OpenWrt in Simalidu Koto Salak, Dharmasraya, addressing the significant challenges posed by the region's telecommunications infrastructure. The primary objective is to evaluate critical Quality of Service (QoS) parameters that greatly influence user experience, specifically focusing on bandwidth, throughput, delay, jitter, and packet loss. Employing a systematic methodology, the study begins with site surveys to assess geographical and infrastructural contexts, followed by the deployment of a Point-To-Point network system designed to ensure optimal signal quality and efficient user management through MikroTik devices. Findings reveal that QoS in the RT/RW Net network is considerably affected by both technical configurations and the quality of the signal, culminating in a QoS score of 3.5, which corresponds to a 75% performance rating. These results indicate that, while the implemented network solution meets basic connectivity needs, further optimization is crucial to enhance user satisfaction and overall performance. Consequently, the study offers several recommendations aimed at improving internet service quality in similar environments, highlighting the necessity of continuous evaluation and adaptation of network configurations to meet the evolving demands of users. Furthermore, it suggests that future research could delve into advanced technologies and methodologies to further enhance network performance and user experience, particularly in rural areas, thereby effectively addressing connectivity challenges and ensuring that the benefits of reliable internet access are widely distributed among local communities.

A Survey of Emerging Techniques for Large Networks of Virtual Local Area Networks (VLANs) with Benefits and Limitations

The numerous benefits of wireless communication have led to its meteoric rise in popularity as a network type, yet there have been numerous obstacles to enhancing its performance. An alternative method that allows a network administrator to construct a logical network out of a physical network is VLAN, which stands for Virtual Local Area Network. Thus, VLANs are fundamental technology for enhancing network performance, capacity and security. VLANs are a means of breaking large networks into smaller broadcast domains, managing broadcast traffic, controlling congestion, and providing increased levels of security. This paper explores the emerging techniques in managing and optimising VLANs within large-scale network environments. VLANs are essential for improving network performance, security, and scalability by the logical segmentation of networks into smaller, isolated broadcast domains. This survey also outlines trends in future VLAN technologies such as Software Defined Networking (SDN), VXLAN, and Big Data and Analytics. Also, the paper covers the uses, advantages, and disadvantages of VLANs, including enhanced security, scalability, and economy, though admitting to issues of VLAN configuration difficulty and security threats. In the paper, the authors discussed the future trends including the integration of multi-cloud, network slicing coupled with 5G, and integration of blockchain for VLAN security.

Porosity identification using residual PPTransformer network

Precisely estimating the carbonate’s porosity is essential for subsurface reservoir characterization. However, conventional methods for obtaining porosity using either core measurements or logging interpretation are expensive and inefficient. Considering the sequence data feature of logging curves and the booming development of intelligent networks in geoscience, this study proposes a reliable and low-cost intelligent Porosity Prediction Transformer (PPTransformer) framework for reservoir porosity prediction using logging curves as inputs. PPTransformer network not only extracts global features through convolutional layers but also captures local features using Encoders and self-attention mechanisms. This proposed network is a data-driven supervised learning framework with a superior accuracy and robustness. The testing results demonstrate that compared to the Transformer network, Long Short-Term time series network, and support vector machine method, the PPTransformer framework exhibits the highest average correlation coefficient and determination coefficient indicators and the lowest root mean square error and absolute error indicators. Moreover, adding stratigraphic lithology as geological constraints to the PPTransformer framework further improves the prediction performance. This indicates that geological constraints will enhance network performance.

Congestion control in internet of things (IoT) using auction theory

The Internet of Things (IoT) facilitates data transmission through communication networks, preventing congestion when input data rate exceeds output, and congestion control in computer networks modulates traffic entry. This paper proposes a fusion of auction theory with reinforcement learning as a means of managing congestion in the IoT. The proposed technique seeks to enhance network performance by utilizing object trustworthiness evaluation and auction-based route selection to manage congestion during data routing. The suggested method calculates the believability of objects by analyzing their historical performance in data forwarding and congestion avoidance, utilizing a learning automaton. The auction approach is employed to determine the most efficient ways for transmitting data. The IoT topology is initially organized into a collection of dependable links known as the Connected Dominating Set (CDS). Active objects employ the learning automata model to assess the reliability of their neighbors. The auction model ultimately chooses the optimal route based on characteristics such as credibility, energy, and delay. The experimental results demonstrate that the proposed methodology surpasses existing comparison methods in the initial scenario, exhibiting a 24.13% reduction in energy usage.

IoT Traffic Parameter Classification based on Optimized BPSO for Enabling Green Wireless Networks

The rapid expansion of artificial intelligence (AI) integrated with the Internet of Things (IoT) has fueled the development of various smart devices, particularly for smart city applications. However, the heterogeneity of these devices necessitates a robust communication network capable of maintaining a consistent traffic flow. This paper employs Machine Learning (ML) models to classify continuously received network parameters from diverse IoT devices, identifying necessary adjustments to enhance network performance. Key network traffic parameters, such as packet data, are transmitted through gateways via specialized tools. Six different ML techniques with default parameters were used: Decision Tree (DT), Random Forest (RF), Support Vector Machines (SVMs), K-Nearest Neighbors (KNN), Naive Bayes (NB), and Stochastic Gradient Descent Classifiers (SGDC), to classify the traffic of the environment (IoT / non IoT). The models' performance was evaluated in a real-time smart laboratory environment comprising 38 IoT devices from various vendors with the following metrics: Accuracy, F1-score, Recall and Precision. The RF model achieved the highest Accuracy of 95.6%. Also the Binary Particle Swarm Optimizer (BPSO) was used across the RF. The results demonstrated that the BPSO-RF with hyperparameter optimization enhanced the Accuracy from 95.6% to 99.4%.

A Comprehensive Strategy for Implementing Adaptive Data Rate (ADR) in LoRaWAN Technology: Optimizing IoT Networks

The Internet of Things (IoT) is increasingly essential for creating smart environments by establishing long range connectivity among devices. LoRaWAN is a prominent technology choice for these applications due to its energy efficiency and extensive coverage. Central to LoRaWAN’s functionality is the Adaptive Data Rate (ADR) mechanism, which optimizes network performance by adjusting each device’s data rate and transmission power dynamically. This study delves into ADR’s operational principles, benefits, and implementation challenges in LoRaWAN networks. The proposed simulation model, featuring configurable parameters like the spreading distribution factor (SF), the adjustable number of devices, and the SNR threshold, denotes enhanced network performance after implementing the ADR algorithm. With an SNR threshold of 15 dB, ADR reduced the average transmission power of 200 devices from 7 dBm to 3 dBm after twenty iterations, underscoring ADR’s role in minimizing energy consumption while improving network efficiency.

Intranet Network Optimization Using VLAN at Vocational High School Gedangan

Purpose: This study aims to optimize the intranet network at Vocational High School Gedangan by using Virtual Local Area Network (VLAN). The main goal is to enhance network performance and security, especially in environments with numerous users, where LAN structures face management and security challenges. Method: The research employs a qualitative descriptive method, utilizing observations and interviews with the school's IT staff to understand how VLAN is implemented and its advantages. The data collected is used to analyze how VLAN can improve network efficiency and flexibility. Practical Applications: By segmenting the network with VLAN, the school can better manage user access and isolate different departments or student groups. This helps prevent network congestion and reduces potential security threats, contributing to a more reliable and secure system for daily operations and learning processes. Conclusion: VLAN implementation at Vocational High School Gedangan significantly optimizes the network's performance and security, creating a more efficient and safer environment for both administration and educational activities.

PDCF-DRL: a contention window backoff scheme based on deep reinforcement learning for differentiating access categories

AbstractIn wireless networks, the Contention Window (CW) is a crucial parameter for wireless channel sharing among numerous stations, directly influencing overall network performance. With the rapid growth and increasing diversity of traffic in wireless networks, differentiating and serving various types of traffic to enhance network performance has become a pressing issue that needs to be addressed. Deep Reinforcement Learning (DRL) optimizes decision-making through the interaction between an agent and its environment, enabling it to handle complex state spaces and high-dimensional data, making it particularly suitable for dynamically adjusting the contention window and adapting to environmental changes in real time. Access Category (AC) is used to differentiate various types of traffic to support different quality of service (QoS) requirements. Therefore, this paper proposes the integration of DRL techniques into the EDCA mechanism, utilizing AC to differentiate network traffic, while the DRL technology adjusts the contention window to adequately ensure QoS for different types of traffic and enhance overall network performance. This paper proposes a CW back off scheme based on DRL for differentiating ACs. The scheme uses DRL technology to observe the channel collision rate and sense the current network conditions, thereby adaptively adjusting the CW size for ACs. In addition, it dynamically adjusts the back off strategy according to the perceived current network conditions to optimize the data transmission process. In the range of 20–120 stations, the scheme was tested in both single AC and multiple AC traffic scenarios, demonstrating excellent performance. The collision rate consistently remained below 18%, while the normalized throughput was maintained above 76%. Additionally, there is a significant improvement compared to existing deep reinforcement learning-based optimization schemes. Experimental results show that this scheme effectively discriminates between different ACs, resulting in lower latency and higher throughput for high-priority traffic. Furthermore, adaptively adjusting the CW size and improving the back off strategy maintains a low collision rate and stable throughput even under heavy load conditions, significantly improving the overall network performance.

Soft Actor-critic-based Distributed Routing Scheme for Edge Computing Integrated with Dynamic IoT Networks

The rapid expansion of the Internet of Things (IoT) necessitates advanced routing schemes capable of meeting the stringent demands for low latency and high accuracy, which are critical for applications such as autonomous vehicles and telemedicine. Traditional edge computing methods often struggle with elevated latency, rendering them unsuitable for time-sensitive applications. Additionally, many reinforcement learning (RL) algorithms require action space discretization, which can introduce biases and dimensionality challenges. This paper introduces a novel Soft Actor-Critic (SAC)-based distributed routing scheme for edge computing, specifically designed to address these limitations. By integrating RL with Maximum Entropy principles and employing a decentralized approach, the proposed model enhances network performance, reduces delays, and effectively manages multi-optimality criteria. The distributed routing scheme operates independently of a centralized controller, allowing routers to make autonomous decisions and adapt seamlessly to changes in the network. This is accomplished through a Markov Decision Process (MDP) that optimizes routing paths based on various factors, including node depth, energy consumption, and transmission probability. The methodology encompasses local training phases for individual nodes, followed by federated training to refine the model across the network. Experimental results conducted on topologies of varying scales demonstrate the model’s efficacy in achieving high accuracy and efficient convergence, particularly in dynamic IoT environments. These findings underscore the potential of the proposed SAC-based distributed routing scheme as a robust solution for enhancing routing efficiency and reliability in the evolving landscape of IoT applications. IMPACT STATEMENT The rapid expansion of Internet of Things (IoT) applications demands advanced routing solutions to ensure low latency and high accuracy, crucial for sectors like autonomous vehicles and telemedicine. Traditional edge computing methods struggle with elevated latency, while many reinforcement learning (RL) algorithms face challenges with action space discretization, leading to biases and dimensionality issues. This study introduces a novel Soft Actor-Critic (SAC)-based distributed routing scheme to address these limitations. Integrating Maximum Entropy principles with RL enhances exploration and decision-making stability. The decentralized approach allows routers to make autonomous, real-time decisions based on local network conditions, optimizing routing paths through a Markov Decision Process (MDP). Experimental results from various simulated IoT network topologies show the model’s superior performance in reducing delays and maintaining bandwidth. This research paves the way for more reliable, low-latency IoT applications, significantly enhancing routing efficiency and network adaptability in dynamic IoT environments.

Deep metric learning with in-batch feature vector constraints and unsupervised label integration

Deep metric learning has increasingly captured the interest of the research community in recent years, mainly due to its effectiveness in integrating distance metric learning with deep neural networks. Despite the existence of various approaches, such as pair-based angular loss functions or spherical embedding constraints, these methods often necessitate extra trainable parameters and overlook class similarities. This paper presents two approaches: ‘In-batch feature vector constraint’ and ‘Unsupervised label integration.’ These methods are notable for considering the similarities between different classes. Because of their high compatibility, these techniques can be seamlessly integrated with various loss functions. Comprehensive experimental evaluations encompassing four image classification datasets and seven network architectures have demonstrated the effectiveness of these proposed methods in enhancing network performance.

The Integration of Artificial Intelligence in Secure Access Service Edge: Enhancing Network Security and Performance

Integrating Artificial Intelligence (AI) with Secure Access Service Edge (SASE) architecture represents a significant advancement in enterprise network security and management. This article examines the transformative impact of AI technologies on SASE implementations, focusing on enhanced threat detection capabilities, dynamic network optimization, and automated compliance management. The article comprehensively analyzes AI-driven security features, including real-time threat detection, zero-trust implementation, and privacy-preserving security measures. Through extensive evaluation of deployment scenarios and performance metrics, our research demonstrates significant improvements in security effectiveness and operational efficiency, including a 90% reduction in threat detection time, a 45% decrease in network latency, and a 65% reduction in manual configuration tasks. The article highlights the system's capability to maintain robust security while preserving data privacy through advanced encrypted traffic analysis techniques. The article addresses current integration challenges and provides insights into successful implementation strategies. This article contributes to the growing body of knowledge on AI-enhanced network security architectures and provides valuable insights for organizations seeking to modernize their security infrastructure while maintaining operational efficiency and compliance with evolving regulatory requirements.

A two-dimensional magnetotelluric deep learning inversion approach based on improved Dense Convolutional Network

Magnetotelluric (MT) inversion is an important means of MT data interpretation. The use of deep learning technology for MT inversion has attracted much attention because it is not limited to the initial model, avoids falling into local optimal solutions, and has the strong ability to process large amounts of data. However, obtaining highly reliable deep learning inversion results remains a challenge. In this paper, we have proposed a two-dimensional (2-D) MT inversion method based on the improved Dense Convolutional Network (DenseNet), with the aim of improving the reliability of the 2-D deep learning MT inversion results. First, the MARE2DEM is used to compute the 2-D MT forward responses when establishing the sample set. Then, an improved DenseNet is proposed by incorporating depthwise separable convolution in lieu of standard convolution within dense connection blocks, and embedding the attention mechanism. Depthwise separable convolution splits the standard convolution operation into depthwise and pointwise convolution, effectively capturing spatial features of input data and correlations between channels. Meanwhile, attention mechanism allows the network to assign varying degrees of importance (or attention) to different elements in a sequence of data, thus enhancing its ability of key feature extraction. This design not only retains the inherent feature reuse and alleviates gradient vanishing of DenseNet but also further enhances network performance. The optimized network parameters for the improved DenseNet are obtained by training on the training set, while the validation set is used to adjust hyperparameters and evaluate model performance. Finally, the proposed 2-D deep learning approach is verified by using both synthetic and field data. Experimental results with synthetic data show that the reliability of inversion results obtained by using the proposed algorithm is improved, and the inversion results obtained by using both TE- and TM-mode data is more accurate than those obtained by using the single mode data. The inversion results of field data show that the proposed 2-D MT deep learning inversion approach can effectively detect the subsurface resistivity structure and has a good application prospect.

A Detailed Inspection of Machine Learning Based Intrusion Detection Systems for Software Defined Networks

The growing use of the Internet of Things (IoT) across a vast number of sectors in our daily life noticeably exposes IoT internet-connected devices, which generate, share, and store sensitive data, to a wide range of cyber threats. Software Defined Networks (SDNs) can play a significant role in enhancing the security of IoT networks against any potential attacks. The goal of the SDN approach to network administration is to enhance network performance and monitoring. This is achieved by allowing more dynamic and programmatically efficient network configuration; hence, simplifying networks through centralized management and control. There are many difficulties for manufacturers to manage the risks associated with evolving technology as the technology itself introduces a variety of vulnerabilities and dangers. Therefore, Intrusion Detection Systems (IDSs) are an essential component for keeping tabs on suspicious behaviors. While IDSs can be implemented with more simplicity due to the centralized view of an SDN, the effectiveness of modern detection methods, which are mainly based on machine learning (ML) or deep learning (DL), is dependent on the quality of the data used in their modeling. Anomaly-based detection systems employed in SDNs have a hard time getting started due to the lack of publicly available data, especially on the data layer. The large majority of existing literature relies on data from conventional networks. This study aims to generate multiple types of Distributed Denial of Service (DDoS) and Denial of Service (DoS) attacks over the data plane (Southbound) portion of an SDN implementation. The cutting-edge virtualization technology is used to simulate a real-world environment of Docker Orchestration as a distributed system. The collected dataset contains examples of both benign and suspicious forms of attacks on the data plane of an SDN infrastructure. We also conduct an experimental evaluation of our collected dataset with well-known machine learning-based techniques and statistical measures to prove their usefulness. Both resources we build in this work (the dataset we create and the baseline models we train on it) can be useful for researchers and practitioners working on improving the security of IoT networks by using SDN technologies.