Enhance Network Performance Research Articles

A Federated Learning-Based Resource Allocation Scheme for Relaying-Assisted Communications in Multicellular Next Generation Network Topologies

Growing and diverse user needs, along with the need for continuous access with minimal delay in densely populated machine-type networks, have led to a significant overhaul of modern mobile communication systems. Within this realm, the integration of advanced physical layer techniques such as relaying-assisted transmission in beyond fifth-generation (B5G) networks aims to not only enhance network performance but also extend coverage across multicellular orientations. However, in cellular environments, the increased interference levels and the complex channel representations introduce a notable rise in the computational complexity associated with radio resource management (RRM) tasks. Machine and deep learning (ML/DL) have been proposed as an efficient way to support the enhanced user demands in densely populated environments since ML/DL models can relax the traffic load that is associated with RRM tasks. There is, however, in these solutions the need for distributed execution of training tasks to accelerate the decision-making process in RRM tasks. For this purpose, federated learning (FL) schemes are considered a promising field of research for next-generation (NG) networks’ RRM. This paper proposes an FL approach to tackle the joint relay node (RN) selection and resource allocation problem subject to power management constraints when in B5G networks. The optimization objective of this approach is to jointly elevate energy (EE) and spectral efficiency (SE) levels. The performance of the proposed approach is evaluated for various relaying-assisted transmission topologies and through comparison with other state-of-the-art ones (both ML and non-ML). In particular, the total system energy efficiency (EE) and spectral efficiency (SE) can be improved by up to approximately 10–20% compared to a state-of-the-art centralized ML scheme. Moreover, achieved accuracy can be improved by up to 10% compared to state-of-the-art non-ML solutions, while training time is reduced by approximately 50%.

Cyber-Secure SDN: A CNN-Based Approach for Efficient Detection and Mitigation of DDoS attacks

Software Defined Networking (SDN) has become popular due to its flexibility and agility in network management, enabling rapid adaptation to changing business requirements, enhancing network performance, and reducing operational costs. However, the ubiquity of internet-based services has given rise to an alarming increase in cyber-attacks, posing serious threats to the security and stability of modern networks. Among these attacks, Distributed Denial of Service (DDoS) attacks have emerged as one of the most devastating, capable of disrupting critical services. Recent studies have shown that Deep Learning (DL) techniques with Software-defined networking have the potential to mitigate these threats effectively. However, existing solutions suffer from issues such as reliance on pre-defined rules and signatures, computational efficiency, low detection rates, and inefficient notification mechanisms, making them ineffective in detecting DDoS attacks. This paper proposes an efficient approach (BRS + CNN) using Balanced Random Sampling (BRS) and Convolutional Neural Networks (CNNs) to detect DDoS attacks in SDN environments. We have applied various mitigation techniques to mitigate these threats, such as filtering, rate limiting, and iptables rule for blocking spoofed IPs. In addition, we introduce a monitoring system that utilizes rate-limiting to oversee blocked IP addresses, ensuring that legitimate traffic is processed efficiently. The proposed model achieves high performance in binary and multi-classification, with an accuracy of over 99.99% for binary classification and 98.64% for multi-classification. Our proposed DDoS detection system not only detects the attack but also sends detailed contextual information to a designated email address. We compare our model with existing literature and demonstrate its superiority using Area Under The Curve (AUC) analysis. Moreover, we evaluated the efficiency and effectiveness of our proposed DDoS mitigation system by conducting a series of experiments across three distinct scenarios: Attack-Free, Attack-No Mitigation, and Attack-Mitigation. These results demonstrate the robustness of our proposed mitigation system in effectively combating DDoS attacks while also safeguarding the seamless continuity of regular network operations.

ContextMix: A context-aware data augmentation method for industrial visual inspection systems

While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial manufacturing contexts. Recently, image mixing-based methods have been introduced, exhibiting improved performance on public benchmark datasets. However, their application to industrial tasks remains challenging. The manufacturing environment generates massive amounts of unlabeled data on a daily basis, with only a few instances of abnormal data occurrences. This leads to severe data imbalance. Thus, creating well-balanced datasets is not straightforward due to the high costs associated with labeling. Nonetheless, this is a crucial step for enhancing productivity. For this reason, we introduce ContextMix, a method tailored for industrial applications and benchmark datasets. ContextMix generates novel data by resizing entire images and integrating them into other images within the batch. This approach enables our method to learn discriminative features based on varying sizes from resized images and train informative secondary features for object recognition using occluded images. With the minimal additional computation cost of image resizing, ContextMix enhances performance compared to existing augmentation techniques. We evaluate its effectiveness across classification, detection, and segmentation tasks using various network architectures on public benchmark datasets. Our proposed method demonstrates improved results across a range of robustness tasks. Its efficacy in real industrial environments is particularly noteworthy, as demonstrated using the passive component dataset.

Routing Selection Algorithm for Mobile Ad Hoc Networks Based on Neighbor Node Density.

In the process of data transmission in mobile ad hoc networks, it is essential to establish optimal routes from source nodes to destination nodes. However, as network density increases, this process is often accompanied by a significant rise in network overhead. To address this issue, the ND-AODV (neighborhood density AODV) protocol has been introduced, which reduces the probability of transmitting control information in high-density node environments to mitigate network overhead. Nevertheless, this may come at the cost of reduced routing accuracy, potentially leading to unnecessary resource wastage in certain scenarios. Furthermore, ND-AODV does not comprehensively consider the location of the receiving nodes, which limits its ability to reduce network overhead effectively. To overcome these limitations, this paper introduces a novel routing approach, known as CND-AODV (common neighborhood density AODV). In comparison to ND-AODV, CND-AODV offers a more comprehensive solution to the challenges posed by high-density network environments. It intelligently processes control information based on the special positioning of the receiving nodes, thereby significantly reducing unnecessary network overhead. Through simulation experiments comparing performance metrics such as throughput, packet delivery rate, and latency, the results clearly indicate that CND-AODV substantially decreases network overhead, enhancing network performance. Compared to ND-AODV, this innovative routing approach exhibits significant advantages. It provides a more efficient and reliable solution for ad hoc networks in high-density environments.

Optimizing Internet-Wide Port Scanning for IoT Security and Network Resilience: A Reinforcement Learning-Based Approach in WLANs with IEEE 802.11ah

ABSTRACT The rapid proliferation of Internet of Things (IoT) devices has spurred the need for robust security mechanisms within wireless local area network (WLAN) environments. Specifically, the IEEE 802.11ah (WiFi-HaLow) technology offers low-power, long-range communication capabilities ideally suited for IoT devices, but these devices face security threats due to constrained computational resources. This research addresses the challenge of optimizing Internet-wide port scanning to enhance IoT security while minimizing disruptions to network performance. In this paper, we propose a novel reinforcement learning-based approach to achieve this optimization. Our approach harnesses the power of the Proximal Policy Optimization (PPO) algorithm to guide decision-making for IoT security and network performance enhancement. The proposed solution entails training an agent to dynamically adjust the port scanning rate, ensuring the delicate balance between security improvement and network responsiveness. We establish a comprehensive system model, encompassing WiFi-HaLow infrastructure, IPv6-enabled IoT devices, and the integration of Internet-security (IPSec) protocols. Mathematical formulations encapsulate constraints such as resource limitations and security-performance trade-offs. Our experimental setup utilizes a carefully curated dataset and a simulation environment to rigorously evaluate the proposed solution’s effectiveness. The proposed approach demonstrates remarkable security enhancement through the prevention of unauthorized access attempts, data breaches, and improved intrusion detection. Moreover, network performance is optimized, with reductions in latency, improvements in throughput, and energy-efficient operation. By presenting a plethora of comparison scenarios, we validate the superiority of our solution against various benchmarks. This research contributes a comprehensive framework that not only advances IoT security within WLAN environments but also highlights the intricate relationship between security and network performance optimization.

TBE-Net: A Deep Network Based on Tree-like Branch Encoder for Medical Image Segmentation.

In recent years, encoder-decoder-based network structures have been widely used in designing medical image segmentation models. However, these methods still face some limitations: 1) The network's feature extraction capability is limited, primarily due to insufficient attention to the encoder, resulting in a failure to extract rich and effective features. 2) Unidirectional stepwise decoding of smaller-sized feature maps restricts segmentation performance. To address the above limitations, we propose an innovative Tree-like Branch Encoder Network (TBE-Net), which adopts a tree-like branch encoder to better perform feature extraction and preserve feature information. Additionally, we introduce the Depth and Width Expansion (D-WE) module to expand the network depth and width at low parameter cost, thereby enhancing network performance. Furthermore, we design a Deep Aggregation Module (DAM) to better aggregate and process encoder features. Subsequently, we directly decode the aggregated features to generate the segmentation map. The experimental results show that, compared to other advanced algorithms, our method, with the lowest parameter cost, achieved improvements in the IoU metric on the TNBC, PH2, CHASE-DB1, STARE, and COVID-19-CT-Seg datasets by 1.6%, 0.46%, 0.81%, 1.96%, and 0.86%, respectively.

Electric Theft Detection Based on Multilayer Backpropagation Neural Network Optimized by Sine Chaotic Genetic Algorithm

Abstract In the era of big data, the growing volume of data in electrical systems has led to a rise in electric theft incidents, posing challenges to grid security. This paper introduces a detection method using the Sine chaotic genetic algorithm to optimize multilayer Backpropagation (BP) neural networks. Initially, a comprehensive dataset is compiled through extensive data collection. A multilayer BP neural network is then trained on this dataset for automated theft identification. Leveraging the Sine chaotic genetic algorithm further enhances network performance. Experimental results show an 88% prediction accuracy, offering improved accuracy, speed, and usability over traditional methods.

Improved schema: Enhancing robustness and efficiency in Mobile Ad Hoc Networks through dynamic neighbour selection and transmission range adjustment

In Wireless Sensor Networks (WSNs), maintaining connectivity is crucial due to their dynamic nature. To address this challenge, this paper proposes an "improved schema," a novel approach aimed at enhancing the robustness and efficiency of Mobile Ad Hoc Networks (MANETs). A core advancement in the "improved schema" is its sophisticated neighbor selection algorithm, which considers factors such as node stability, link quality, and proximity. This algorithm ensures the selection of reliable neighbors, thereby improving overall network stability. Another significant improvement in the "improved schema" is the dynamic transmission range adjustment. By adapting transmission ranges in real-time based on current network conditions, the scheme optimizes communication ranges, enhancing network performance in varying environments. Additionally, the scheme leverages knowledge of network topology for pathfinding. By incorporating awareness of the network structure, the "improved schema" identifies more efficient paths for connectivity restoration, thereby minimizing resource utilization and latency. This study conducted extensive simulations to evaluate the performance of the "improved schema" against established schemes, including the Restoring Connectivity through Inward Motion (RIM), Nearest Neighbour (NN), and Survivability-Aware Connectivity Restoration (SACR) strategies. The results consistently demonstrate that the "improved schema" outperforms existing schemes in terms of connectivity robustness, adaptability to dynamic scenarios, and overall network efficiency. These findings underscore the effectiveness of the "improved schema" in addressing the inherent challenges faced by WSNs and MANETs, making it a promising solution for improving network performance in dynamic environments.

Reinforced Metapath Optimization in Heterogeneous Information Networks for Drug-Target Interaction Prediction.

Graph neural networks offer an effective avenue for predicting drug-target interactions. In this domain, researchers have found that constructing heterogeneous information networks based on metapaths using diverse biological datasets enhances prediction performance. However, the performance of such methods is closely tied to the selection of metapaths and the compatibility between metapath subgraphs and graph neural networks. Most existing approaches still rely on fixed strategies for selecting metapaths and often fail to fully exploit node information along the metapaths, limiting the improvement in model performance. This paper introduces a novel method for predicting drug-target interactions by optimizing metapaths in heterogeneous information networks. On one hand, the method formulates the metapath optimization problem as a Markov decision process, using the enhancement of downstream network performance as a reward signal. Through iterative training of a reinforcement learning agent, a high-quality set of metapaths is learned. On the other hand, to fully leverage node information along the metapaths, the paper constructs subgraphs based on nodes along the metapaths. Different depths of subgraphs are processed using different graph convolutional neural network. The proposed method is validated using standard heterogeneous biological benchmark datasets. Experimental results on standard datasets show significant advantages over traditional methods.

Optimising the placement and sizing of a predefined number of battery energy storage systems on Distribution Networks

Increased deployment of distributed renewable energy on distribution networks has become a popular approach in the effort towards decarbonisation. The paper addresses the challenges related to voltage deviation and power loss resulting from higher levels of photovoltaic systems (PV) penetration. Battery Energy Storage Systems (BESS) provide a flexible solution to enhance network performance. The paper develops a novel methodology for the optimal placement and sizing of a set number of BESS units on the network. The methodology is intended to assist Distribution Network Operators (DNOs) in planning the optimal deployment of a specified number of BESS units. The problem is modelled as a mixed-integer linear program with conic relaxation approach. Numerical simulations are carried out to demonstrate the usefulness of the proposed approach with the help of the IEEE 33-bus network utilising 3, 5 and 7 BESS units. The paper examines the BESS requirements and performance as the set number of units deployed is varied.

Integrating Smart Computility for Subflow Orchestration in Remote Virtual Services.

The burgeoning domain of the metaverse has sparked significant interest from a diverse array of industries, including healthcare services. However, the metaverse and its associated applications present various challenges. This could strain the comprehensive capacity of existing networks. In this paper, we have investigated vital network demands of healthcare services within the metaverse. First, to meet the increasing demands of the metaverse, there is a need for enhanced bandwidth, reduced latency, and improved packet loss control. Furthermore, the transmission mechanism should exhibit flexibility to automatically adapt to the diverse hybrid needs of different healthcare services. Considering the aforementioned challenges, a transmission paradigm tailored for the metaverse-based healthcare services is developed. Multipath transmission has the potential to effectively enhance network performance in multiple aspects. Significantly, we devise an orchestration framework to reconcile edge-side subflow management with diverse healthcare applications. Using machine learning techniques, the framework can produce near-optimal subflow adjustment strategies for client nodes and miscellaneous services. Comprehensive experiments are performed on applications with diverse requirements to validate the adaptability of the framework to the application needs. The experimental results demonstrate that the proposed method enables the network to autonomously adapt to changing network conditions and service requirements. This includes applications' preferences for high throughput, low delay, and high stability. Moreover, the test results show that the proposed approach can notably decrease the occurrences of network quality falling below the minimum requirement. Given its adaptability and impact on network quality, this work paves the way for future metaverse-based healthcare services.

FDSR: An Interpretable Frequency Division Stepwise Process Based Single-Image Super-Resolution Network.

Deep learning has excelled in single-image super-resolution (SISR) applications, yet the lack of interpretability in most deep learning-based SR networks hinders their applicability, especially in fields like medical imaging that require transparent computation. To address these problems, we present an interpretable frequency division SR network that operates in the image frequency domain. It comprises a frequency division module and a step-wise reconstruction method, which divides the image into different frequencies and performs reconstruction accordingly. We develop a frequency division loss function to ensure that each reconstruction module (ReM) operates solely at one image frequency. These methods establish an interpretable framework for SR networks, visualizing the image reconstruction process and reducing the black box nature of SR networks. Additionally, we revisited the subpixel layer upsampling process by deriving its inverse process and designing a displacement generation module. This interpretable upsampling process incorporates subpixel information and is similar to pre-upsampling frameworks. Furthermore, we develop a new ReM based on interpretable Hessian attention to enhance network performance. Extensive experiments demonstrate that our network, without the frequency division loss, outperforms state-of-the-art methods qualitatively and quantitatively. The inclusion of the frequency division loss enhances the network's interpretability and robustness, and only slightly decreases the PSNR and SSIM metrics by an average of 0.48 dB and 0.0049, respectively.

A Survey on User Grouping Schemes in Non- Orthogonal Multiple Access (NOMA)

In wireless networks, managing an increasing number of users becomes increasingly challenging as user density rises. To address these challenges, various algorithms are employed to divide users into smaller, more controllable groups. This approach is crucial for optimizing the performance of Non-Orthogonal Multiple Access (NOMA) systems, which are a key component of nextgeneration wireless networks like 5G and 6G. User grouping schemes in NOMA systems are essential for optimizing resource allocation, mitigating interference, improving spectral efficiency, ensuring fairness, and reducing complexity. As wireless networks evolve, particularly with the integration of advanced technologies like Coordinated Multi-Point (CoMP), Internet of Things (IoT), Millimeter- Wave (mmWave), Terahertz (THz), Unmanned Aerial Vehicles (UAVs), Multi-Input Multi-Output (MIMO), and 5G-6G, effective user grouping will become increasingly critical. This research paper provides a systematic classification and analysis of various user grouping schemes, offering valuable insights for enhancing network performance in next-generation wireless networks.

HDRA: A Haybird Data Reduction and Routing Algorithm

Presently, wireless sensor networks (WSNs) are emerging as a vibrant field of research due to various challenging aspects such as energy consumption, routing strategies, effectiveness, among others. Despite unresolved issues within WSNs, a substantial array of applications has already been developed. For any application design, a primary objective is to optimize the WSN in terms of its lifecycle and functionality. Recent studies on data reduction methods have shown that sensor nodes often transmit data directly (single hop) to the base station (BS). However, a significant concern is that most existing multi-hop routing protocols do not address data reduction before forwarding data to the BS. Consequently, this study introduces a Hybrid Data Reduction and Routing Algorithm (HDRA). The principal aim of HDRA is to prolong the lifespan of cluster-based WSNs. It strives to decrease the packet transmission by sensor nodes, especially when there's minimal change in sensor readings. The findings indicate that HDRA outperforms the LEACH protocol in terms of energy efficiency in sensor networks, irrespective of network type (T, H, or TH) or deployment scenarios (200x200m or 400x400m). Overall, the proposed algorithm enhances network performance by conserving energy and extending network lifespan.

VRPR: A New Data Center Protocol for Enhanced Network Performance, Resilience, and Recovery

VRPR: A New Data Center Protocol for Enhanced Network Performance, Resilience, and Recovery

A Fair and Self-sufficient Value Stack-Based Compensation Scheme for DERs Enhancing Network Performance

A Fair and Self-sufficient Value Stack-Based Compensation Scheme for DERs Enhancing Network Performance

Innovative Power Smoothing Technique for Enhancing Renewable Integration in Insular Power Systems Using Electric Vehicle Charging Stations

The reliance on imported fuels for electricity generation and internal transportation in insular electrical systems has historically posed a significant challenge due to their geographic isolation. The vulnerability of insular ecosystems to pollution has driven the need to transition toward renewable energy sources. Despite their inherent variability, wind and solar energy have gained acceptance. Integrating these renewable technologies into insular grids presents technical challenges that impact the quality of the power supply, particularly with the increasing presence of electric vehicles. Nevertheless, the batteries of these vehicles provide an opportunity to enhance network performance. This article introduces an innovative power smoothing technique that utilizes electric vehicle batteries to optimize self-consumption and reduce power fluctuations. The proposed method is an enhanced version of the ramp-rate energy smoothing method, incorporating adaptability through real-time control of the ramp-rate using fuzzy logic. It employs an aggregated model of lithium-ion batteries with a bidirectional power electronic converter. Experimental validation is carried out in the Micro-Grid Laboratory of the University of Cuenca, Ecuador. Experimental results demonstrate a significant 14% reduction in energy generation variability, resulting in a more stable electrical supply profile. Additionally, there is a marginal improvement in energy delivery, with an additional injection of 0.23 kWh compared to scenarios without the participation of electric vehicle batteries in power smoothing tasks. These findings support the effectiveness of the proposed approach in optimizing the integration of intermittent renewable generators and electric vehicle charging in insular energy systems.

Survey of the Influence of Routing Protocols to Network Performance Enhancement

Routing protocols play a crucial role in the operation of computer networks by determining the optimal paths for data transmission. The selection of an appropriate routing protocol can significantly impact network performance, including factors such as latency, throughput, reliability, and scalability. This survey aims to provide a comprehensive analysis of the influence of various routing protocols on network performance enhancement. The survey begins by presenting an overview of common routing protocols with their key characteristics. Subsequently, it explores the impact of these protocols on network performance metrics, focusing on their ability to adapt to changing network conditions, mitigate congestion, and ensure efficient resource utilization. Through a systematic review of literature, empirical studies, and real-world implementations, this survey aims to provide network administrators, researchers, and practitioners with valuable insights into selecting and optimizing routing protocols for specific network environments. Additionally, it identifies areas for further research and development to continue advancing the field of routing protocols and network performance enhancement. Keywords: Optimizing Routing Protocols, Performance Metrics, Reliability and Scalability, Resource Utilization, Wireless Local Area Networks, Accurate Routing Tables Juliana I. Consul & Bunakiye R. Japheth (2023): Survey of the Influence of Routing Protocols to Network Performance Enhancement. Journal of Advances in Mathematical & Computational Science. Vol. 11, No. 4. Pp 13-28 Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V11N4P2

WAN optimization techniques: Exploring BGP attributes across industries

Wide Area Network (WAN) optimization has become a critical focus for industries seeking to enhance network performance, particularly in the era of digital transformation and cloud-based services. This paper explores the role of Border Gateway Protocol (BGP) attributes as a key element in WAN optimization across various industries. BGP, as the protocol responsible for routing data between autonomous systems on the internet, plays a significant role in determining the efficiency and reliability of data transmission across WANs. By leveraging specific BGP attributes, organizations can optimize network paths, reduce latency, and improve overall network performance. The paper begins by providing an overview of WAN optimization techniques and the importance of BGP in modern network architecture. It then delves into the specific BGP attributes that are instrumental in optimizing WAN performance, including Local Preference, AS Path, MED (Multi-Exit Discriminator), and BGP Communities. The discussion includes how these attributes can be manipulated to achieve optimal routing decisions, prioritize traffic, and manage bandwidth more effectively. Case studies from various industries, including financial services, healthcare, manufacturing, and telecommunications, are presented to illustrate the practical applications and benefits of BGP-based WAN optimization. These examples highlight how organizations have successfully implemented BGP attribute manipulation to address industry-specific challenges such as ensuring low-latency communication, maintaining high availability, and supporting large-scale data transfers. The paper also addresses the challenges associated with BGP attribute manipulation, including the complexities of configuration and the potential risks of misconfigurations leading to network instability. It concludes with a discussion on emerging trends in WAN optimization, such as the integration of software-defined WAN (SD-WAN) technologies and the role of machine learning in automating and enhancing BGP-based optimizations. In summary, this paper provides a comprehensive exploration of how BGP attributes can be leveraged for WAN optimization across different industries, offering insights into best practices and future directions in network performance enhancement. Keywords: WAN, Optimization, Techniques, BGP, Attributes.

Effects Investigation of MAC and PHY Layer Parameters on the Performance of IEEE 802.15.6 CSMA/CA

The recently released IEEE 802.15.6 standard specifies several physical (PHY) layer and medium access control (MAC) layer protocols for variety of medical and non-medical applications of Wireless Body Area Networks (WBAN). The most suitable way for enhancing network performance is to be the choice of different MAC and PHY parameters based on quality of service (QoS) requirements of different applications. The impact of different MAC and PHY parameters on the network performance and the tradeoff relationship between the parameters are essential to overcome the limitations of exiting carrier sense multiple access with collision avoidance (CSMA/CA) scheme of IEEE 802.15.6 standard. To address this issue, we develop a Markov chain-based analytical model of IEEE 802.15.6 CSMA/CA for all user priorities (UPs) and apply this general model to different network scenarios to investigate the effects of the packet arrival rate, channel condition, payload size, access phase length, access mechanism and number of nodes on the performance parameters viz. reliability, normalized throughput, energy consumption and average access delay. Moreover, we conclude the effectiveness of different access phases, access mechanisms and user priorities of intra-WBAN.