Improve Network Performance Research Articles

GeoSynth: A Photorealistic Synthetic Indoor Dataset for Scene Understanding.

Deep learning has revolutionized many scene perception tasks over the past decade. Some of these improvements can be attributed to the development of large labeled datasets. The creation of such datasets can be an expensive, time-consuming, and imperfect process. To address these issues, we introduce GeoSynth, a diverse photorealistic synthetic dataset for indoor scene understanding tasks. Each GeoSynth exemplar contains rich labels including segmentation, geometry, camera parameters, surface material, lighting, and more. We demonstrate that supplementing real training data with GeoSynth can significantly improve network performance on perception tasks, like semantic segmentation. A subset of our dataset will be made publicly available at https://github.com/geomagical/GeoSynth.

Optimization of Drone Base Station Location for the Next-Generation Internet-of-Things Using a Pre-Trained Deep Learning Algorithm and NOMA

Next-generation Internet-of-Things applications pose challenges for sixth-generation (6G) mobile networks, involving large bandwidth, increased network capabilities, and remarkably low latency. The possibility of using ultra-dense connectivity to address the existing problem was previously well-acknowledged. Therefore, placing base stations (BSs) is economically challenging. Drone-based stations can efficiently address Next-generation Internet-of-Things requirements while accelerating growth and expansion. Due to their versatility, they can also manage brief network development or offer on-demand connectivity in emergency scenarios. On the other hand, identifying a drone stations are a complex procedure due to the limited energy supply and rapid signal quality degradation in air-to-ground links. The proposed method uses a two-layer optimizer based on a pre-trained VGG-19 model to overcome these issues. The non-orthogonal multiple access protocol improves network performance. Initially, it uses a powerful two-layer optimizer that employs a population of micro-swarms. Next, it automatically develops a lightweight deep model with a few VGG-19 convolutional filters. Finally, non-orthogonal multiple access is used to schedule radio and power resources to devices, which improves network performance. We specifically examine how three scenarios execute when various Cuckoo Search, Grey Wolf Optimization, and Particle Swarm Optimization techniques are used. To measure the various methodologies, we also run non-parametric statistical tests, such as the Friedman and Wilcoxon tests. The proposed method also evaluates the accuracy level for network performance of DBSs using number of Devices. The proposed method achieves better performance of 98.44% compared with other methods.

Evolution of cooperation in vehicular cloud assisted networks for ITS services: A hunt game-based approach

Modern-day vehicles that are generally equipped with advanced sensors, devices, and communication technologies and sophisticated cloud computing facilities paved the way for vehicular cloud-assisted networks. It has the potential to effectively offer a broad range of on-demand services to help intelligent transportation systems sustain current traffic loads. The system can be fully functional only when the vehicles remain available and cooperate to form such a system and provide services. However, the behavior of the nodes is highly dependent on the neighborhood environment and the needs of the owner. Hence, nodes may bail out from the system at random. Therefore, the stimulation of cooperation becomes a research challenge. In this work, we analyzed the behavior of nodes by modeling the event of intelligent transportation service provisioning in a vehicular cloud-assisted network as a cooperative hunt game to find a sufficient condition under which cooperation could be evolved. Subsequently, an incentive-based cooperation scheme is proposed that guarantees optimal incentives to the nodes depending upon their roles and the amount of participation in the network activities. To evaluate the scheme, we have created a static vehicular cloud testbed that provides Intelligent Transportation services like optimal route information to vehicles. Evaluation results show that our scheme brings about conditions where obeying network protocols and serving faithfully to the system becomes the most suitable and stable strategy for nodes. We have also analyzed various network parameters such as end-to-end delay, packet delivery ratio, normalized acceptance rate, normalized delivery rate, etc., that show the improvement in network performance as compared to other strategies.

A reliable position-based routing scheme for controlling excessive data dissemination in vehicular ad-hoc networks

In the past two decades, the automotive industry has undergone tremendous changes, as this field has become one of the fastest developing and growing fields, especially with the progress of global digitization and massive research related to networks. So, it comes as no surprise that self-driving vehicles are ubiquitous mainly relying on Vehicular ad-hoc networks (VANETs). This transformation ensures improved road navigation and traffic congestion avoidance by relying on Rapid Data Deployment (DD). On the other hand, although DD achieves high connection reliability, it may affect network bandwidth and performance. In addition, excessive DD causes frequent link outages resulting in reduced data delivery, massive packet loss, and premature end of network life. This paper presents an integrated architecture proposal for a vehicle dynamic assistance architecture, based on reliable methods to ensure steering accuracy while minimizing the energy expended for controlling the DD rate via VANETs. The proposed architecture integrates between Software-Defined Networks (SDN) and fog computing based on dealing with the mobility factors that exploit vehicle communication behaviors. Such integration will aid in improving network performance in terms of packet delivery and DD. The study also discusses how to take into consideration the Euclidean distance, geographical routing information, residual power ratio, and latency time to maximize network stability and avoid possible link disruption. The simulation results prove that there is a 62% to 70% enhancement of the whole power consumption and network throughput, depending on the implementation of the proposed position-based routing approach. Interestingly, the proposed routing protocol is a dual-phase routing protocol with a 90% of SDN data packet delivery ratio and an 82% of SDN data loss reduction. So, when the SDN fails to deliver packets, the proposed position-based routing handles them as a parallel mechanism of SDN.

Meta-Routing Paradigm for Robotic Ad-hoc Networks

With the increasing use of robotic networks, communication issues such as maintaining connections between nodes are becoming more prevalent. While previous routing protocols for wireless networks have been developed, they tend to address routing and link maintenance separately. Consequently, the separation leads to increased costs and delays in network communication. Existing routing protocols typically focus on discovering links, connecting them, finding the most efficient path, and reducing costs associated with the path. However, their limitations have led to the development of a new routing mechanism for robotic networks called Meta-Routing. Meta-Routing builds on existing routing protocols by incorporating regular routing of packets and maintenance of links in mobile agent environments. This approach aims to improve efficiency and reduce routing and link maintenance costs. In addition, meta-Routing seeks to minimize communication path costs and the overhead cost associated with discovering a route, repairing a link, or creating a new communication path among nodes. This paper presents a method for achieving Meta-Routing by controlling robot motion based on recognizing the radio frequency (RF) environment through Hidden Markov Models (HMMs) and gradient descent methods. Simulation results show that Meta-Routing, based on controlling individual robot motion, can provide self-healing capabilities in mobile robot networks, decrease network latency, and improve network performance.

Energy-Efficient and Physical-Layer Secure Computation Offloading in Blockchain-Empowered Internet of Things

This article investigates computation offloading in blockchain-empowered Internet of Things (IoT), where the task data uploading link from sensors to a base station (BS) is protected by intelligent reflecting surface (IRS)-assisted physical-layer security (PLS). After receiving task data, the BS allocates computational resources provided by mobile-edge computing (MEC) servers to help sensors perform tasks. Existing blockchain-based computation offloading schemes usually focus on network performance improvements, such as energy consumption minimization (ECM) or latency minimization, and neglect the Gas fee for computation offloading, resulting in the dissatisfaction of high Gas providers. Also, the secrecy rate during the data uploading process cannot be measured by a steady value because of the time-varying characteristics of IRS-based wireless channels, thereby computational resources allocation with a secrecy rate measured before data uploading is inappropriate. In this article, we design a Gas-oriented computation offloading scheme that guarantees a low degree of dissatisfaction of sensors, while reducing energy consumption. Also, we deduce the ergodic secrecy rate of IRS-assisted PLS transmission that can represent the global secrecy performance to allocate computational resources. The simulations show that the proposed scheme has lower energy consumption compared to existing schemes and ensures that the node paying higher Gas gets stronger computational resources.

A Versatile Resilience Packet Ring Protocol Model for Homogeneous Networks

Optimizing routes and paths improves network performance. Due to the encapsulation and tunneling of the packets, mobile IP-based communication contributes to packet drops or significant delays between the sender and receiver. Packet loss during handoff reduces TCP throughput as well. One solution is to use the IEEE 802.11 Medium Access Control (MAC) protocol and TCP or UDP models to increase routing protocol performance. In the linkage of homogeneous networks, it is challenging to determine route failure. In addition, the 802.11 MAC also uses a link connection. As a result, re-covering the entire route path takes a longer time. Thus, improving wired and wireless mobile node communication and handover is both challenging and critical. To overcome this challenge, we propose to use the Versatile Resilience Packet Ring protocol (VRPR)-based model. In this paper, we propose a novel VRPR-based network model that allows uninterrupted communication in both wired and wireless media. VRPR is used in the network layer to avoid buffer overflow and client mobility. Our new model also identifies the cause of the route failure, whether it is due to client mobility (handover), due to link breakage (channel degradation), or due to buffer overflow. We evaluate our network model based on three performance factors, namely, the delay, packet, and packet loss, and compared it between wired and wireless media. Our Enhanced-VRPR-based network model outperforms the current VRPR wired and wireless network models. We validate our model through OMNet++ simulations.

Refined regression detector for multiclass-oriented target in optical remote sensing images

In recent years, multiclass target detection in remote sensing images has become a popular research topic, and it has been widely applied in military and civilian fields. Multiclass-oriented target detection in remote sensing images presents the following challenges: small densely parked targets (SDPT), multidirectionality, interclass unbalanced number of samples (ICUNS), and hard example detection. These problems will impact the result. Therefore, to solve the abovementioned problems, we propose a multiclass-oriented target detection method in optical remote sensing images. In the detection stage, an oriented bounding box (OBB) is used to predict the angle of the target, which can overcome the problems of SDPT and multidirectionality. A cascade refined module is proposed to solve the problem of network performance degradation caused using the OBB. Second, the smooth L1 loss function is used, which can complete OBB regression by adding an angle parameter. This method can improve network performance. Finally, gradient harmonized mechanism loss is applied to the OBB. It can solve problems, such as ICUNS and hard example detection. We describe experiments conducted on the DOTA public optical remote sensing dataset. The experimental results show that this method is effective for multiclass-oriented target detection in optical remote sensing images.

Design of NULLMAC Protocol for Mobile Ad Hoc Network Using Adaptive Antenna Array

Usually, omnidirectional radiation pattern antenna is used in the mobile ad hoc network (MANET) which causes neighbor node interference, consumes more power, and supports only limited range of transmission. To overcome these problems, smart antennas are used. A lot of medium access control (MAC) protocols are proposed using smart antennas. Existing works addressed various problems such as hidden terminal problem, hidden beam problem, deafness of nodes, and head of line blocking problem. However, certain factors including determination of weight vector and conveying it to the neighbor nodes for distortion-free transmission are not considered. In this study, nullifying MAC (NULLMAC) framework is proposed using an adaptive antenna array (AAA) for improving network performance in MANET. NULLMAC framework uses channel information for achieving high throughput and spatial reuse through integrated physical and MAC layer. Before the transfer of data packets, the receiver initially determines its weight vector and conveys it to the transmitter through control packets. Then, the transmitter computes its weight to nullify the dynamic receivers present in the neighborhood region to find the desired receiver. Beamformer weights are determined through channel coefficients between a transmitter-receiver pair to establish distortion-free transmission. Extensive simulations are performed using OPNET integrated with MATLAB. NULLMAC framework achieves 27.22% more throughput and 40.46% increase in signal-to-noise ratio.

A Multi-Objective Virtual Network Migration Algorithm Based on Reinforcement Learning

Virtual network migration (VNM) helps improve network performance by remapping a subset of virtual nodes or links to physical infrastructure, aligning the resource allocation to the virtual network&#x0027;s changing conditions. However, existing VNM methods neglect integrating multiple objectives that affect network performance, such as energy, communication, migration, and service level agreement violation (SLAV). It is challenging to make VNM decisions to optimize the overall objective in a large-scale cloud environment. This article establishes a multi-objective optimization model and proposes a multi-objective VNM algorithm called MiOvnm. The MiOvnm employs the double deep <inline-formula><tex-math notation="LaTeX"><?TeX $Q$?></tex-math></inline-formula>-learning approach to cope with ample state space. It also applies an action selection method called actfilter to deal with large-scale action space. The MiOvnm finds the migration action with optimal potential reward from the candidate action set. Simulation results demonstrate the superiority of our MiOvnm to the state-of-the-art methods. More specifically, MiOvnm reduces average SLAV, communication cost, and total cost by 24.32&#x0025;, 4.95&#x0025;, and 12.45&#x0025;, respectively. Furthermore, evaluation results in a real-world OpenStack platform reveal that making full use of computation and network resources, the MiOvnm reduces the completion time of computation- and network-intensive benchmarks by 11.35&#x0025; and 10.31&#x0025;, respectively, with a total cost reduction of 26.02&#x0025;.

A NOVEL ARCHITECTURE OF INTELLIGENT DECISION MODEL FOR EFFICIENT RESOURCE ALLOCATION IN 5G BROADBAND COMMUNICATION NETWORKS

Intelligent Decision Model for efficient resource allocation in 5G broadband communication networks is essential for ensuring the most efficient use of available resources. This model considers several factors, such as traffic demand, network topology, and radio access technology, to make the most efficient decisions about resource allocation. It is based on intelligent algorithms and advanced analytics, which allow the network to quickly and accurately identify the optimal resource allocation for a given situation. This model can reduce costs, improve network performance, and increase customer satisfaction. In addition, the Intelligent Decision Model can help operators reduce the complexity and cost of managing a 5G network. The intelligent decision model for efficient resource allocation in 5G broadband communication networks is based on a combination of artificial intelligence (AI) and optimization techniques. The proposed decision models can use AI to identify patterns in traffic and user behavior. In contrast, the proposed can use optimization techniques to maximize resource utilization and reduce latency in the network. This model can also leverage predictive analytics and machine learning algorithms to determine the most efficient allocation of resources. Additionally, the proposed model can use AI to detect and mitigate potential security threats and malicious activities in the network. the proposed IDM has reached 91.85% of accuracy, 90.05% of precision, 90.96% of recall and 91.33% of F1-score.

Capacity Maximization in RIS-UAV Networks: A DDQN-Based Trajectory and Phase Shift Optimization Approach

Reconfigurable Intelligent Surface (RIS) has grown rapidly due to its performance improvement for wireless networks, and the integration of unmanned aerial vehicle (UAV) and RIS has obtained widespread attention. In this paper, the downlink of non-orthogonal multiple access (NOMA) UAV networks equipped with RIS is considered. The objective is to optimize the UAV trajectory with RIS phase shift to maximize the system capacity under the UAV energy consumption constraint. By deep reinforcement learning, a capacity maximization scheme under energy consumption constraints based on double deep Q-Network (DDQN) is proposed. The joint optimization of UAV trajectory with RIS phase shift design is achieved by DDQN algorithm. From the numerical results, the proposed optimization scheme can increase the system capacity of the RIS-UAV-assisted NOMA networks.

Unpaired image-to-image translation of structural damage

Condition assessment of civil infrastructure from manual inspections can be time consuming, subjective, and unsafe. Advances in computer vision and Deep Neural Networks (DNNs) provide methods for automating important condition assessment tasks such as damage and context identification. One critical challenge towards the training of robust and generalizable DNNs for damage identification is the difficulty in obtaining large and diverse datasets. To maximally leverage available data, researchers have investigated using synthetic images of damaged structures from Generative Adversarial Networks (GANs) for data augmentation. However, GANs are limited in the diversity of data they can produce as they are only able to interpolate between samples of damaged structures in a dataset. Unpaired image-to-image translation using Cycle Consistent Adversarial Networks (CCAN) provide one means of extending the diversity and control in generated images, but have not been investigated for applications in condition assessment. We present EIGAN, a novel CCAN architecture for generating realistic synthetic images of a damaged structure, given an image of its undamaged state. EIGAN has the capability to translate undamaged images to damaged representations and vice-versa while retaining the geometric structure of the infrastructure (e.g, building shape, layout, color, size etc). We create a new unpaired dataset of damaged and undamaged building images taken after the 2017 Puebla Earthquake. Using this dataset, we demonstrate how EIGAN is able to address shortcomings of three other established CCAN architectures specifically for damage translation with both qualitative and quantitative measures. Additionally, we introduce a new methodology to explore the latent space of EIGAN allowing for some control over the properties of the generated damage (e.g., the damage severity). The results demonstrate that unpaired image-to-image translation of undamaged to damaged structures is an effective means of data augmentation to improve network performance.

Knowledge Distillation for Optical Flow-Based Video Super-resolution

Recently, deep learning-based super-resolution (SR) models have been used to improve SR performance by equipping preprocessing networks with baseline SR networks. In particular, in video SR, which creates a high-resolution (HR) image with multiple frames, optical flow extraction is accompanied by a preprocessing process. These preprocessing networks work effectively in terms of quality, but at the cost of increased network parameters, which increase the computational complexity and memory consumption for SR tasks with restricted resources. One well-known approach is the knowledge distillation (KD) method, which can transfer the original model’s knowledge to a lightweight model with less performance degradation. Moreover, KD may improve SR quality with reduced model parameters. In this study, we propose an effective KD method that can effectively reduce the original SR model parameters and even improve network performance. The experimental results demonstrated that our method achieved a better PSNR than the original state-of-the-art SR network despite having fewer parameters.

A Developed Compression Scheme to Optimize Data Transmission in Wireless Sensor Networks

Improving performance is an important issue in Wireless Sensor Networks (WSN). WSN has many limitations including network performance. The research question is how to reduce the amount of data transmitted to improve network performance? The work will include one of the dictionary compression methods which is Lempel Ziv Welch(LZW). One problem with the dictionary method is that the token size is fixed. The LZW dictionary method is not very useful with little data, because it loses many bytes when storing small-sized tokens. From the results obtained, the best compression ratios were in the proposed algorithm. The proposed work suggests using a dynamic size token where the tokens are classified according to their size(one byte, two bytes, or three bytes). The main idea of the proposed work is based on increasing the frequency of data to increase the compression ratio. To increase the frequency of data, the work suggests keeping the amount of incremental reading data instead of keeping the whole real data. Because the climate reading data changes very slowly, the amount of change would be frequent.

IEEE-69 Distribution Network Performance Improvement by Simultaneously Optimal Distributed Generation Sizing and Location Using PSO Algorithm

Integrated distributed generation (DG) to the network is the most popular technique to improve the network performance since DG sizing and location could reduce the power loss. However, using a non-optimal DG sizing and location could cause voltage fluctuation and power loss increase. Therefore, it is very important to develop a suitable optimization method that determines the optimal DG sizing and location. This research proposes a new strategy that leads to finding the simultaneous optimal solution involving both the optimal DG sizing and location. The proposed method aims to reduce the overall fitness function that taking into account both the voltage profile index and the power loss reduction. The particle swarm optimization (PSO) technique is the method that is used in this work. MATLAB simulations carried out on IEEE 69-bus radial distribution networks were used to prove the ability of the suggested method. The results obtained demonstrate the effectiveness of the presented method to determine the simultaneously optimal sizing and location of the DG units that minimize the overall power loss and improve the overall voltage profile.

Optimal Allocation of PV-STATCOM Devices in Distribution Systems for Energy Losses Minimization and Voltage Profile Improvement via Hunter-Prey-Based Algorithm

Incorporating photovoltaic (PV) inverters in power distribution systems via static synchronous compensators (PV-STATCOM) during the nighttime has lately been described as a solution to improve network performance. Hunter prey optimization (HPO) is introduced in this study for efficient PV-STATCOM device allocation in distribution systems. HPO generates numerous scenarios for how animals could act when hunting, some of which have been expanded into stochastic optimization. The PV-STATCOM device allocation issue in distribution networks is structured to simultaneously minimize the electrical energy losses and improve the voltage profile while accounting for variable 24 h loadings. The impacts of varying the number of installed PV-STATCOM devices are investigated in distribution systems. It is tested on two IEEE 33-node and 69-node distribution networks. The effectiveness of the proposed HPO is demonstrated in comparison to the differential evolution (DE) algorithm, particle swarm optimization (PSO), artificial rabbits algorithm (ARA), and golden search optimizer (GSO). The simulation results demonstrate the efficiency of the proposed HPO in adequately allocating the PV-STATCOM devices in distribution systems. For the IEEE 33-node distribution network, the energy losses are considerably decreased by 57.77%, and the voltages variance sum is significantly reduced by 42.84%. The energy losses in the IEEE 69-node distribution network decreased by 57.89%, while voltage variations are reduced by 44.69%. Additionally, the suggested HPO is highly consistent than the DE, PSO, ARA, and GSO. Furthermore, throughout the day, the voltage profile at all distribution nodes surpasses the minimum requirement of 95%.

A Review on Communication Protocols of Wireless Sensor Networks

Wireless Sensor Networks (WSNs) are networks of small, low-cost, low-power, and wirelessly connected sensor nodes. These sensor nodes can be distributed over a large area and can collect data about the environment, such as temperature, humidity, light, sound, vibration, and motion. WSNs are useful in a variety of applications, including environmental monitoring, smart agriculture, healthcare, industrial automation, and security. They can be used to gather data in remote or hard-to-reach locations, and they can also be used to monitor large areas continuously and in real-time. The nodes in a WSN are typically battery-powered and have limited processing and communication capabilities. Therefore, energy efficiency is a critical concern in WSNs, and the nodes are designed to conserve energy wherever possible. Proper choice of Communication protocols are essential for energy conservation in Wireless Sensor Networks (WSNs).This paper discuss about various communication protocols and its types. They help to reduce idle listening time, minimize data transmission, optimize routing, and control transmission power. By using energy-efficient communication protocols, WSNs can achieve longer network lifetime, better data accuracy, and improved network performance.

Joint Beamforming Design for RIS-Assisted Integrated Satellite-HAP-Terrestrial Networks Using Deep Reinforcement Learning

In this paper, we consider reconfigurable intelligent surface (RIS)-assisted integrated satellite high-altitude platform terrestrial networks (IS-HAP-TNs) that can improve network performance by exploiting the HAP stability and RIS reflection. Specifically, the reflector RIS is installed on the side of HAP to reflect signals from the multiple ground user equipment (UE) to the satellite. To aim at maximizing the system sum rate, we jointly optimize the transmit beamforming matrix at the ground UEs and RIS phase shift matrix. Due to the limitation of the unit modulus of the RIS reflective elements constraint, the combinatorial optimization problem is difficult to tackle effectively by traditional solving methods. Based on this, this paper studies the deep reinforcement learning (DRL) algorithm to achieve online decision making for this joint optimization problem. In addition, it is verified through simulation experiments that the proposed DRL algorithm outperforms the standard scheme in terms of system performance, execution time, and computing speed, making real-time decision making truly feasible.

IEEHR: Improved Energy Efficient Honeycomb Based Routing in MANET for Improving Network Performance and Longevity

IEEHR: Improved Energy Efficient Honeycomb Based Routing in MANET for Improving Network Performance and Longevity