Congestion Control System Research Articles

Performance Analysis of Multi-Core Systems in Multistage Interconnection Networks: Investigating Challenges in Inter-Processor Communication

For high-performance computers and data-heavy apps, how well multi-core systems work in multistage interconnection networks (MINs) is very important. As the need for parallel processing grows, inter-processor communication (IPC) has become a major issue that affects both the speed of work and the ability of the system to grow. This essay looks into the problems with IPC in multi-core systems set up with MINs, mainly delay, bandwidth limits, and network congestion. imulation-based performance review is used to test multi-core systems with different amounts of traffic, message sizes, and route techniques. A mix of mathematical models and simulation tools are used to test different MIN designs on measures like delay, speed, and fault tolerance. It is also looked at how network structures and methods for controlling crowding affect IPC efficiency. According to the results, MINs can be used to connect multiple devices, but when there is a lot of traffic, the delay goes up a lot because of bottlenecks in some parts of the network. Also, in higher-dimensional networks, processors fighting over bandwidth causes speed to drop. Some of these problems can be solved with optimized transport methods and adaptable congestion control systems, which also make IPC work better overall. This study shows how important it is to keep improving how processors talk to each other in multi-core systems, especially when it comes to making network switching and managing congestion more efficient.

Secure and transparent traffic congestion control system for smart city using a federated learning approach

This study addresses the increasing problems of traffic congestion in smart cities by introducing a Secure and Transparent Traffic Congestion Control System using federated learning. Traffic congestion control systems face key issues such as data privacy, security vulnerabilities, and the necessity for joint decision-making. Federated learning, a type of distributed machine learning, is effective because it allows for training models on decentralized data while maintaining data privacy. Furthermore, incorporating blockchain technology improves the system’s security, integrity, and transparency. The proposed system uses federated learning to securely gather and analyze local traffic data from different sources within a smart city without moving sensitive data away from its original location. This method minimizes the risk of data breaches and privacy issues. Blockchain technology creates a permanent, transparent record for monitoring and confirming decisions related to traffic congestion control, thereby promoting trust and accountability. The combination of federated learning's decentralized nature and blockchain's secure, transparent features aids in building a strong traffic management system for smart cities. This research contributes to advancements in smart city technology, potentially improving traffic management and urban living standards. Moreover, tests of the new combined model show a high accuracy rate of 97.78% and a low miss rate of 2.22%, surpassing previous methods. The demonstrated efficiency and adaptability of the model to various smart city environments and its scalability in expanding urban areas are crucial for validating its practical use in real-world settings.

TCC-HDL: A Hybrid Deep Learning Based Traffic Congestion Control System for VANET

TCC-HDL: A Hybrid Deep Learning Based Traffic Congestion Control System for VANET

Dynamic Properties of Dual-delay Network Congestion Control System Based on Hybrid Control

Dynamic Properties of Dual-delay Network Congestion Control System Based on Hybrid Control

Improved Congestion Control in Wireless Sensor Networks Using Clustering with Metaheuristic Approach

The wireless sensor network (WSN) assists an extensive range of sensor nodes and enables several real-time uses. Congestion on the WSN is based on high pocket traffic and low wireless communication capabilities under network topology. Highly loaded nodes will consume power quickly and increase the risk of the network going offline or breaking. Additionally, loss of packet and buffer overflows would result in an outcome of increased end-to-end delay, performance deterioration of heavily loaded nodes, and transport communication loss. In this paper, a novel congestion control system is proposed to diminish the congestion on network and to enhance the throughput of the network. Initially, cluster head (CH) selection is achieved by exhausting K-means clustering algorithm. After the selection of cluster head, an efficient approach for congestion management is designed to select adaptive path by using Adaptive packet rate reduction (APTR) algorithm. Finally, Ant colony optimization (ACO) is utilized for enhancement of wireless sensor network throughput. The objective function increases the wireless sensor network throughput by decreasing the congestion on network. The proposed system is simulated with (Network Simulator NS-2). The proposed K-means C-ACO-ICC-WSN attains higher throughput 99.56%, 95.62% and 93.33%, lower delay 4.16%, 2.12% and 3.11% and minimum congestion level 1.19%, 2.33% and 5.16% and the proposed method is likened with the existing systems as Fuzzy-enabled congestion control through cross layer protocol exploiting OABC on WSN (FC-OABC-CC-WSN), Optimized fuzzy clustering at wireless sensor networks with improved squirrel search algorithm (FLC-ISSA-CC-WSN) and novel energy-aware clustering process through lion pride optimizer (LPO) and fuzzy logic on wireless sensor networks (EAC-LPO-CC-WSN), respectively. Finally, the simulation consequences demonstrate that proposed system may be capable of minimizing that congestion level and improving the throughput of the network.

Developing machine learning based framework for the network traffic prediction

Network traffic analysis is a crucial step in developing efficient congestion control systems and identifying valid and malicious packets. Because network resources are apportioned based on predicted usage, these solutions reduce network congestion. For a variety of reasons, including dynamic bandwidth allocation, network security, and network planning, the ability to forecast network traffic is critical. Machine learning (ML) techniques to network traffic analysis have received a lot of interest. This article outlines an approach for analyzing network traffic. Three machine learning-based methodologies make up the methodology. The experimental investigation employed the NSL KDD data set. On the basis of accuracy and other criteria, KNN, Support vector machine, and nave bayes are compared.

Arduino Based Congestion Control System for Ambulance

Abstract: Congestion problem is a fact which contributed large impact on the transport system in the country. because many problems especially when there are emergency cases at traffic light junctions which are always busy with so many vehicles. A congestion control system is designed in order to solve all these problems. This system was designed in such a way that it should be activated when it receives a signal from an ambulance based on radio frequency (RF) transmission and uses a microcontroller to change the sequence back to the normal sequence before the emergency mode is activated. This system will lessen what often happens at the traffic light intersections because other vehicles have to gather together for giving a special route to an emergency vehicle. As a result, this project is successful and the implementation of wireless communication i.e. the radio frequency (RF) transmission in the traffic light control system for emergency vehicles like an ambulance is made possible. The main aim of this project is to design a system that is capable to identify an emergency situation in an ambulance and automatically controls the traffic at the signal. In the future, this system can be improved by controlling real traffic congestion, in fact improving the present traffic light system technology. The existing traffic control system has a lot of limitations because of its fixed time method used. The traffic signal will not alter based on the real-time traffic on road near the junction of two or more roads. Due to this, the traffic congestion cannot be controlled efficiently and the utilization of roads cannot be done to its maximum limit.

Smart cities: Fusion-based intelligent traffic congestion control system for vehicular networks using machine learning techniques

Smart cities have been developed over the past decade, and reducing traffic congestion has been the top concern in smart city development. Short delays in communication between vehicles and Roadside Units (RSUs), smooth traffic flow, and road safety are the key challenges of Intelligent Transportation Systems (ITSs). The rapid upsurge in the number of road vehicles has increased traffic congestion and the number of road accidents. To fix this issue, Vehicular Networks (VNs) have developed many new ideas, including vehicular communications, navigation, and traffic control. Machine Learning (ML) is an efficient approach to finding hidden insights into ITS without being programmed explicitly by learning from data. This research proposed a fusion-based intelligent traffic congestion control system for VNs (FITCCS-VN) using ML techniques that collect traffic data and route traffic on available routes to alleviate traffic congestion in smart cities. The proposed system provides innovative services to the drivers that enable a view of traffic flow and the volume of vehicles available on the road remotely, intending to avoid traffic jams. The proposed model improves traffic flow and decreases congestion. The proposed system provides an accuracy of 95% and a miss rate of 5%, which is better than previous approaches.

Good Learning, Bad Performance: A Novel Attack Against RL-Based Congestion Control Systems

Reinforcement Learning (RL) has been applied to solve decision-making problems in computer network designs, especially in TCP congestion control. As RL-based congestion control methods enable powerful learning abilities, it achieves competitive performance and adaptiveness advantages over the traditional methods. However, RL-based systems suffer from adversarial attacks that generate perturbations to significantly degrade the performance. In this paper, we conduct a comprehensive study of adversarial attacks against RL-based congestion control systems. Unlike the state-of-the-art adversarial attacks on images where an attacker can easily obtain the input states to introduce perturbations, the attacker cannot directly obtain the input states in congestion control settings that are only available to the agents. It is challenging to add effective perturbations without knowing the input states for RL-based congestion control models. To solve the challenge, we develop an adversarial attack to estimate states of the target agent, craft adversarial perturbations, and apply the generated perturbations in an automated fashion. We evaluate how our adversarial attack affects the target agent’s decision-making process. Our experiments illustrate that our attack can effectively reduce about 50% average throughput while increasing more than 36x latency and 45% packet loss rate.

The Application of Mental Health Teaching Method and Special Teaching Method in College Chinese Teaching under the Network Environment.

In order to improve the quality of College Chinese teaching, innovate the teaching mode, enrich the teaching content, and fundamentally improve the application and practice ability of college students so as to promote the reform of College Chinese teaching, this article briefly describes the research background of this subject, introduces the special teaching mode under the network environment, and briefly describes the basic content and practice of the special teaching method. This article mainly explores the construction of a network environment based on blockchain technology, including the construction of a blockchain framework and the application of the blockchain system. This article briefly analyzes the functional requirements of the network environment, explores the application practice of the mental health teaching method and the special subject teaching method based on the network environment, and finally studies the creation and implementation of the network environment conditions of the special subject teaching method. By creating a high-quality network environment, it provides a technical guarantee for the application and realization of special teaching method, effectively meets the needs of College Chinese teaching, and cultivates students' interest. Under the joint action of the above algorithms, the BTP congestion control system is verified by the laboratory simulation environment: it has more than 40% random packet loss resistance, the bandwidth is still available as low as 300 kbps, and the network jitter is 1200 ms. It has been proved that the mental health teaching method, the special subject teaching method, and the network environment have remarkable application effects in College Chinese teaching and are worthy of wide application and promotion.

Quality of service aware adaptive target queue length generation for active queue management

Active queue management techniques have been proposed to mitigate serious congestion issues caused by transmission control protocol flows. Active queue management controllers based on control theory are superior in terms of control performance. Such a controller utilizes a target queue length as a control input, and the congestion control system attempts to maintain the actual queue length close to the target value. However, the specific setting of the target queue length has not been discussed sufficiently. For example, raising or lowering the target queue length may increase goodput or reduce queueing delay, respectively. Therefore, the target queue length should be appropriately generated according to the required quality of services and buffer status. This paper proposes a quality of services–aware adaptive target queue length generation algorithm for an active queue management controller based on control theory. The proposed algorithm comprises two modes (loss-aware and delay-aware modes) and attempts to raise or lower the target queue length by considering the buffer status to increase the goodput or reduce the queueing delay. Simulation results revealed that the proposed algorithm could increase goodput or reduce queueing delay on each mode by adapting to the buffer status, which is in contrast to conventional methods.

Optimal Fitting Method of Nonlinear Simultaneous Equations Considering Structural Tensor Image Modeling

For the purpose of resolving the phenomenon of network congestion in the process of many-to-one communication in multimedia networks at present, the optimal fitting method of nonlinear simultaneous equations (OFMNSEs) is applied to the multimedia transmission congestion control system in this paper. The rate control and resource scheduling are effectively combined, and a clustering network structure is used to activate the congestion control method in turn based on the cluster header and intracluster-related indexes. Finally, it can be known through the analysis of the simulation results that the OFMNSE algorithm put forward in this paper can improve the congestion issue of the multimedia network transmission process and reduce the packet loss rate of data during the transmission effectively under the condition of different relative cache sizes compared with the conventional algorithm.

AIoT Enabled Traffic Congestion Control System Using Deep Neural Network

With rapid population growth in cities, to allow full use of modern technology, transportation networks need to be developed efficiently and sustainability. A significant problem in the traffic motion barrier is dynamic traffic flow. To manage traffic congestion problems, this paper provides a metho

IoT-based traffic prediction and traffic signal control system for smart city

Because of the population increasing so high, and traffic density remaining the same, traffic prediction has become a great challenge today. Creating a higher degree of communication in automobiles results in the time wastage, fuel wastage, environmental damage, and even death caused by citizens being trapped in the middle of traffic. Only a few researchers work in traffic congestion prediction and control systems, but it may provide less accuracy. So, this paper proposed an efficient IoT-based traffic prediction using OWENN algorithm and traffic signal control system using Intel 80,286 microprocessor for a smart city. The proposed system consists of ‘5’ phases, namely IoT data collection, feature extraction, classification, optimized traffic IoT values, and traffic signal control system. Initially, the IoT traffic data are collected from the dataset. After that, traffic, weather, and direction information are extracted, and these extracted features are given as input to the OWENN classifier, which classifies which place has more traffic. Suppose one direction of the place has more traffic, it optimizes the IoT values by using IBSO, and finally, the traffic is controlled by using Intel 80,286 microprocessor. An efficient OWENN algorithm for traffic prediction and traffic signal control using a Intel 80,286 microprocessor for a smart city. After extracting the features, the classification is performed in this step. Hereabout, the classification is done by using the optimized weight Elman neural network (OWENN) algorithm that classifies which places have more traffic. OWENN attains 98.23% accuracy than existing model also its achieved 96.69% F-score than existing model. The experimental results show that the proposed system outperforms state-of-the-art methods.

Global asymptotic consensus of multi-agent internet congestion control system.

This paper considers the Internet congestion control and consensus problems of a multi-agent system composed of a congested node, some aggregation nodes and their following nodes. First, a novel multi-agent Internet congestion control system with both discrete and distributed delays is proposed. Second, the stability and Hopf bifurcation of the congested node are discussed. Subsequently, a simple error controller designed for aggregation nodes, some necessary and sufficient conditions have been established to solve the bifurcation consensus problem between aggregating nodes and the congested node. Bifurcation consensus of aggregation nodes and their following nodes are also obtained through consensus protocols which based on a novel predictive controller. So far, the bifurcation asymptotically consensus of multi-agent Internet congestion control system is achieved. It is worth noting that conditions for global stability of system can be obtained by selecting appropriate control parameters, and conclusions of global asymptotic stability consensus is given to draw conditions for avoiding network congestion in the whole system. Finally, numerical examples illustrated the correctness and validity of the main results.

Optimal Routing based Load Balanced Congestion Control using MAODV in WANET Environment

A decentralized sort of network that can allow the nodes to communicate with them lacking any central controller is Wireless Ad hoc Networks (WANET). Network Congestions can befall on account of nodes' restricted Bandwidth (BW) together with dynamic topology. Network Congestions brings about data loss as it makes the Data Packets (DP) be dropped on the network. Therefore, in order to lessen Network Congestions, it is necessary to model Congestion Control (CC) systems aimed at the WANET. Thus, this paper offers an optimal routing centered CC scheme utilizing the Modified Ad hoc on-demand Distances Vector (MAODV) Routing Protocol (RP) aimed at the WANET. Here, primarily, the Source Node (SN) together with Destination Nodes (DN) is initialized, and after that, the MAODV discovers the multiple routing paths. Subsequently, Stochastic Gradients Descent Deep Learning Neural Network (SGD-DLNN) identifies the Congestion Status (CS) of every node in the discovered paths. In addition, the MAODV allocates the traffic over the optimum congestion-free routing path if congestion befalls. The Levy Flight Based Black Widow Optimization (LF-BWO) algorithm chooses the optimal routing paths as of congestion-free paths. Centered upon path lifetime, residual energy, link cost, together with path distance, this algorithm enhances the Data Transmission (DT) performance by means of discovering a path. The experimentation’s outcomes are rendered to exhibit the proposed RP’s effectiveness.

BCOOL: A Novel Blockchain Congestion Control Architecture Using Dynamic Service Function Chaining and Machine Learning for Next Generation Vehicular Networks

This paper presents the first, novel, dynamic, resilient, and consistent Blockchain COngestion ContrOL (BCOOL) system for vehicular networks that fills the gap of trustworthy Blockchain congestion prediction systems. BCOOL relies on the heterogeneity of Machine Learning, Software-Defined Networks and Network Function Virtualization that is customized in three hybrid cloud/edge-based On/Offchain smart contract modules and ruled by an efficient and reliable communication protocol. BCOOL’s first novel module aims at managing message and vehicle trustworthiness using a novel, dynamic and hybrid Blockchain Fog-based Distributed Trust Contract Strategy (FDTCS). The second novel module accurately and proactively predicts the occurrence of congestion, ahead of time, using a novel Hybrid On/Off-Chain Multiple Linear Regression Software-defined Contract Strategy (HOMLRCS). This module presents a virtualization facility layer to the third novel K-means/Random Forest-based On/Off-Chain Dynamic Service Function Chaining Contract Strategy (KRF-ODSFCS) that dynamically, securely and proactively predicts VNF placements and their chaining order in the context of SFCs w.r.t users’ dynamic QoS priority demands. BCOOL exhibits a linear complexity and a strong resilience to failures. Simulation results show that BCOOL outperforms the next best comparable strategies by 80% and 100% reliability and efficiency gains in challenging data congestion environments. This yields to fast, reliable and accurate congestion prediction decisions, ahead of time, and optimizes transaction validation processing time. Globally, the Byzantine resilience, complexity and attack mitigation strategies along with simulation results prove that BCOOL securely predicts the congestion and provides real-time monitoring, fast and accurate SFC deployment decisions while lowering both capital and operational expenditures (CAPEX/OPEX) costs.

Stop-and-Go: Exploring Backdoor Attacks on Deep Reinforcement Learning-Based Traffic Congestion Control Systems

Recent work has shown that the introduction of autonomous vehicles (AVs) in traffic could help reduce traffic jams. Deep reinforcement learning methods demonstrate good performance in complex control problems, including autonomous vehicle control, and have been used in state-of-the-art AV controllers. However, deep neural networks (DNNs) render automated driving vulnerable to machine learning-based attacks. In this work, we explore the backdooring/trojanning of DRL-based AV controllers. We develop a trigger design methodology that is based on well-established principles of traffic physics. The malicious actions include vehicle deceleration and acceleration to cause stop-and-go traffic waves to emerge (congestion attacks) or AV acceleration resulting in the AV crashing into the vehicle in front (insurance attack). We test our attack on single-lane and two-lane circuits. Our experimental results show that the backdoored model does not compromise normal operation performance, with the maximum decrease in cumulative rewards being 1%. Still, it can be maliciously activated to cause a crash or congestion when the corresponding triggers appear.

Deep learning-based urban big data fusion in smart cities: Towards traffic monitoring and flow-preserving fusion

ObjectiveIn the last few years, several techniques and models are used for retrieving significant information from urban big data of smart cities. This research work aims at developing a data fusion-based traffic congestion control system in smart cities using a deep learning model. MethodologyA hybrid model based on the convolution neural network (CNN) and long short term memory (LSTM) architectures are used for region-based traffic flow predictions in smart cities. CNN is used for the classification of spatial data while LSTM for temporal data. ConclusionThe experiments used the CityPulse Traffic and CityPulse Pollution datasets, and measured root mean square error (RMSE), time consumption and accuracy. A small RMSE value of 49 and highest accuracy of 92.3% compared to other baseline models depicts the applicability of the proposed model in the region-based traffic flow prediction problems in the smart cities.

Sudden Transition from Equilibrium to Hybrid Chaos and Periodic Oscillations of the State-Dependent Round-Trip Delayed Nonsmooth Compound TCP with GRED Congestion Control System via HB-AFT

In this paper, the nonsmooth compound transmission control protocol (TCP) with the gentle random early detection (GRED) system with the state-dependent round-trip delay is investigated in detail. Uniqueness of the positive equilibrium is proved firstly. Then, the closed approximate periodic solutions in this state-dependent delayed nonsmooth compound TCP with the GRED model are obtained by employing the harmonic balance and alternating frequency/time domain (HB-AFT) method. Then, we compare the results generated by numerical simulations with those of the closed approximate expressions obtained by HB-AFT. It indicates that HB-AFT is simple, correct, and powerful for state-dependent delayed nonsmooth dynamical systems. Finally, we find the complicated dynamic: chaos. It is a grazing chaos with a hybrid property, i.e., where usually w oscillates at a very low frequency and q oscillates at a very high frequency. And, the route to chaos is a very rare route, i.e., the instantaneous and local transition of stable equilibrium to chaos. So, to the end of stability and good performance, we should adjust the parameters carefully to avoid the periodic and chaotic oscillations.