Search

Traffic congestion in urban areas poses several challenges to municipal authorities including pollution, productivity loss, reckless driving, and delays in dealing with emergencies. Smart cities can use modern IoT infrastructure to solve the congestion problem and reduce pollution and delays. In this article, we focus on congestion mapping and mitigation for emergency vehicles in smart cities. We use a novel traffic light control technique to change the flow of cars on lights of interest thereby making way for emergency vehicles. We use a simulation model for a selected area of Manhattan to implement congestion mapping and to help find the fastest path for routing emergency vehicles based on the congestion metrics. The system controls traffic lights to block off the roads feeding into congestion and allows flow away from the congested path. This helps in clearing the preferred route to help emergency vehicles reach the destination faster. We show that the proposed algorithm can map congestion on city roads with accuracy thus helping to improve the response time of the emergency services and saving precious lives. [ABSTRACT FROM AUTHOR]

In Wireless Sensor Networks (WSNs), congestion control is essential for ensuring effective data transfer and extending the network's lifetime. When combining Reinforcement learning with Ant Colony Optimization (ACO) for congestion control in clustered WSNs, the strategy usually makes use of both methods' advantages to improve data routing and control traffic load. This research presents a novel approach named Adaptive Rendezvous based Congestion Control (ARCC) for congestion control by selecting the rendezvous nodes as Cluster Head (CH) using ACO integrated with Reinforcement learning model. By optimizing energy consumption, lowering congestion, and enhancing data transmission dependability overall, the proposed strategy aims to improve network performance. [ABSTRACT FROM AUTHOR]

Named data networking (NDN) is a novel networking paradigm characterized by in-network caching, receiver-driven communication, and multi-source, multi-path data retrieval, which poses new challenges for congestion control. Existing work has largely focused on receiver-driven mechanisms. Due to delays in obtaining network control information (timeouts, NACKs) within NDN, consumers are unable to access the network congestion status from this information in a timely manner. To address the issues above, this paper combines the Q-learning algorithm with the NDN architecture, proposing Q-NDN. In Q-NDN, consumers can dynamically adjust the congestion window (cwnd) through the real-time monitoring of network status, leveraging the Q-learning algorithm, achieving automatic congestion control for the NDN architecture. Additionally, this paper introduces content popularity-based traffic scheduling for multi-user scenarioswhich adjusts the transmission rates of content with different popularity levels to maintain a dynamic balance in the network. The experimental results show that Q-NDN can converge quickly, make full use of bandwidth resources, and keep the packet loss rate to 0 in the basic network topology. In competing network topologies, Q-NDN can rapidly address conflict issues, efficiently utilize bandwidth resources, and maintain a relatively low packet loss rate. [ABSTRACT FROM AUTHOR]

In order to improve network performance, traffic management is imperative. In addition to increasing the volume of network data, software-defined networks have expanded and the amount of information exchanged between the data plane and the control plane has increased. This will lead to congestion and reduce network efficiency because more traffic will flow through these networks. Congestion in these networks can be controlled effectively with switch migration. A mechanism that provides congestion control through the virtual migration of switches is presented, known as Virtual Network Request Load Balancing Profit (VNR_LBP). It is a problem to have many requests at a switch node, and to solve it, there is an effective solution. Network virtualization allows the controller to migrate switches into this space by taking advantage of available resources in switches and links. In order to control congestion, we have calculated the profit function of nodes and links to determine how much congestion exists. We also request a virtual network (VNR) to reduce load and manage resources. Lastly, the proposed method was evaluated using NS2 simulator according to various criteria. Simulated results show that in comparison with the basic method, the proposed method increases throughput by about 4.3%, decreases delay by about 5.3%, and reduces the average cost by 26%. [ABSTRACT FROM AUTHOR]

Wireless multimedia sensor networks (WMSNs) have stringent constraints and need to deliver data packets to the sink node within a predefined limited time. However, due to congestion, buffer overflow occurs and leads to the degradation of the quality-of-service (QoS) parameters of event information. Congestion in WMSNs results in exhausted node energy, degraded network performance, increased transmission delays, and high packet loss. Congestion occurs when the volume of data trying to pass through a network exceeds its capacity. First, the BOCC protocol uses two congestion indicators to detect congestion. One is the buffer occupancy and other is the buffer occupancy change rate. Second, a rate controller is proposed to protect high-priority I-frame packets during congestion. BOCC sends a congestion notification to the source node to reduce congestion in the network. The source node adjusts its data transmission rate after receiving the congestion notification message. In the proposed algorithm, the rate adjustment is made by discarding low-priority P-frame packets from the source nodes. Third, to further improve the performance of the BOCC protocol, the problem is formulated as a constrained optimization problem and solved using convex optimization and sequential quadratic programming (SQP) methods. Experimental results based on Raspberry Pi sensor nodes show that the BOCC protocol achieves up to 16% reduction in packet loss and up to 23% reduction in average end-to-end delay compared to state-of-the-art congestion control algorithms. [ABSTRACT FROM AUTHOR]

Efficient congestion control has always been a critical challenge in the field of datacenter networks. Accurate measurement of Round Trip Time (RTT) is the cornerstone of RTT-based reactive congestion control algorithms. Based on Swift congestion control algorithm, this paper proposes Gyration, a packet deflection congestion control algorithm based on RTT measurement. Gyration incorporates the deflection packet delay into the calculation of RTT, thereby augmenting the RTT calculation with the measurement of deflection delay. This approach enables a more accurate assessment of network congestion conditions. Experimental results demonstrate that compared to Swift, under heavy load traffic patterns such as Cache Follower, Data Mining, Web Search, and Web Server, Gyration achieves a reduction in flow completion time FCT by 20%, 80%, 13%, and 60%, respectively, and an increase in throughput by 38%, 6%, 15%, and 2%, respectively. This signifies that Gyration provides more timely and precise congestion control for datacenter networks, effectively mitigating congestion issues within these networks. [ABSTRACT FROM AUTHOR]

In contemporary datacenter networks, various applications experience the challenge of incast occurrences. Data-intensive applications, particularly in distributed scenarios such as distributed deep learning, frequently encounter incast. While single-path transport protocols are widely deployed in datacenter networks, the available bandwidth is often severely underutilized. MP-RDMA, as a state-of-the-art multi-path transport protocol, has been implemented; however, it faces performance issues during large-scale incast communications. MP-RDMA employs insufficient congestion feedback and fixed rate adjustment for congestion management, making the scheme hardly scalable. In this paper, we introduce MPTD, an RTT-based multi-path transport protocol. MPTD encompasses two primary aspects: (1) a novel congestion control algorithm based on the setting of target delay; (2) an optimized packet scheduling mechanism. Specifically, the receiver dynamically updates the target delay in real-time based on network conditions, and the sender adjusts the sending rate accordingly. A categorized implementation for paths is added to achieve a more accurate identification of path characteristics. Our evaluation demonstrates that, in comparison to MP-RDMA, MPTD can achieve speedups of 1.35x/1.40x in flow completion time for two traffic patterns. [ABSTRACT FROM AUTHOR]

Wireless networks, especially 5G and WiFi networks, have made great strides in increasing network bandwidth and coverage over the past decades. However, the mobility and channel conditions inherent to wireless networks have the potential to impair the performance of traditional Transmission Control Protocol (TCP) congestion control algorithms (CCAs). Google proposed a novel TCP CCA based on Bottleneck Bandwidth and Round-Trip propagation time (BBR), which is capable of achieving high transmission rates and low latency through the estimation of the available bottleneck capacity. Nevertheless, some studies have revealed that BBR exhibits deficiencies in fairness among flows with disparate Round-Trip Times (RTTs) and also displays inter-protocol unfairness. In high-speed wireless networks, ensuring fairness is of paramount importance to guarantee equitable bandwidth allocation among diverse traffic types and to enhance overall network utilization. To address this issue, this paper proposes a BBR–Pacing Gain (BBR–PG) algorithm. By deriving the pacing rate control model, the impact of pacing gain on BBR fairness is revealed. Adjusting the pacing gain according to the RTT can improve BBR's performance. Simulations and real network experiments have shown that the BBR–PG algorithm retains the throughput advantages of the original BBR algorithm while significantly enhancing fairness. In our simulation experiments, RTT fairness and intra-protocol fairness were improved by 50% and 46%, respectively. [ABSTRACT FROM AUTHOR]

Abstract 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.

Mobile Opportunistic Networks (MONs) are characterized by frequently changing network topologies and intermittent connectivity due to nodes’ limited communication range. These dynamics often lead to constrained buffer resources, causing excessive message drops and inefficient replication strategies, which in turn result in high overhead and performance degradation from buffer congestion and head-of-line blocking. Existing replication-based routing schemes fail to account for these limitations, particularly in considering the impact of contact duration on network performance. In this paper, we develop a congestion avoidance mechanism that addresses these issues by modeling contact duration using a lognormal distribution, derived from both real-world mobility traces and synthetic mobility models. Our approach includes the prediction and detection of buffer congestion, the calculation of optimal congestion window sizes, and the design of an efficient message scheduling algorithm to minimize buffer occupancy and prevent packet drops. This mechanism is applicable to both homogeneous and heterogeneous contact networks. Simulation results on synthetic and real-world mobility traces demonstrate that our proposed scheme significantly reduces overhead while enhancing delivery performance, outperforming existing approaches. [ABSTRACT FROM AUTHOR]

In the rapidly evolving landscape of the Internet of Vehicles, optimizing data trustworthiness and congestion control has emerged as a pivotal challenge. To address this challenge, this research proposes a novel approach that synergistically integrates the Adaptive Particle Convergence Optimization algorithm with blockchain-based architecture. The objective is to strike a balance between ensuring trustworthy data exchange and efficient communication within the Internet of Vehicles network. The proposed approach begins with a thorough investigation of the Internet of Vehicles intricacies, highlighting the critical need for optimized parameters to simultaneously enhance data trust and alleviate congestion. The proposed approach’s unique features, including dynamic convergence threshold adaptation, velocity scaling, and adaptive inertia weight, empower the algorithm to efficiently navigate the complex solution space. To validate the approach, a comprehensive simulation environment is established. Realistic traffic data is generated to emulate vehicular movement, while the Ethereum blockchain with Geth 1.10.4 client is employed to construct a private blockchain for data trust and security. The proposed model achieves a data trust level of 0.85, a congestion rate of 0.10, a communication overhead of 7.5 ms, and a successful data sharing rate of 88% by effectively optimizing parameters and fostering equilibrium between data trustworthiness and congestion control. Comparative analyses against other state-of-the-art methods underscore its superiority across diverse performance metrics. This research not only contributes to the field of the Internet of Vehicle but also paves the way for efficient, secure, and trustworthy vehicular communication networks. [ABSTRACT FROM AUTHOR]

This work is the first part of a large bibliographic review of active queue management algorithms of the Random Early Detection (RED) family, presented in the scientific press from 1993 to 2023. The third part will provide data on algorithms published from 2016 to 2023.

Summary: With the continuous expansion scale of data center networks (DCNs), the probability of network failures becomes high. Trustworthy fault‐tolerant routing is extremely significant for reliable communication in data centers. In this article, we tackle the challenge by proposing a novel fault‐tolerant routing scheme for a torus‐based DCN. First, we present a multipath information transmission model based on the trust degree of reachable paths and propose a novel Hamiltonian odd–even turning model without deadlock. Second, we design an efficient deadlock‐free fault‐routing algorithm by constructing the longest fault‐free path between any two fault‐free nodes in DCN. Extensive simulation results show that the proposed fault‐tolerant routing outperforms the previous algorithms. Compared with the most advanced fault‐tolerant routing algorithms, the proposed algorithm has a 21.5% to 25.3% increase in throughput and packet arrival rate. Moreover, it can reduce the average delay of 18.6% and the maximum delay of 23.7% in the network respectively. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As network technology continues to advance, network congestion has become an inevitable aspect of network communication. Considering the external interference, unmodeled uncertainty and the interaction between nodes, a multi-bottleneck TCP/AWM network model is established in this paper. A new fixed-time congestion controller was designed by combining a neural network and the backstepping technique. The neural network approximation property is used to eliminate the interference of unmodeled uncertainty and UDP flow in the system. The controller designed in this paper can ensure the stability of the TCP/AWM closed-loop system in a fixed time. Finally, the simulation results demonstrate the effectiveness of the proposed TCP/AWM controller. [ABSTRACT FROM AUTHOR]

Summary: Wireless Sensor Networks (WSNs) find applications in diverse fields such as environmental monitoring, healthcare, and military surveillance. Nonetheless, one of the primary challenges encountered by WSNs is congestion. Congestion arises in WSNs when there is a high volume of traffic on the network, leading to significant repercussions. These repercussions encompass packet loss, heightened latency durations, and diminished network efficiency. This paper presents an innovative congestion control mechanism named Dual Indicator Random Early Detection (DIRED). DIRED leverages two indicators, namely queue length and packet loss rate, to dynamically adjust the dropping probability of packets, thereby mitigating congestion and enhancing network performance. For the successful execution of the DIRED model, a congestion control algorithm is introduced. This strategy efficiently prevents the deterioration of network performance that can commonly arise from extremely low packet drop probabilities. Simulations are conducted to evaluate the proposed DIRED model, comparing it with the KACO and KFOA techniques. The results demonstrate that DIRED outperforms KACO and KFOA in terms of network performance, achieving a more optimal balance between performance metrics and packet‐dropping probability. [ABSTRACT FROM AUTHOR]

Congestion Control (CC) is a fundamental mechanism to achieve effective and equitable sharing of network facilities. As future networks evolve towards more complex paradigms, traditional CC methods are required to become more powerful and reliable. On the other hand, Machine Learning (ML) has become increasingly popular for solving challenging and sophisticated problems, and scientists have started to turn their interest from rule-based approaches to ML-based methods. This paper employs machine learning models to con- struct a performance evaluation scheme to predict network metrics for the Self-Clocked Rate Adaptation for Multimedia (SCREAM) algorithm. It uses a rigorous data preprocessing pipeline and a systematic application of ML methods to enhance the performance of the regression model for SCReAM's performance metrics. Also, we constructed a dataset that pro- vides SCREAM's input parameters and output metrics, such as network queue delay, smoothed Round Trip Time (sRTT), and network throughput. Each prediction process has several phases: choosing the best initial regressor model, hyperparameter tuning, ensemble learning, stacking regressors, and utilizing the holdout data. Each model's performance was evaluated through various regression metrics; this study will mainly focus on the coefficient of determination (R2) score. The improvement between the initial best-selected model and the final improved model determined that we were able to increase R2 up to 96.64% for network throughput, 99.4% for network queue delay, and 100% for sRTT. [ABSTRACT FROM AUTHOR]

The comprehensive performance and user experience of large-scale distributed video conference systems are constrained by network traffic, and conventional network services are difficult to ensure the stability and reliability of the above data transmission activities. This article combines conference video transmission and congestion control related technologies to propose a conference video traffic prediction model based on the large neural network GRU algorithm, and constructs a large-scale distributed video conference transmission congestion control mode on this basis. The simulation experiments on the real-time congestion control model of research results show that it effectively avoids system fluctuations and significantly improves the user experience, providing a feasible method for improving the comprehensive performance of large-scale distributed video conference systems. [ABSTRACT FROM AUTHOR]

For remote health monitoring, activity tracking, and other applications in healthcare such as sports, Wireless Body Area Networks (WBANs) have become a feasible technology. However, the limited resources and dynamic nature of WBANs pose significant challenges to designing efficient and reliable routing protocols. To address these challenges, the proposed work suggests a thermal-aware, energy-efficient, and congestion-aware routing protocol (TECRP) for WBAN. TECRP focuses on improving transmission in both inter-WBAN and intra-WBAN scenarios. It addresses three key Quality of Service (QoS) parameters: energy efficiency, node temperature, and congestion, aiming to enhance overall WBAN communication efficiency. To achieve all these parameters, the algorithm is considered a multi-objective problem. The analysis shows that the temperature rises and delay increases with the number of data transmission, but the multi-objective approach helps to mitigate such effects. The result analysis shows that the path loss values fluctuate with increasing data transmission and network traffic. But the temperature rise increases with more data transmission and larger packets. On the other hand, the Packet Delivery Ratio (PDR) decreases with an increase in data transmission and with larger packet sizes. This shows that with higher congestion ratios, a higher likelihood of packet loss is seen. But in overall performance, the proposed TECRP shows better efficiency and congestion management as compared to other existing state-of-art-models and achieves high PDR, and minimizes packet loss. The proposed approach shows 0.42% improvement in energy efficiency as compared to existing approaches. [ABSTRACT FROM AUTHOR]

Wireless Sensor Networks (WSN) have been broadly applied in various fields, such as medicine and agriculture. A network is likely to experience information congestion when many sensors initiate sending data concurrently. This could lead to maximizing in the packet loss ratio, thereby reducing efficiency and affecting the total system performance, so congestion control is an utmost challenge. To solve this problem, a Fuzzy Congestion Control in WSN based on the Spider Monkey Optimization Algorithm (FCC-WSN-SMOA) is proposed. The proposed method combines random early detection with the fuzzy proportional integral derivative controller. The proportional integral derivative (PID) and fuzzy logic conjointly together to help control the target buffer queue. FLC regulates the transmitting rate of every node. Then, FLC input and output parameters are optimized by SMOA. The simulation is activated in MATLAB. The FCC-WSN-SMOA method attains 21.28%, 32.20%, and 17.42% lower packet loss ratio and 16.25%, 26.07%, and 23.38% lower packet loss probability compared with existing methods, such as progressive fuzzy PSO-PID congestion control approach for WSN (FCC-WSN-PSO), optimized fuzzy clustering utilizing moth-flame optimization approach in WSNs (FCC-WSN-MFOA), and time synchronization depending on Improved Wolf Colony Algorithm-Cuckoo Search Optimized Fuzzy PID Controller for Smart Grid (FCC-WSN-IWCA-CSO), respectively. [ABSTRACT FROM AUTHOR]

In wireless sensor networks, the expensive and scarce resources are energy and frequency spectrum. To overcome this scarcity of spectrum, cognitive radio has been introduced in WSNs. The licensed band is utilized by the primary users in cognitive radio whereas the secondary users can use the licensed channels. For improving the network lifetime, overall network scalability, and energy consumption, the clustering technique is used to group the sensor nodes into clusters. Clustering algorithms must be energy efficient because of the difficulties in replacing or recharging the batteries of nodes. While designing the algorithms, more constraints result in the clustering for CRSN as the dynamic spectrum access has been addressed. We propose an energy-efficient fuzzy clustering and congestion control algorithm (EFCCA) in this paper to improve energy efficiency. With the consideration of spectrum availability, queue length, and residual energy, the election of cluster head contributes to the energy efficiency of the algorithm. The active Queue Management algorithm is used to monitor and control the congestion rate. The proposed EFCCA's performance evaluates with the help of comparison with other clustering methods and it shows enhanced performance in energy efficiency and lifetime based on the outcomes of experimental investigation. [ABSTRACT FROM AUTHOR]

AI large model is leading the hot ICT(information and communications technology) industry in the next decade. Intelligent computing center network is a communication base to support the distributed training of AI large model, and it is one of the key factors to determine the efficiency of AI clusters. The data volume and the number of parameters of AI large model are expanding continuously, which brings the network of intelligent computing centers serious challenges, and also brings an opportunity for intergenerational innovation of key network technologies. In the process of AI large model training and inferencing, providing high performance and high security transmission of data are the two core requirements of AI business for intelligent computing network. Efficient load balancing, congestion control technologies and network security protocols are the key network technologies. To address the challenge brought by large-scale AI business, global scheduling ethernet (GSE) was proposed as a corresponding solution, and realistic test environment was built to compare the performance of GSE and RoCE. The test results show that GSE significantly improves JCT compared with RoCE network.

This work is the second part of a large bibliographic review of active queue management algorithms of the Random Early Detection (RED) family, presented in the scientific press from 1993 to 2023. This part provides data on algorithms published from 2006 to 2015.

Summary: Recently, wireless sensor networks (WSNs) have been used for monitoring, sensing, processing, and communication purposes in real‐time applications. It is employed with a routing protocol that performs an effective data transmission process. However, while transmitting large data, there occurs an over fitting issue, which leads to determining a huge data leakage. Also, the delay is increased with heavy congestion in the network. Hence, a novel method is proposed to diminish the network congestion regarding distributed networks as well as cloud edge computing. Moreover, it diminished the data loss from an overloaded condition. However, the proposed technique controls congestion that resists the traffic in the network through lightweight, ultra‐dense label‐less federation and incorporates adaptive multi‐agent Markov reinforcement learning. Furthermore, a distributed energy‐efficient delay‐aware routing protocol is employed to analyze and regulate congestion control in the network. Also, it varies the network dynamically by adjusting the routing protocol that optimizes the congestion and implements the traffic mechanism. Moreover, the congestion in WSNs overwhelms the nodes and channels distributed in the packets. The evaluation of the proposed method is determined by various metrics such as queuing delay, network lifetime, energy efficiency, throughput, and packet delivery ratio. The experimental results revealed that the proposed method attained an enhanced performance by maximizing energy efficiency and packet delivery ratio by 94% as well as 89% and reducing the delay by 55%, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Traffic modeling is crucial for designing and evaluating active queue management (AQM) methods used in network routers to control congestion. The Bernoulli process (BP), commonly used to model the traffic, falls short in capturing the burstiness of Internet traffic. Besides, the Markov Modulated Bernoulli Process (MMBP) with multiple states and varying probabilities allows the determination of each state's load independently but does not set specific overall traffic loads. This limitation hinders the establishment of a baseline for evaluating AQM methods. To address these issues, this paper introduces an enhanced traffic modeling approach using the stationary distribution of the Markov Modulated Bernoulli Process (MMBP-SD). This new model calculates the stationary distribution to match the required traffic load while varying its burstiness, enabling a fair comparison with the Bernoulli process of a predefined traffic load and facilitating the assessment of AQM behaviors. The proposed approach was tested under various traffic loads and evaluated using the burstiness factor (BF) and the maximum burstiness duration (MBD). The results showed that the MMBP-SD improved the BF by 6.2% and the MBD by 118% compared to the BP. Evaluating Random Early Detection (RED) was conducted using MMBP-SD and based on delay, loss, and packet dropping. This evaluation revealed that the RED performance in terms of packet loss degrades when using a 4-state MMBP-SD (e.g., packet loss increased by 28.5%) as RED maintains the same dropping rate as in the single-state model, highlighting a limitation of the RED method. [ABSTRACT FROM AUTHOR]

Reinforcement Learning (RL) has gained significant momentum in the development of network protocols. However, RL-based protocols are still in their infancy, and substantial research is required to build deployable solutions. Developing a protocol based on RL is a complex and challenging process that involves several model design decisions and requires significant training and evaluation in real and simulated network topologies. Network simulators offer an efficient training environment for RL-based protocols because they are deterministic and can run in parallel. In this article, we introduce RayNet, a scalable and adaptable simulation platform for the development of RL-based network protocols. RayNet integrates OMNeT++, a fully programmable network simulator, with Ray/RLlib, a scalable training platform for distributed RL. RayNet facilitates the methodical development of RL-based network protocols so that researchers can focus on the problem at hand and not on implementation details of the learning aspect of their research. We developed a simple RL-based congestion control approach as a proof of concept showcasing that RayNet can be a valuable platform for RL-based research in computer networks, enabling scalable training and evaluation. We compared RayNet with ns3-gym, a platform with similar objectives to RayNet, and showed that RayNet performs better in terms of how fast agents can collect experience in RL environments. [ABSTRACT FROM AUTHOR]

The congestion management mechanism is essential to manage the explosive evolution of data traffic associated with advanced applications and services in the 5G system. As a result, we suggest a novel methodology to manage congestion for mobile edge computing in the 5G system. Furthermore, the proposed model enhances delay, energy consumption, and throughput. The enhanced random early detection strategy and the K-means approach are used in the suggested model to execute this. Also, a virtual list is realized to maintain packet information and suit more packets. The proposed model is realized in NS2 green cloud simulator. In comparison with the traditional cloud model and the fog computing model, the simulation results confirm that the proposed model reduces delay, boosts throughput, and decreases energy consumption. [ABSTRACT FROM AUTHOR]

The Transmission Control Protocol (TCP) serves as a cornerstone mechanism for implementing Congestion Control (CC) across the Internet. Designing a solution that provides high bandwidth utilization and mitigates the phenomenon of bufferbloat across a spectrum of diverse scenarios poses a considerable challenge. The introduction of Bottleneck Bandwidth and Round Trip propagation time (BBR) in 2016 marked a significant shift in congestion control methodology. Its improved performance and adaptability contributed to the initial acclaim and widespread interest that it received.. Unlike most currently used CCs, it operates around Kleinrock's optimal point, thus offering high throughput even in lossy networks while preventing buffer saturation. Unfortunately, it quickly became evident that BBR was unable to fairly share bandwidth with flows characterized by different path delays, as well as loss-based CCs. In response, Google recently introduced a third iteration to address these shortcomings. This study explores the performance of BBRv3 across a wide range of scenarios, thereby considering different buffer sizes and paths with varying Round Trip Times (RTTs), and it evaluates its superiority over its predecessors. Through extensive simulations, this work assesses whether BBRv3 can finally play fair with other bandwidth contenders, which is a critical consideration given the widespread deployment of BBR. The framework is publicly available to facilitate additional validation and ensure the reproducibility of the study's findings. The results indicate that while BBRv3 demonstrates enhanced fairness towards loss-based CC algorithms, it struggles when competing against other BBR flows, especially in multi-RTT networks, thus falling short even when compared to the initial version. [ABSTRACT FROM AUTHOR]

This paper proposes a new H ∞ static output feedback control method to address the congestion control problem in transmission control protocol networks using active queue management routers. Based on linear matrix inequality optimization, this method determines a static output feedback control law to minimize the H ∞ norm of the transfer function between the controlled queue length of the buffer and the exogenous disturbance affecting the available link bandwidth. A linear matrix inequality formulation is presented as a sufficient condition to guarantee the closed-loop system's asymptotic stability while maintaining disturbance rejection within a specified level, regardless of round-trip time delays. The proposed robust static output feedback control eliminates the need to measure or estimate all system states, thus simplifying practical implementation. The effectiveness of the proposed design method is demonstrated by applying it in a practical process, as illustrated through a numerical example. [ABSTRACT FROM AUTHOR]

Vehicular networks are the key paradigm of the Internet of Vehicles (IoV) as the extension of the Internet of Things (IoT) notion in Intelligent Transportation Systems (ITS) which can assist in the development of autonomous driving in smart cities. This technology can provide a wide variety of onboard data services, such as road safety, and increase traffic efficiency by connecting vehicles with road infrastructure and pedestrians. However, it is a challenging task to provide a satisfactory quality of service (QoS) to this network due to a number of limiting factors such as resource collision, resource interference, and congested channels because of the network topology and rapid changes produced by the high mobility as well as hardware imperfections and the anticipated growth of vehicular network devices. As a result, it will be essential to ensure that the resources of the available cellular network are allocated and used in the most efficient possible way. To achieve these goals, 3GPP has standardized the cellular vehicle to everything (C-V2X) with two versions, the long-term evolution-V2X (LTE-V2X) in Release 14 and the new radio-V2X (NR-V2X) in Release 16, as prominent technologies to improve resource allocation for vehicular networks. In order to capture the continuous effort for improving resource allocation, we present a systematic literature review (SLR) on distributed resource allocation (DRA) schemes for the two cellular-based vehicular network technologies. First, we discuss the technical configuration of resource allocation in the light of LTE-V2X and NR-V2X technologies and classify the state-of-the-art for each technology. Afterward, we explain the impact of machine learning (ML) and congestion control (CC) on the DRA. Then, we point out the primary performance metrics and simulation tools that were used in the related work. Ultimately, we highlight the challenges, open issues, and opportunities for DRA in C-V2X and outline several promising future research directions. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunications Science is the property of Beijing Xintong Media Co., Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The emergence of online education platforms, driven by interactive mobile technology, has significantly reshaped traditional educational paradigms and underscored the critical need for advanced analysis and improvement of student interactions. Effective analysis of student interaction is crucial for enhancing teaching quality and optimizing the learning experience in these digitally enriched environments. Traditional analysis frameworks often face challenges such as inaccuracies in anomaly detection and inefficiencies in data handling, particularly when handling extensive datasets typical of online platforms. This study introduces a novel approach to enhancing student interaction analysis systems by leveraging the synergy between machine learning and advanced interactive mobile technologies. Initially, the study proposes an advanced anomaly detection method tailored for identifying irregular student interactions. This method utilizes a blend of machine learning algorithms and the real-time data processing capabilities of mobile technology. Furthermore, to address the complexities of data transmission in mobile-based online education ecosystems, a state-of-the-art congestion control algorithm has been developed. This algorithm optimizes data flow, significantly enhancing transmission stability and efficiency. The integration of interactive mobile technology with machine learning offers a robust and dynamic framework for analyzing student interactions, thereby facilitating a more engaging and effective online educational experience. This research contributes to the advancement of online education quality and efficiency by emphasizing the role of interactive mobile technology in shaping future learning environments. [ABSTRACT FROM AUTHOR]

The ever-growing need for seamless data transmission in wireless networks indicates a significant requirement for efficient congestion control mechanisms. Conventional congestion control approaches suffer major drawbacks due to low responsiveness, primarily owing to the inherently dynamic and unpredictable environment of wireless networks. Static parameters characterize these traditional methods, making them unable to adapt to real-time network dynamics, and hence their performances turn out to be suboptimal. In this regard, presented are non-traditional approaches from innovation in the Bacterial Foraging Optimizer (BFO) model that synergizes the ensemble classification method with aid from Multilayer Perceptron (MLP) and Logistic Regression (LR), and QLearning for path optimization. The BFO, influenced by the foraging behavior of Escherichia coli bacteria, dynamically determines distinct paths within a network, effectively bypassing congested routes. The bioinspired algorithm, by mechanisms of chemotaxis, reproduction, and elimination-dispersal, efficaciously scours through the search space and effectively finds good network paths, surpassing static routing approaches. Meanwhile, the ensemble classification strategy comprising MLP and LR predicts network congestion by considering a range of features, such as path length, traffic load, and historical congestion data samples. This integrated approach strengthens congestion prediction accuracy as a result of integrating the strengths of individual classifiers and mitigating their respective weaknesses. On top of that, the implementation of Q-Learning for real-time path optimization is another major innovation, where an optimal path is selected based on continuously feeding back from the network. This strategy will ensure that the suggested model shall remain responsive to variations in the network, which is a dynamic environment. With the synergy of all the involved methods, holistic approaches toward the management of congestion have been expressed, considering the multi-faceted challenges from detection to cure. This model not only demonstrates superior adaptability and scalability, pertinent for large-scale wireless networks, but also boasts computational efficiency conducive to real-time applications. This implementation shall bring out great improvements in network performance indices like packet delivery ratio, end-to-end delay, and throughput and thus provide an opportunity to surpass conventional static congestion control mechanisms. The impact of this paper ranges from academic contributions to practical implications in the area of wireless communication. In that case, this research will provide a strong framework for reliable and efficient operation of wireless networks, provided that demands from modern digital communication systems persist. In this way, this paradigm shift of congestion control strategies reflects a landmark in the evolution of management of wireless networks. [ABSTRACT FROM AUTHOR]

This paper discusses the congestion control challenges in a network employing multi-bottleneck Transmission Control Protocol/Active Queue Management (TCP/AQM). The study specifically focuses on networks characterized by input nonlinearity and unknown disturbances. We regard the network as a whole, and consider the influence between multiple nodes and unknown disturbance, a dynamic model of multi-bottleneck network is established. And the impact of dead zone and saturation on the system is taken into account for the first time in the model, the builded TCP/AQM model is more practicable. Based on the characteristics of fuzzy logic systems (FLS), combined with backstepping technology and Lyapunov function, an adaptive congestion control algorithm is designed to make full use of the link resources of each node and improve the network utilization. Ultimately, the proposed algorithm's efficacy and superiority are substantiated through simulation. [ABSTRACT FROM AUTHOR]