Network Congestion Control Algorithm Research Articles

Feedback-Based Control Loop Congestion Control Algorithm for Wireless Networks

Feedback-Based Control Loop Congestion Control Algorithm for Wireless Networks

Plausibility of BBR as CUBIC’S Replacement and proposed improvement to BBR using GENET

Recent advancements in deep reinforcement learning (RL) have opened new avenues for enhancing network congestion control algorithms. Our research builds upon these developments, particularly focusing on the BBR (Bottleneck Bandwidth and Round-trip propagation time) congestion control algorithm. We propose integrating GENET's reinforcement learning framework, a novel training paradigm that has demonstrated success in various network adaptation algorithms, including adaptive video streaming, congestion control, and load balancing. GENET leverages curriculum learning to effectively train RL models by progressively introducing more challenging network environments. This method counters the common pitfalls in RL training, such as suboptimal performance in a wide range of environments and poor generalization in narrowly defined training scenarios. Our approach exploits the strengths of GENET in identifying and emphasizing network conditions where the current RL model underperforms compared to traditional rule-based baselines, thereby facilitating significant improvements. This research aims to demonstrate that applying GENET's methodology to the BBR congestion control algorithm can yield RL policies that surpass both regularly trained RL policies and conventional baselines, thereby advancing the efficiency and reliability of network congestion control.

An efficient reconfigurable geographic routing congestion control algorithm for wireless sensor networks

<span lang="EN-US">In recent times, huge data is transferred from source to destination through multi path in wireless sensor networks (WSNs). Due to this more congestion occurs in the communication path. Hence, original data will be lost and delay problems arise at receiver end. The above-mentioned drawbacks can be overcome by the proposed efficient reconfigurable geographic routing congestion control (RgRCC) algorithm for wireless sensor networks. the proposed algorithm efficiently finds the node’s congestion status with the help queue length’s threshold level along with its change rate. Apart from this, the proposed algorithm re-routes the communication path to avoid congestion and enhances the strength of scalability of data communication in WSNs. The proposed algorithm frequently updates the distance between the nodes and by-pass routing holes, common for geographical routing. when the nodes are at the edge of the hole, it will create congestion between the nodes in WSNs. Apart from this, more nodes sink due to congestion. it can be reduced with the help of the proposed RgRCC algorithm. As per the simulation analysis, the proposed work indicates improved performance in comparison to conventional algorithm. By effectively identifying the data congestion in WSNs with high scalability rate as compared to conventional methods</span>

Through the RTT Lens : A Comparative study of CUBIC and BBR Congestion Control

As the demand for high-performance internet applications continues to surge, the efficiency of network congestion control algorithms becomes a critical factor in ensuring a seamless user experience. This research paper delves into the comparative analysis of two prominent congestion control mechanisms: BBR (Bottleneck Bandwidth and Round- trip propagation time) and Cubic[1]. Both algorithms play pivotal roles in regulating data flow within networks, but their approaches differ significantly. The comparison section highlights the adaptive behavior of each algorithm, emphasizing real-world implications for diverse network scenarios. The discussion interprets the findings, offering a nuanced understanding of the strengths and weaknesses of both BBR and Cubic, thereby contributing to the broader discourse on congestion control strategies.

An energy efficient fuzzy clustering-based congestion control algorithm for cognitive radio sensor networks

An energy efficient fuzzy clustering-based congestion control algorithm for cognitive radio sensor networks

Pareto: Fair Congestion Control With Online Reinforcement Learning

Modern-day computer networks are highly diverse and dynamic, calling for fair and adaptive network congestion control algorithms with the objective of achieving the best possible throughput, latency, and inter-flow fairness. Yet, prevailing congestion control algorithms, such as hand-tuned heuristics or those fueled by deep reinforcement learning agents, may struggle to perform well on multiple diverse networks. Besides, many algorithms are unable to adapt to time-varying real-world networking environments; and some algorithms mistakenly overlooked the need of explicitly taking inter-flow fairness into account, and just measured it as an afterthought. In this paper, we propose a new staged training process to train <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Pareto</i> , a new congestion control algorithm that generalizes well to a wide variety of environments. Different from existing congestion control algorithms running reinforcement learning agents, Pareto is trained for fairness using the first multi-agent reinforcement learning framework that is communication-free. Pareto continues training online adapting to newly observed environments in the real-world. Our extensive array of experiments shows that Pareto (i) performs well in a wide variety of environments, (ii) offers the best fairness when it comes to competing with other flows sharing the same network link, and (iii) improves its performance with online learning to surpass the state-of-the-art.

A Novel Active Queue Management Algorithm Based on Average Queue Length Change Rate

The rapid development of information technology has promoted the transformation of traditional networks into intelligent networks. Huge data traffic is generated by various types of traffic services in the intelligent networks, which can easily lead to network congestion, system instability, and other problems. These problems may incur great requirements and pose challenges for queue management algorithms. Most traditional active queue management (AQM) algorithms judge the congestion level of the network based only on the size of the average queue length while ignoring the network traffic variations. This makes these algorithms difficult to achieve effective improvement of congestion control efficiency. To address this problem, a novel network congestion control algorithm, namely the average queue length and change rate &#x2013;RED (AC-RED) is proposed in this paper. AC-RED can better relieve network congestion by reconfiguring the packet loss strategy model based on the average queue length change rate. The simulation results of NS2 show that in complex and dynamic network environments, the performance of AC-RED algorithm in the average queue length, packet loss rate, delay, and delay jitter is improved in most load conditions compared with the other five algorithms.

Artificial Intelligence Based Sensor Network Congestion Fuzzy Control Algorithm

The topology control of sensor sensor network was studied based on fuzzy control algorithm. Aiming at the dynamic changes of the topology of large-scale and heterogeneous artificial intelligence sensor networks and the incomplete information between nodes, a smart network-based congestion control algorithm for sensor networks was proposed and the performance of fuzzy control algorithms was analyzed. Based on this, a fuzzy control algorithm was designed. The algorithm fully considered the residual energy of nodes and the distribution of nodes in the network. Therefore, the reasonable election of the cluster head can be realized through the game between nodes, which effectively avoided energy holes, made the network energy consumption more uniform, prolonged the network life cycle, and optimized the network topology.

An IoT-Based Water Level Detection System Enabling Fuzzy Logic Control and Optical Fiber Sensor

The usage of wireless sensors has become widespread for the collection of data for various Internet of Things (IoT) products. Specific wireless sensors use optical fiber technology as transmission media and lightwave signals as carriers, showing the advantages of antielectromagnetic interference, high sensitivity, and strong reliability. Hence, their application in IoT systems becomes a research hotspot. In this article, multiple optical fiber sensors are constructed as an IoT detection system, and a Transmission Control Protocol (TCP)/Internet Protocol (IP) communication stack is used for the sensor module. Furthermore, design of gateway module, data server, and monitoring module is established in order to run the data server in the Windows system and communicate across the network segments. Furthermore, the optical fiber sensor is connected to the development board with WiFi, meanwhile considering the optical fiber wireless network’s congestion problem. The fuzzy logic concept is introduced from the perspective of cache occupancy, and a fiber sensor’s network congestion control algorithm is proposed. In the experiment, the IoT detection system with multiple optical fiber sensors is used for water level detection, and the sensor’s real-time data detected by the User Interface (UI) are consistent with the feedback results. The proposed method is also compared with the SenTCP algorithm and the CODA algorithm, and it was observed that the proposed network congestion control algorithm based on the fuzzy logic can improve network throughput and reduce the network data packet loss.

Network Intelligent Control and Traffic Optimization Based on SDN and Artificial Intelligence

For telecom operators, it is of great significance to employ artificial intelligence (AI) and big data technology in a software-defined network (SDN) in order to achieve intelligent network control, traffic management and optimization. This paper proposes a solution for intelligent work control and traffic optimization. This paper is mainly focused on SDN-based network traffic algorithm optimization and experimental verification. In this paper, we design a network control mechanism for network intelligent control as well as solutions for traffic optimization based on SDN and artificial intelligence. We analyze operators’ network requirements (e.g., the carrying of the 5th generation mobile network (5G) service, multi-protocol label switching virtual private networks optimization, cloudification of services and the IP backbone network). Then, we propose an intelligent network control architecture based on SDN and artificial intelligence. The proposed architecture consists of three modules, including a network status collection/perception module, an AI intelligent analysis module and an SDN controller module. Moreover, this paper also analyzes the objects of traffic optimization as well as routing calculation algorithms (e.g., the greedy algorithm, the top-k-shortest paths (KSP) algorithm) and routing optimization algorithms (e.g., particle swarm optimization, simulated annealing and genetic algorithms). In addition, we also put forward three optimization algorithms for the operator’s network, namely, network congestion control and prevention algorithms, resource preemption algorithms and balance of the entire network traffic algorithms. Then, we propose optimization algorithms for the above three objectives of operator network optimization, respectively. Finally, we conduct large-scale experiments to verify the effectiveness of the control mechanism and algorithms. The experimental results demonstrate that the use of SDN and artificial intelligence in operator networks can realize network intelligent control and traffic optimization more intelligently.

Policy Distillation for Real-Time Inference in Fronthaul Congestion Control

Centralized Radio Access Networks (C-RANs) are improving their cost-efficiency through packetized fronthaul networks. Such a vision requires network congestion control algorithms to deal with sub-millisecond delay budgets while optimizing link utilization and fairness. Classic congestion control algorithms have struggled to optimize these goals simultaneously in such scenarios. Therefore, many Reinforcement Learning (RL) approaches have recently been proposed to deal with such limitations. However, when considering RL policies’ deployment in the real world, many challenges exist. This paper deals with the real-time inference challenge, where a deployed policy has to output actions in microseconds. The experiments here evaluate the tradeoff of inference time and performance regarding a TD3 (Twin-delayed Deep Deterministic Policy Gradient) policy baseline and simpler Decision Tree (DT) policies extracted from TD3 via a process of policy distillation. The results indicate that DTs with a suitable depth can maintain performances similar to those of the TD3 baseline. Additionally, we show that by converting the distilled DTs to rules in C++, we can make inference-time nearly negligible, i.e., sub-microsecond time scale. The proposed method enables the use of state-of-the-art RL techniques to congestion control scenarios with tight inference-time and computational constraints.

A Contention-Based Hop-By-Hop Bidirectional Congestion Control Algorithm for Ad-Hoc Networks.

Existing hop-by-hop congestion control algorithms are mainly divided into two categories: those improving the sending rate and those suppressing the receiving rate. However, these congestion control algorithms have problems with validity and limitations. It is likely that the network will be paralyzed due to the unreasonable method of mitigating congestion. In this paper, we present a contention-based hop-by-hop bidirectional congestion control algorithm (HBCC). This algorithm uses the congestion detection method with queue length as a parameter. By detecting the queue length of the current node and the next hop node, the congestion conditions can be divided into the following four categories: 0–0, 0–1, 1–0, 1–1 (0 means no congestion, 1 means congestion). When at least one of the two nodes is congested, the HBCC algorithm adaptively adjusts the contention window of the current node, which can change the priority of the current node to access the channel. In this way, the buffer queue length of the congested node is reduced. When the congestion condition is 1–1, the hop-by-hop priority congestion control (HPCC) method proposed in this paper is used. This algorithm adaptively changes the adjustment degree of the current node competition window and improves the priority of congestion processing of the next hop node. The NS2 simulation shows that by using the HBCC algorithm, when compared with distributed coordination function (DCF) without congestion control, the proposed unidirectional congestion control algorithms hop-by-hop receiving-based congestion control (HRCC) and hop-by-hop sending-based congestion control (HSCC), and the existing congestion control algorithm congestion alleviation—MAC (CA-MAC), the average saturation throughput increased by approximately 90%, 62%, 12%, and 62%, respectively, and the buffer overflow loss ratio reduced by approximately 80%, 79%, 44%, and 79%.

Modeling and performance analysis of VI‐CRA: A congestion control algorithm for vehicular networks

SummaryThis study proposes a Vehicle ID‐based CAM Rate Adaptation (VI‐CRA) algorithm for beacon messages in the vehicular network. Foremost, an improved vehicle ID–based analytical model is proposed at the MAC layer of vehicular network. The model weighs the random back‐off number chosen by vehicles participating in the back‐off process, with the vehicle ID incorporated in their respective CAMs. This eventually leads to the selection of a vehicle ID–based random back‐off number, minimizing the probability of collision due to same back‐off number selection. It is worth noting that the improved analytical model outperforms the existing works in terms of average packet delay since only one fourth of the contention window size is used throughout the simulation. To enhance the performance of the analytical model, the paper incorporates a congestion control algorithm, by adapting the rate of CAM broadcast over the control channel. The algorithm is designed considering a wide range of scenarios, ranging from nonsaturated to extremely saturated network (in terms of collision probability) and sparsely distributed to teemed network (in terms of vehicular density). For better analyses of simulation results, the algorithm is applied over different vehicle ID–based back‐off numbers. Simulation results for all the back‐off numbers show that vehicle ID–based CAM rate adaptation algorithm performs better than the traditional fixed CAM rate IEEE 802.11p, even at high vehicular density.

TCP-ACC: performance and analysis of an active congestion control algorithm for heterogeneous networks

Transmission control protocol (TCP) is a reliable transport layer protocol widely used in the Internet over decades. However, the performances of existing TCP congestion control algorithms degrade severely in modern heterogeneous networks with random packet losses, packet reordering and congestion. In this paper, we propose a novel TCP algorithm named TCP-ACC to handle all three challenges mentioned above. It integrates 1) a real-time reorder metric for calculating the probabilities of unnecessary Fast Retransmit (FRetran) and Timeouts (TO), 2) an improved RTT estimation algorithm giving more weights to packets that are sent (as opposed to received) more recently, and 3) an improved congestion control mechanism based on packet loss and reorder rate measurements. Theoretical analysis demonstrates the equilibrium throughput of TCP-ACC is much higher than traditional TCP, while maintaining good fairness with regard to other TCP algorithms in ideal network conditions. Extensive experimental results using both network emulators and real network show that the algorithm achieves significant throughput improvement in heterogeneous networks as compared with other state-of-the-art algorithms.

Invs: A New Congestion Control Algorithm for Heterogeneous Networks

The available bandwidth, round trip time (RTT) and packet loss rate in the Internet can vary over many orders of magnitude, which is known as the heterogeneity of the Internet. To cope with the heterogeneity in Internet Congestion Control, we propose a new TCP protocol, namely Invs, that has three key components. First, it employs a novel increase function of congestion window with an adaptive increase factor that adjusts through estimation of path bandwidth-delay product (BDP) and minimum RTT. The increase function can modulate the window growth rate to fit with the path condition. Second, Invs adopts a novel scheme that adaptively adjusts the queue threshold in loss classification, which distinguishes non-congestion loss from congestion loss. Third, Invs introduces a new back-off scheme to enable quick convergence of congestion window. The performance analysis and evaluation show that Invs achieves good fairness, friendliness, RTT fairness and utilization in heterogeneous networks.

A Survey of Packets Scheduling Congestion Control Algorithms in Internet Protocol Storage Area Networks

Several approaches have been proposed to empower communication systems with quality of service (QoS) capabilities. In general, their main goal is to coherently support the end-to-end performance needs of applications, based on the establishment of, and agreement on, a set of concepts, policies and mechanisms. The fiber channel is the standard technology used in storage are network communications but it does not have mechanisms for providing QOS guarantees. However the increasing use of transmission control/internet protocol based network storage has introduced the possibility of using already existing techniques and tools to achieve to achieve QOS guarantees in Internet protocol Storage Area Networks. Due to the existence of other competing traffic in internet protocol networks it is necessary to provide storage input/output traffic with guaranteed network bandwidth. This paper discusses the available packet scheduling mechanisms pin pointing their advantages and disadvantages. The main goal is to combine two packets scheduling mechanisms and come up with a hybrid that assure a given storage QOS requirement between a storage client and internet protocol storage.

Stability Analysis of Internet Congestion Control Model with Compound TCP Under RED

Many applications require fast data transfer over high speed and long distance networks. Compound TCP(CTCP) is a novel congestion control algorithm for high-speed and long delay networks. This paper develops a dis- crete time dynamic feedback model of a congestion control system with CTCP under random early detection (RED). We find that periodic doubling bifurcation occurs when varying the RED control parameters or other system parameters. The fixed point of congestion control system and the critical value of parameters are determined by theoretical analysis. More- over, the result of theoretical analysis is proved and bifurcation and chaotic phenomena are numerically studied by using bifurcation diagrams and Lyapunov Exponent.

Improving the Performance of Network Congestion Control Algorithms

This technical note describes a redesign framework for fluid-flow models of network congestion control algorithms. Motivated by the augmented Lagrangian method, we introduce extra dynamics to algorithms resulting from traditional primal-dual methods to improve their performance while guaranteeing stability. We use our method to redesign the primal-dual, primal and dual algorithms for network flow control. In particular, we investigate the influence of the gains resulting from the extra dynamics on system stability and robustness to time delays. We provide a method to improve the transient performance and delay robustness of the overall system by tuning these gains.

Adaptive Logarithmic Increase Congestion Control Algorithm for Satellite Networks

This paper presents a new algorithm called the adaptive logarithmic increase and adaptive decrease algorithm (A-LIAD), which mainly addresses the Round-Trip Time (RTT) fairness problem in satellite networks with a very high propagation delay as an alternative to the current TCP congestion control algorithm. We defined a new increasing function in the fashion of a logarithm depending on the increasing factor α, which is different from the other logarithmic increase algorithm adopting a fixed value of α = 2 leading to a binary increase. In A-LIAD, the α value is derived in the RTT function through the analysis. With the modification of the increasing function applied for the congestion avoidance phase, a hybrid scheme is also presented for the slow start phase. From this hybrid scheme, we can avoid an overshooting problem during a slow start phase even without a SACK option. To verify the feasibility of the algorithm for deployment in a high-speed and long-distance network, several aspects are evaluated through an NS-2 simulation. We performed simulations for intra- and inter-fairness as well as utilization in different conditions of varying RTT, bandwidth, and PER. From these simulations, we showed that although A-LIAD is not the best in all aspects, it provides a competitive performance in almost all aspects, especially in the start-up and packet loss impact, and thus can be an alternative TCP congestion control algorithm for high BDP networks including a satellite network.

Reducing Packet loss in Active Queue Management

Random Early Detection (RED) is a network congestion control algorithm which detects incipient congestion according to current length of average queue. It detects congestion only after a packet has been dropped. In the recent, high speed networks, it is important to have some mechanisms that keep throughput high and average queue sizes low without packet loss and it would be undesirable to have large queue because it would significantly increase the average delay in the network.