Congestion Control Solution Research Articles

Troubleshooting solution for traffic congestion control

The Internet has existed since the 1970s as a means of data exchange between network devices in small networks. In the early stage, there was a small number of devices, but today there is an ever-increasing number of devices, leading to congestion in the network. Therefore, congestion control has attracted so much attention in the academic community and the industry for the past 30 years. Recently, Google has developed BBR (Bottleneck Bandwidth and Round-Trip Time), a rate-based congestion control algorithm. BBR controls transmission rates based on delivery rate and round-trip time (RTT). However, such a static congestion control algorithm (e.g., BBR, etc.) cannot achieve high performance in various network conditions (e.g., low bandwidth, etc.). Concretely, these static algorithms cannot adapt to the dynamic changes of the network environment. Therefore, in this paper, we propose an adaptive algorithm (called ABBR) for congestion control in next-generation networks. ABBR takes into account the reinforcement learning algorithm to learn relevant policies to change the transmission rate corresponding to each congestion control algorithm to optimize long-term performance. The experimental results show that our proposal can achieve good performance in terms of throughput, RTT, and fairness compared to the benchmarks.

Congestion Control Using In-Network Telemetry for Lossless Datacenters

In the Ethernet lossless Data Center Networks (DCNs) deployed with Priority-based Flow Control (PFC), the head-of-line blocking problem is still difficult to prevent due to PFC triggering under burst traffic scenarios even with the existing congestion control solutions. To address the head-of-line blocking problem of PFC, we propose a new congestion control mechanism. The key point of Congestion Control Using In-Network Telemetry for Lossless Datacenters (ICC) is to use In-Network Telemetry (INT) technology to obtain comprehensive congestion information, which is then fed back to the sender to adjust the sending rate timely and accurately. It is possible to control congestion in time, converge to the target rate quickly, and maintain a near-zero queue length at the switch when using ICC. We conducted Network Simulator-3 (NS-3) simulation experiments to test the ICC’s performance. When compared to Congestion Control for Large-Scale RDMA Deployments (DCQCN), TIMELY: RTT-based Congestion Control for the Datacenter (TIMELY), and Re-architecting Congestion Management in Lossless Ethernet (PCN), ICC effectively reduces PFC pause messages and Flow Completion Time (FCT) by 47%, 56%, 34%, and 15.3×, 14.8×, and 11.2×, respectively.

Approximate reinforcement learning to control beaconing congestion in distributed networks

In vehicular communications, the increase of the channel load caused by excessive periodical messages (beacons) is an important aspect which must be controlled to ensure the appropriate operation of safety applications and driver-assistance systems. To date, the majority of congestion control solutions involve including additional information in the payload of the messages transmitted, which may jeopardize the appropriate operation of these control solutions when channel conditions are unfavorable, provoking packet losses. This study exploits the advantages of non-cooperative, distributed beaconing allocation, in which vehicles operate independently without requiring any costly road infrastructure. In particular, we formulate the beaconing rate control problem as a Markov Decision Process and solve it using approximate reinforcement learning to carry out optimal actions. Results obtained were compared with other traditional solutions, revealing that our approach, called SSFA, is able to keep a certain fraction of the channel capacity available, which guarantees the delivery of emergency-related notifications with faster convergence than other proposals. Moreover, good performance was obtained in terms of packet delivery and collision ratios.

Congestion Control for NDN-Based MANETs

A mobile ad hoc network (MANET) has several intrinsic features that create unique queuing dynamics, and thus congestion control inside a MANET must be achieved under time-critical conditions. Meanwhile, the Named Data Networking (NDN) architecture ensures traffic optimization and has attracted renewed attention as part of the future internet. The synergy between NDN and MANETs can be exploited in order to improve the performance of dynamic content routing and congestion control mechanisms. This overview identifies the key concepts involved in congestion control for NDN-based MANETs. It also proposes some criteria for categorising existing congestion control solutions for NDN-based MANETs and discusses the advantages and disadvantages of each category. Future challenges regarding congestion control for NDN-based MANETs are also highlighted.

Fair hop-by-hop interest rate control to mitigate congestion in named data networks

Data retrieval in Named Data Networking (NDN) is based on content names irrespective of their hosting location. The NDN architecture introduces original naming, forwarding and caching techniques to improve data delivery efficiency. These distinctive techniques make the TCP congestion control scheme not suitable for the NDN architecture. In particular, the in-network caching and the multi-path forwarding used in the NDN architecture lead to fluctuations in the Round Trip Time (RTT) measurements. This makes the Retransmission TimeOut (RTO) an unreliable congestion indicator. Thus, the congestion problem in Named Data Networks deserves to be reconsidered. In this paper, we present a new congestion control algorithm, called IRNA (Interest Rate Notification and Adjustment), to mitigate the congestion problem in Named Data Networks while maintaining per flow and per consumer fairness property. More specifically, IRNA is a hop-by-hop scheme where each router monitors the occupation level of its outgoing queues to detect in advance potential congestion events. When the queue size is above or below a preset threshold, the router sends explicit notifications to its downstream nodes to specify the appropriate interest rate. Hence, by cooperatively adjusting the Interest transmission rate of each node and for each flow, IRNA succeeded to provide a fair transmission. We evaluated the performance of our solution using ndnSIM simulations. We compared IRNA to state-of-the-art hop-by-hop congestion control solution and we proved that IRNA managed to provide a faster congestion reaction and to achieve per flow and per consumer throughput fairness while maintaining a good bandwidth usage.

Stabilization of city-scale road traffic networks via macroscopic fundamental diagram-based model predictive perimeter control

Traffic control for large-scale urban road networks remains a challenging problem. Aggregated dynamical models of city-scale traffic, based on the macroscopic fundamental diagram (MFD), enable development of model-based perimeter control methods. Involving actuation over aggregated traffic flows, perimeter control specifies an effective and practicable congestion control solution. In this paper, we propose nonlinear model predictive perimeter control schemes, for regulation and economic optimization objectives, with closed-loop stability by construction. Macroscopic and microscopic simulations demonstrate the performance and domain of attraction properties of the proposed formulations. Results indicate potential of the methods for efficient and reliable control of city-scale traffic.

TCP-NCL: A serialized-timer approach for enhancing TCP over heterogeneous wired/wireless networks

In heterogeneous wired/wireless networks, TCP performs unsatisfactorily since packet reordering and non-congestive losses may be falsely interpreted as congestive losses. This causes TCP to trigger fast retransmission and fast recovery spuriously, leading to under-utilization of available network resources. In this paper, we have developed a smart TCP sender (STS) model to differentiate congestive issues from the non-congestive ones for constructing more reliable signals of packet loss and network congestion over general error-prone channels. Two serialized timers are employed so that their expirations offer two separate signals of a packet loss and network congestion. The first timer is started when a packet is first injected into the network, and it will be cancelled if the acknowledgement is received. Otherwise, the packet will be retransmitted and the second timer is started upon the expiration of the first timer. The STS model is constructed based on the concept of minimizing expected cost and optimal setting of expiration periods for timer is determined. We have devised a novel TCP variant, known as TCP for non-congestive loss (TCP-NCL), as a practical approximation of the STS model. TCP-NCL can thus serve as a unified solution for effective congestion control, sequencing control, and loss recovery over wireless networks. The deployment of TCP-NCL requires modifications to sender-side TCP only, thereby facilitating possible future wide deployment. Our simulation studies show that TCP-NCL is robust against packet reordering as well as non-congestive packet loss while maintaining good responsiveness against congestive loss.

Congestion adaptive load balanced clustering scheme for prolonging network lifetime in mobile ad-hoc network

Clustering in Mobile Ad-hoc Network (MANET) is the most effective technique to improve scalability and network lifetime. However, congestion and load balancing are still a major concern for optimising energy consumption and packet loss. Most of the existing routing protocols for MANET provide a solution for congestion control or load balancing among cluster heads separately. In this paper, a congestion adaptive load balanced clustering scheme is proposed where we are emphasising not only on the problem of appropriate cluster head selection, but also on assigning mobile nodes to cluster heads efficiently, based on the congestion status of cluster heads. Thus, our proposed algorithm revolves around three benefactions for load balanced clustering with congestion control, i.e. the selection of most suitable nodes to serve as cluster heads, minimising the overall loads to cluster heads and congestion control, which improve network lifetime with minimal overhead. The simulation results demonstrate the effectiveness of the proposed clustering algorithm compared with the existing algorithms in terms of average number of clusters formed, average end-to-end delay, packet delivery ratio, average number of re-clustering required and network lifetime.

Congestion adaptive load balanced clustering scheme for prolonging network lifetime in mobile ad-hoc network

Clustering in Mobile Ad-hoc Network (MANET) is the most effective technique to improve scalability and network lifetime. However, congestion and load balancing are still a major concern for optimising energy consumption and packet loss. Most of the existing routing protocols for MANET provide a solution for congestion control or load balancing among cluster heads separately. In this paper, a congestion adaptive load balanced clustering scheme is proposed where we are emphasising not only on the problem of appropriate cluster head selection, but also on assigning mobile nodes to cluster heads efficiently, based on the congestion status of cluster heads. Thus, our proposed algorithm revolves around three benefactions for load balanced clustering with congestion control, i.e. the selection of most suitable nodes to serve as cluster heads, minimising the overall loads to cluster heads and congestion control, which improve network lifetime with minimal overhead. The simulation results demonstrate the effectiveness of the proposed clustering algorithm compared with the existing algorithms in terms of average number of clusters formed, average end-to-end delay, packet delivery ratio, average number of re-clustering required and network lifetime.

Traffic Shaping for Congestion Control

The problem of congestion is not new to the field of telecommunications; its root can be traced back to the very foundations of the internet. Most, if not all networks, are currently faced with this problem. The distribution of resources on the network is very vital. The fact that resources are limited brought about major problem such that these limited resources would be shared among various workstations and nodes. As the network grows, and the number of workstations and nodes increases; resources become integral and if not properly managed no meaningful work will be done in such networks. Congestion control, which involved managing resources when the network utilization becomes so high, is of utmost importance so as to avoid congestion collapse. The complex calculations and computation carried out in the existing solutions, increase utilization as well as the problem of congestion. Traffic shaping algorithms provide solutions with little overhead and thus would be preferred to use in medium sized networks. This work proposes traffic shaping as a better solution for congestion control especially in medium size networks.

An Adaptive Solution for Congestion Control in CoAP-based Group Communications

The use of lightweight devices and constrained resources like Wireless Sensors Network (WSN) makes patterns traffic in the Internet of Things (IoT) different from the ones in conventional networks. One of the most emerging messaging protocols used to address the needs of these lightweight IoT nodes is Constrained Application Protocol (CoAP). CoAP presents a lot of advantages compared to other IoT application layer protocols; it ensures group communication via multicast communications between a server and multiple clients. Nevertheless, it doesn’t support a group communication from a client to multiple servers; it relies on multiple unicasts to do so. Regarding the fact that these constrained devices communicate via a large amount of messages and notifications, network congestion occurs. This paper proposes an adaptive congestion control algorithm designed for group communications using unicast between a client and multiple servers. Simulated results show that the proposed mechanism can appropriately achieve higher performances in terms of response time and packet loss.

Migrating Unfairness among Subflows in MPTCP with Network Coding for Wired-Wireless Networks

Recently, two new technologies have been introduced into the transport layer. One is network coding, and the other is multipath transmission control protocol (MPTCP). Network coding is introduced into the transport layer to enhance the performance of transmission control protocol (TCP) in wireless networks. Benefiting from multi-interface devices, MPTCP is proposed to make full use of the network resource. Theoretically, combining these two technologies can utilize resources more adequately. However, network coding and multipath transportation cannot collaborate well with each other because network coding invalidates the load-balancing feature of MPTCP congestion control schemes. In this paper, we first discuss the unfair congestion control issue in MPTCP combined with network coding (MPTCP/NC). Then, a new end-to-end congestion control solution, named Couple+, is presented to deal with the unfairness among subflows. In Couple+, sender tries to slightly slow down sending rate if the reason of packet loss is not decided. After judging of packet loss reason based on the characteristics of packet loss events, the rate will be recovered soon if the loss is caused by wireless error (wireless noise or collision) or be further reduced if the loss is caused by congestion. By simulation, we compare the performances of Couple+ and the previous congestion control scheme of MPTCP. The performance analysis proves that unfairness among subflows indeed exists, and our scheme can balance congestion among coded and noncoded subflows and can stay friendly with TCP flow.

Congestion Control Design for Multipath Transport Protocols: A Survey

High-quality services over wired and wireless networks require high bitrate network content delivery. Multipath transport protocols utilize multiple paths to support increased throughput for network applications. Ubiquitous mobile devices with multiple interfaces such as WiFi and 4G/5G cellular, and data centers supporting big data analysis and cloud-computing, motivate adoption of multipath transmission in current and future network architectures. Congestion control mechanisms play a fundamental role in these multipath transport protocols. Diverse approaches have been proposed in the literature, differing in terms of their goals, principles, performance, and mostly in how various issues are addressed in their design. This paper presents a survey of congestion control solutions for multipath transport protocols and discusses the multipath congestion control design in order to address the need for some desirable properties including TCP-friendliness, load balancing, stability, and Pareto optimality. Existing window-based and rate-based multipath congestion control algorithms are investigated and categorized based on their theoretical algorithm design. Next, this paper discusses the congestion control mechanisms used in diverse multipath transport protocols in the context of different network scenarios. Finally, the trends in the future multipath congestion control design are presented.

Performance Evaluation of AODV Using Fuzzy Logic to Reduce Congestion in MANET

Mobile ad-hoc network is an infrastructure less network as it doesn’t follow any particular network topology. In MANET congestion is a major problem in small size networks congestion’s effect is low as compared to the large size networks. Congestion degrades the performance of overall network drastically. Many algorithms have been proposed to handle the congestion famous one are the active que management algorithms (AQMs). But still there is no universally accepted solution for it. In this paper a congestion control solution is devised using fuzzy logic controller. In this node density and load are taken as input and packet drop probability as output, which is effective to control congestion in large networks.

Network coding based resource efficient congestion control for video streaming

The paper proposes a resource efficient solution for Network Coding (NC) based congestion control consisting in identification around the congested links of multiple butterfly or other low complexity NC-capable topologies by using the Discrete Lagrange Multiplier optimization algorithm. The identification of the NC-capable topologies is based on the resource management capabilities foreseen for the network entities of the Future Internet. The congestion control issue is tackled by separate encoding of appropriately selected groups of data flows passing through the bottleneck link. By optimal selection of the data flows to be encoded, the additional network resources required by the NC operations can be minimized. The encoding is realized by using an XOR-based algorithm adapted for unequal bit rate data flows, and the experimental performances are reported here. Due to its efficient usage of the network resources and high degree of scalability, the congestion control solution proposed in this paper is suitable for large bit rate transmissions, like video streaming.

A Study of Fair Bandwidth Sharing with AIMD-Based Multipath Congestion Control

The multi-homed capability offers a good opportunity to explore multipath transmission. To ensure fair bandwidth sharing between multipath flows and legacy single-path flows, congestion control is an essential mechanism at the transport layer to regulate traffic flows for bandwidth consumption. However, in a multipath scenario, the congestion control algorithm of the dominant transport control protocol (TCP) may result in too aggressive behavior. In this paper, we consider the generic congestion control principle of additive increase and multiplicative decrease (AIMD) and investigate two AIMD-based multipath congestion control solutions. We derive the conditions for AIMD parameters to ensure TCP-friendliness and satisfy two constraints for fair bandwidth sharing between multipath and single-path flows. Simulation results demonstrate that the AIMD-based multipath solutions well achieve the fairness goals.

Cross-Layer Design Approach with Power Consciousness for Mobile Ad-Hoc Networks

The protocols used in mobile ad-hoc networks are based on the layered architecture. The layered approach is highly rigid and strict since each layer of the architecture is only concerned about the layers immediately above it or below it. Recent wireless protocols rely on significant interactions among various layers of the network stack. A cross-layer design (CLD) introduces stack wide layer interdependencies to optimize network performance. The CLD use the state information flowing throughout the network stack to adapt their behavior accordingly. In this paper, CLD based architecture is proposed, where the objective is to provide a solution for power conservation, congestion control, and link failure management. The link quality is determined by the received signal strength at the physical layer. The channel interference, contention and RTS/CTS packets of the MAC layer are used to determine the transmitting power and ensure the Quality of Service at the application layer.

Distributed multichannel assignment with congestion control in wireless mesh networks

AbstractIn Multichannel Wireless Mesh Network architecture, topology discovery, traffic profiling, channel assignment and routing are essential. From the existing work done so far, we can observe that no work has been carried out on the combined solution of multichannel assignment with routing protocol and congestion control. In this paper, we propose to design a Distributed Multichannel Assignment with Congestion control (DMAC) routing protocol. In this protocol, a traffic‐aware metric provides the solution for multichannel assignment and congestion control. Hence, the proposed protocol can improve the throughput and channel utilization to a very high extent. The proposed algorithm avoids self‐interference by not assigning a channel to any link whose incident links have already been assigned channels. By our simulation results, we show that our proposed protocol attains high throughput and delivery ratio along with reduced delay. Copyright © 2011 John Wiley & Sons, Ltd.

Cross-layer congestion control in ad hoc wireless networks

The paper presents the problem of performance degradation of transport layer protocols due to congestion of wireless local area networks. Following the analysis of available solutions to this problem, a cross-layer congestion avoidance scheme (C 3TCP) is presented, able to obtain higher performance by gathering capacity information such as bandwidth and delay at the link layer. The method requires the introduction of an additional module within the protocol stack of the mobile node, able to adjust the outgoing data stream based on capacity measurements. Moreover, a proposal to provide optional field support to existing IEEE 802.11 protocol, in order to support the presented congestion control solution as well as many other similar approaches, is presented. Achieved results underline good agreement with design considerations and high utilization of the available resources.

Cascaded Fuzzy Congestion Controller for TCP/IP Traffic

This paper presents a fuzzy congestion control solution for active queue management in wireline packet switched networks, that use TCP to solve end-to-end flow control. Queue management is a trade-off between link utilisation, delay and the loss of packets. The targets of it are to reduce the average queue length in routers, decrease the end-to-end delay and reduce the packet loss probability by preventing buffer overflows. In the presented solution, a fuzzy controller regulates the rejection probability of received packets in routers to prevent buffer overflow and the rejection of all packets during congestion. Using simulations a fuzzy controller is compared with the traditional random early discard (RED) algorithm. Pareto distributed traffic was used in the comparison for the evaluation of controllers. The results showed that the fuzzy controller decreased the packet loss rate with lower buffer occupation and increased the link utilisation and throughput. It also decreased control traffic between the transmitting nodes and routers via decreasing the number of ICMP (Internet Control Message Protocol) messages. In addition, by keeping the average queue size small, the developed algorithm had the ability to accommodate itself more effectively to very bursty traffic than the RED algorithm without dropping packets.