Intelligent Congestion Control Research Articles

DECC: Achieving Low Latency in Data Center Networks With Deep Reinforcement Learning

Data Center Networks (DCNs) suffer from synchronized bursts for segmentation and aggregation modes, leading to buffer overflows at switches and increasing network delay. To overcome this problem, some congestion control algorithms like DCTCP use Explicit Congestion Notification (ECN) to notify in-network congestion and reduce switch buffer occupancy. However, the traditional Additive Increase Multiplicative Decrease (AIMD) method causes high fluctuation of round-trip time (RTT) in DCNs. Some intelligent congestion control algorithms designed for Internet can achieve great flexibility, but are not applicable in DCNs for a lack of accurate congestion feedback. In this paper, we analyze the deficiencies of utilizing RTT as congestion signals and the applicability of learning algorithms in DCNs. Then, we propose DECC, a smart TCP congestion control algorithm for DCNs, which combines Deep Reinforcement Learning (DRL) with ECN to achieve high bandwidth utilization as well as low queuing delay. DECC fully utilizes precise in-network feedback and formulates several QoS requirements to a multi-objective function. Meanwhile, it decouples cwnd adjustment with DRL decision making to gradually learn the optimal congestion control policy in real-time. We evaluate the performance of DECC in various scenarios. Simulation results show that DECC can reduce the queue length at bottleneck switches by more than 50% compared to DCTCP, while maintaining high bandwidth utilization and reducing Flow Completion Time (FCTs) under burst traffic.

Intelligent TCP Congestion Control Scheme in Internet of Deep Space Things Communication

In deep space missions, large-scale deep space information and continuous sensory data are generated, processed, and exchanged over Internet of deep space things (IoDST). Ensuring reliable communication in IoDST requires resolution of challenges engendered by the unique characteristics of IoDST, including long propagation delays, link outages, high error rates, and asymmetric bandwidths. Thus, transmission control protocol (TCP) layer functionalities are crucial for ensuring reliable IoDST communications. However, existing TCP congestion control (CC) protocols present poor performance in IoDST communications, owing to the dependence of traditional window-based CC approaches on pre-configured rules to adjust transmission rate against the aforementioned unique characteristics. In this paper, we propose an intelligent CC scheme called optimistic actor–critic-based TCP congestion control (OAC-TCPCC) to solve the problems of the challenging link conditions in IoDST. OAC-TCPCC dynamically determines optimal congestion window for data transmission over IoDST communication links to maximize the TCP throughput performance and minimize file transfer time. Simulation results reveal that OAC-TCPCC improves the TCP throughput performance by up to 27%, 79%, 92%, 477%, 643%, and 766%; and reduces file transfer time by up to 16%, 37%, 50%, 48%, 58%, and 79%, compared to DRL-CC, TP-Planet, FAST TCP, TCP Peach, TCP BBR, and TCP CUBIC, respectively.

ICoCoA: intelligent congestion control algorithm for CoAP using deep reinforcement learning

iCoCoA: intelligent congestion control algorithm for CoAP using deep reinforcement learning

A rapidly-exploring random tree-based intelligent congestion control through an alternate routing for WSNs

A rapidly-exploring random tree-based intelligent congestion control through an alternate routing for WSNs

An Intelligent Congestion Control Strategy in Heterogeneous V2X Based on Deep Reinforcement Learning

High mobility and the complexity of mobile behavior are the main characteristics of nodes in Vehicle to Everything (V2X). Furthermore, these characteristics entail that resource deployment cannot effectively meet the demands of users for differentiated service quality. Due to this significance, the main objective of this study is to propose an intelligent congestion control strategy based on deep reinforcement learning (ICCDRL) in heterogeneous V2X, which can meet the diverse service needs of vehicles to some extent, so as to solve the problem of network congestion effectively. The proposal is implemented through three aspects: Firstly, the paper establishes a congestion control model based on DRL. Secondly, a large amount of QoS data is used as the training set to optimize the model. Finally, the congestion sensitivity factor is used to select the size of the congestion window for the next moment, resulting in an intelligent congestion control strategy based on QoS on-demand drive. For verification, a series of simulation experiments are designed on the ns-3 simulation platform. The results show that the proposed ICCDRL outperforms the traditional algorithm in terms of throughput, convergence, friendliness and fairness, and can effectively guarantee real-time, reliable information interaction in V2X.

A Rapidly-exploring random tree-based intelligent congestion control through an alternate routing for WSNs

A Rapidly-exploring random tree-based intelligent congestion control through an alternate routing for WSNs

Research on an intelligent traffic congestion control model

This paper summarizes the status quo of intelligent traffic congestion control and vehicle following on traffic road, puts forward the key technology model and its content of intelligent traffic control, elaborates the model and content in detail, and summarizes the research done, hoping to provide reference for the related research on intelligent traffic congestion control.

Machine Learning for End-to-End Congestion Control

End-to-end congestion control has been extensively studied for over 30 years as one of the most important mechanisms to ensure efficient and fair sharing of network resources among users. As future networks are becoming more and more complex, conventional rule-based congestion control approaches tend to become inefficient and even ineffective. Inspired by the great success that machine learning (ML) has achieved in addressing large-scale and complex problems, researchers have begun to shift their attention from the rule-based method to an ML-based approach. This article presents a selected review of the recent applications of ML to the field of end-to-end congestion control. In this survey, we start with a brief review of the relationship between congestion control and ML. We then review the recent works that apply ML to congestion control. These works either help the agent to make an intelligent congestion control decision or achieve enhanced performance. Finally, we highlight a series of realistic challenges and shed light on potential future research directions.

English

English

Wireless Fair Intelligent Congestion Control — A QoS Performance Evaluation

In Broadband Wireless Access (BWA) networks, provisioning of Quality of Service (QoS) is absolutely essential for real time and non real time services. Congestion in these networks can lead to deterioration in QoS experienced by the network users. Congestion avoidance is rarely considered to ensure the QoS of wireless connections. Efforts are mainly aimed at reducing the overload once it has occurred. To avoid congestion at the base station in WiMAX networks, the WiMAX Fair Intelligent Congestion Control (WFICC) was proposed to ensure the traffic is scheduled in such a way that the base station output buffer operates around a target operating point without violating the QoS requirements of connections. The aim of this paper is to investigate WFICC thoroughly and evaluate its performance in terms of throughput, delay and jitter for different Classes of Services (CoSs) under various parameter settings of the algorithm. A detailed and comprehensive simulation study on various settings of parameters is performed in ns-2. The results show that WFICC performs excellently in allocating resources fairly among Class of Services (CoSs) and also preserves their QoS requirements. Furthermore, WFICC is robust and easily adapted to various traffic conditions.

Foreword to Special Issue

Parallel and distributed computing has been under many years of development, having played a central role in shaping different research and application trends such as grid computing, cloud computing, green computing, etc. The broad applications of parallel and distributed computing have also made the relevant research field interdisciplinary, cross boundaries among architectures, communications, computing, algorithms and programming. The objective of this special issue is to address some recent developments in this interdisciplinary area. The special issue is based on the presentations made at the 13th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2012) held in Beijing, 14–16 December 2012. Fatima Furqan and Doan B. Hoang in their paper “Wireless Fair Intelligent Congestion Control — A Qos Performance Evaluation” propose a congestion control scheme in WiMAX Networks, by scheduling the traffic and ensuring the output buffer of base station operates around a target operating point without violating the QoS requirement of connections. The paper evaluates the performance of the proposed scheme in terms of throughput, delay and jitter for different classes of services under various parameter settings. A detailed simulation study on various settings of parameters is also carried out in NS-2. Yangyang Li, Hongbo Wang, Jiankang Dong, Junbo Li and Shiduan Cheng in their paper “Differentiated Bandwidth Guarantees for Cloud Data Centers” propose a differentiated bandwidth allocation scheme for data center networks, to guarantee network performance of applications and provide fine-grained service differentiation. The problem is formulated as a multi-objective optimization problem and solved by a heuristic algorithm. Xu Liang, Youli Qu and Guixiang Ma in their paper “Research on Contrastive Viewpoint Summarization for Opinionated Texts” propose an approach for summarizing multi-topic contrastive viewpoints in opinionated text processing. They model the opinionated texts with Topic-Aspect Model and get the topic and aspect attribute of each sentence, and use some ranking methods to evaluate the centrality of each sentence, based on which the summary is finally generated. We sincerely thank all the authors and reviewers for their contributions to this special issue. Special thanks are given to Prof. Francis Lau, the EIC of JOIN, for

Intelligent Control of Congestion Based on Multi-SoftMan

Low performance and unfairness existed in current congestion control, meanwhile network is growing rapidly. It needs a new effective congestion control to meet expanded demands and improve actual state. As a new technique framework, SoftMan is proposed with its intelligence, autonomy and initiative to bring a new idea for information system. The paper looks not only at the benefits derived from intelligence, but also at those associated with Multi-SoftMan alliance in general. After exploring these benefits, an intelligent control model of congestion control based on multi-SoftMan is proposed. At the same time, the paper visualizes the architecture and system behaviors of Multi-SoftMan intelligent congestion control system (MSMICC).

Wireless Hybrid QoS Architecture with an Enhancement of Fair Intelligent Congestion Control

More subtle and explicit QoS control mechanisms are required at the radio access level, even though the simple and scalable Differentiated Services (DiffServ) QoS control model is acceptable for the core of the network. At the radio access level, available resources are severely limited and the degree of traffic aggregation is not significant, thus rendering the DiffServ principles less effective. In this paper we present a suitable hybrid QoS architecture framework to address the problem. At the wireless access end, the local QoS mechanism is designed in the context of IEEE 802.11 WLAN with 802.11e QoS extensions; so streams of those session-based applications are admitted, established according to the traffic profile they require, and guaranteed. As the core in the Admission Control of the hybrid QoS architecture, the Fair Intelligent Congestion Control (FICC) algorithm is applied to provide fairness among traffic aggregates and control congestion at the bottleneck interface between the wireless link and the network core via mechanisms of packet scheduling, buffer management, feedback and adjustments. It manages effectively the overloading scenario by preventing traffic violation from uncontrolled traffic, and providing guarantee to the priority traffic in terms of guaranteed bandwidth allocation and specified delay.

Interval Type-2 Fuzzy Logic Congestion Control for Video Streaming Across IP Networks

Intelligent congestion control is vital for encoded video streaming of a clip or film, as network traffic volatility and the associated uncertainties require constant adjustment of the bit rate. Existing solutions, including the standard transmission control protocol (TCP) friendly rate control equation-based congestion controller, are prone to fluctuations in their sending rate and may respond only when packet loss has already occurred. This is a major problem, because both fluctuations and packet loss affect the end-user's perception of the delivered video. A type-1 (T1) fuzzy logic congestion controller (FLC) can operate at video display rates and can reduce packet loss and rate fluctuations, despite uncertainties in measurements of delay arising from congestion and network traffic volatility. However, a T1 FLC employing precise T1 fuzzy sets cannot fully cope with the uncertainties associated with such dynamic network environments. A type-2 FLC using type-2 fuzzy sets can handle such uncertainties to produce improved performance. This paper proposes an interval type-2 FLC that achieves a superior delivered video quality compared with existing traditional controllers and a T1 FLC. To show the response in different network scenarios, tests demonstrate the response both in the presence of typical Internet cross-traffic as well as when other video streams occupy a bottleneck on an All-Internet protocol (IP) network. As All-IP networks are intended for multimedia traffic, it is important to develop a form of congestion control that can transfer to them from the mixed traffic environment of the Internet. It was found that the proposed type-2 FLC, although it is specifically designed for Internet conditions, can also successfully react to the network conditions of an All-IP network. When the control inputs were subject to noise, the type-2 FLC resulted in an order of magnitude performance improvement in comparison with the T1 FLC. The type-2 FLC also showed reduced packet loss when compared with the other controllers, again resulting in superior delivered video quality. When judged by established criteria, such as TCP-friendliness and delayed feedback, fuzzy logic congestion control offers a flexible solution to network bottlenecks. These findings offer the type-2 FLC as a way forward for congestion control of video streaming across packet-switched IP networks.

Intelligent congestion control for ABR service in ATM networks

The emergence of asynchronous transfer mode (ATM) technology has generated new challenging problems for computer network designers. One of these challenges lies in the efficient management of ATM traffic so that the communication bandwidth of the network can be optimally utilized. Considerable standardization efforts in recent ATM Forum activities have been centered on the traffic management of available bit rate (ABR) service. In this paper, we examine congestion control schemes for ABR service in ATM networks. We describe a rate-based scheme that is now referred to by the ATM Forum as 'intelligent congestion control' and is currently considered as one of the most promising approaches. Moreover, we present analytical and simulation results illustrating the characteristics of the proposed scheme.