Jointly Optimal Congestion Control, Forwarding Strategy and Power Control for Named-Data Multihop Wireless Network

In multi-hop wireless networks, maximizing network utility by joint congestion control and scheduling has drawn much research interest, and significant progress has been made that has yielded much insight. However, in attempting to maximize network utilization, most scheduling mechanisms proposed in earlier works are too complicated to be implemented in wireless devices. One traditional approach to address complexity is to approximate the optimal but complex solution by a feasible solution that can provide a certain performance guarantee. In this paper, we suggest an alternative approach that simplifies the optimization problem itself in such a way that the solution of the new problem is guaranteed to be a fraction of the optimal solution of the original problem. The fraction depends on the “interference degree” of the network. Based on the simplified model, we propose a scheme which combines congestion control and random access MAC. We subsequently analyze its theoretical performance, and prove that the algorithm guarantees stability, and asymptotically converges to the near-optimal operational point. Future work is needed to investigate the mechanism by which such a scheme can be implemented.

In this paper, an analytical framework is proposed for the optimization of network performance through joint congestion control, channel allocation, rate allocation, power control, scheduling, and routing with the consideration of fairness in multi-channel wireless multihop networks. More specifically, the framework models the network by a generalized network utility maximization (NUM) problem under an elastic link data rate and power constraints. Using the dual decomposition technique, the NUM problem is decomposed into four subproblems - flow control; next-hop routing; rate allocation and scheduling; power control; and channel allocation - and finally solved by a low-complexity distributed method. Simulation results show that the proposed distributed algorithm significantly improves the network throughput and energy efficiency compared with previous algorithms.

Since the initial publication of Kelly et al.'s seminal paper on resource allocation in wired networks, a large number of studies based on the network utility maximization (NUM) framework have been conducted, for example, on resource allocations in wired networks as well as wireless networks. Congestion control, used to adapt the traffic rates injected into a network, can be controlled separately at the transport layer or mutually with other layers, using a cross-layer design. The focus of this paper is a review of the research following the NUM framework and addressing the problem of congestion control from several dimensions, specifically, elastic traffic or inelastic traffic, same-timescale or multi-timescale, and single-path or multipath transmissions. First, cross-layer designs for wireless networks, basics of optimization theory, and an example of cross-layer congestion control are summarized. Then, studies on NUM-based congestion control are sequentially presented from several points of view. In addition, we survey the recent literature on cross-layer resource allocation in next generation networks, software-defined networking, and cloud radio access networks, which can enhance the performances and address issues found in current networks. Finally, we outline what we consider to be the current challenges and open issues in the area of NUM-based congestion control for wireless networks.

Recent years have witnessed an active research on the stochastic network utility maximization (NUM) problem, where the optimal network resource allocation policy, such as congestion control, routing, and scheduling, is formulated as a constrained maximization of some utility function under the stochastic dynamics in users' traffic and time-varying wireless channels. So far, the stochastic NUM problem and its associated solutions are investigated under light-tailed (LT) traffic assumption, which is largely departing from the recent large-scale empirical studies, which verify the emergence of heavy-tailed (HT) traffic in a variety of networked systems. The unique stochastic features of HT traffic fundamentally challenges the feasibility of the classic algorithms developed for the stochastic NUM problem. This paper aims to develop effective algorithms to maximize network utility in the presence of heavy tailed traffic. First, it is proven that without considering the inherent bursty nature of HT traffic, the classic stochastic subgradient algorithm, which is utility optimal, fail to achieve queue stability. Our theoretical analysis reveals that such queue instability phenomenon is due to the fact that the stochastic subgradient algorithm inherently exploits queue length to update Lagrange dual variables. To counter this challenge, a time-average stochastic gradient algorithm is proposed, which decouples the queue-length update process and the dual variable update process in such a way that utility-optimality and queue-stability can be simultaneously achieved. Our convergence and stability analysis shows that the proposed algorithm can avoid the LT queues from competing with the HT queues, thus completely shielding those LT queues from the destructive impact of HT traffic.

Wireless networks are defined as that the network nodes which are connected by wireless data connections. The devices are connected via wireless link to communicate with each other. Measuring the delay performance of end-to-end nodes is the one of the most convoluted issues in wireless networks. In wireless networks, it is very difficult to maintain the substitution between throughput and delay. This paper proposes a new joint scheduling and congestion control algorithm for multihop wireless networks with dynamic route flows. The proposed algorithm achieves a provable throughput guarantee and provable end-to-end delay of every flow. The new joint scheduling and congestion control algorithm improves throughput and delay for dynamic wireless network by shifting scheduling scheme with virtual adaptation model. The proposed algorithm combines window-based flow control with a new rate based distributed scheduling algorithm to survive the quality of the system. This approach adaptively selects a set of routes according to the traffic load. Furthermore this dynamic adaptation mechanism achieves better concert in terms of throughput, end-to-end delay and packet delivery ratio.

In this paper we explore congestion control solutions in a network running the Named Data Networking (NDN) protocol. Since requested data can be retrieved from either original producers or in-network caches, the end-to-end connection oriented TCP congestion control solutions, such as BBR (Bottleneck Bandwidth and Round-trip propagation time) do not work well for NDN transport, especially in wireless networks. We propose a BBR-guided congestion control, BBR-CD, for bulk data fetching by a group of users. BBR-CD applies RTT filtering and interest scheduling to improve BBR's efficiency in NDN. Our evaluation shows that BBR-CD achieves much higher application goodput compared with ndncatchunks which implements the TCP AIMD and CUBIC congestion control algorithms. Moreover, compared with one-flow-per-file SIRC, an NDN congestion control algorithm that paces interests based on inter-data-gap, BBR-CD provides better fairness and bandwidth utilization. Finally, BBR-CD outperforms a direct adoption of the original BBR to NDN, suggesting that our changes to BBR are effective.

The concave utilities in the basic network utility maximisation (NUM) problem are only suitable for elastic flows. In networks with both elastic and inelastic traffic, the utilities of inelastic traffic are usually modelled by the sigmoidal functions which are non‐concave functions. Hence, the basic NUM problem becomes a non‐convex optimisation problem. To address the non‐convex NUM, the authors approximate the problem which is equivalent to the original one to a strictly convex problem. The approximation problem is solved efficiently via its dual by the gradient algorithm. After a series of approximations, the sequence of solutions to the approximation problems converges to a local optimal solution satisfying the Karush‐Kuhn‐Tucker conditions of the original problem. The proposed algorithm converges with any value of link capacity. The authors also extend their work to jointly allocate the rate and the power in a multihop wireless network with elastic and inelastic traffic. Their framework can be used for any log‐concave utilities.

BATS (BATched Sparse) codes are a class of efficient random linear network coding variation that has been studied for multihop wireless networks mostly in scenarios of a single communication flow. Towards sophisticated multi-flow network communications, we formulate a network utility maximization (NUM) problem that jointly optimizes the BATS code parameters of all the flows and network scheduling. The NUM problem adopts a batch-wise packet loss model that can be obtained from the network local statistics without any constraints on packet loss patterns. Moreover, the NUM problem allows a different number of recoded packets to be transmitted for different batches in a flow, which is called adaptive recoding. Due to both the probably nonconcave objective and the BATS code-related variables, the algorithms developed for the existing flow optimization problems cannot be applied directly to solve our NUM problem. We introduce a two-step algorithm to solve our NUM problem, where the first step solves the problem with nonadaptive recoding schemes, and the second step optimizes adaptive recoding hopby-hop from upstream to downstream in each flow. We perform various numerical evaluations and simulations to verify the effectiveness and efficiency of the algorithm.

In this paper, we deal with a cross-layer optimization problem in Ad Hoc networks. Based on network utility maximization framework, we formulate the joint congestion and power control problem providing SINR guarantee and energy saving. We adopt dual decomposition technique to deduce two maximization sub problem, and then design the optimal distributed congestion control algorithm at the transport layer and power control algorithm at the physical layer, respectively. In this cross-layer optimization algorithm, the sources update their transmission rates by the congestion measures, and the links update their transmission powers to satisfy SINR requirement and save node energy. The simulation results show that the proposed algorithm providing SINR guarantee and energy saving. Moreover, it can achieve the global optimum within reasonable convergence time.

RaceCC: A rapidly converging explicit congestion control for datacenter networks

In this study we investigate the interaction between TCP and MAC layer in a wireless multi-hop network. This type of network has traditionally found applications in the military (automated battlefield), law enforcement (search and rescue) and disaster recovery (flood, earthquake), where there is no fixed wired infrastructure. Wireless "ad-hoc" multi-hop networks have previously been proposed for nomadic computing applications. Key requirements in all the above applications are reliable data transfer and congestion control, features that are generally supported by TCP. Unfortunately, TCP performs on wireless in a much less predictable way than on wired protocols. Using simulation, we provide new insight into two critical problems of TCP over wireless multi-hop. The first is the conflict between data packets and ACKs, which causes TCP performance to degrade for window sizes greater than 1 packet. The second is the interaction between MAC and TCP layer backoff timers which causes severe unfairness and capture conditions. In the paper, we identify these problems in several representative simulation runs on various topologies and traffic patterns and indicate possible remedies to improve TCP efficiency over a wireless multi-hop network.

In Named Data Networking (NDN), content can be retrieved from multiple sources through multiple path, which makes the traditional end-to-end congestion control mechanisms unsuitable for NDN. A lot of works have been done to achieve the congestion control by limiting the transmission rate of interest packets, but most of them overlooked the intelligent forwarding feature in NDN. In this paper, we propose a ratebased, multipath-aware congestion control algorithm MNRCP, which is inspired by Rate Control Protocol (RCP). MNRCP calculates the transmission rate for every flow and feedbacks it to the consumer to control the sending rate of interest packets. In order to fully exploit the features of multiple data sources, in-network caching and multipath forwarding and adapt to the practical scenarios that interest packets requesting the same data can arrive from different interfaces, we propose a novel multipath forwarding strategy and a multipath feedback mechanism to achieve fairness and network utilization. In addition, simulation results of our algorithm in ndnSIM2.3 show that compared with other congestion control mechanisms, MNRCP can achieve higher total throughput while ensuring fairness. According to the available bandwidth of the path, MNRCP also can achieve the optimal traffic split ratio, and thus performs better in load balancing.

The objective of congestion control is to maximize network bandwidth utilization and minimize the average flow completion time in data center networks. Key performance indicators required to achieve this objective are high throughput and low packet latency. Existing approaches have proposed various methods to control packet delivery based on various network events or parameters such as packet loss, bottleneck bandwidth, RTT, and queue length. However, these methods often result in suboptimal packet transmission states that compromise throughput or latency. We provide a method to overcome this drawback. To this end, we introduce a congestion control method called PRTT (Predicted RTT) that leverages predicted RTT for congestion control. By using accurately predicted RTT values, PRTT dynamically adjusts the packet delivery rate to control the number of in-flight packets. This enables the transmission to approach states where the buffer holds only a few packets while fully utilizing the link bandwidth. Experimental results show that PRTT achieves higher throughput, lower latency, and shorter flow completion times than other state-of-the-art methods, particularly under bursty traffic. These results demonstrate that PRTT offers a promising solution for congestion control.

In this letter we address the problem of users' desired trade-off between optimal throughput and delay in wireless multihop networks under the framework of Network Utility Maximization (NUM). Via dynamic utility design and proper adaptation of the constraint set of the NUM problem, the impact of users' delay sensitivity on the resulting optimal throughput is considered. A cross-layer policy is proposed-stemming from Lyapunov drift techniques-that performs routing, scheduling and congestion control optimizing the above trade-off. Via modeling, analysis and simulations the performance of the proposed problem formulation and policy is evaluated.

In this paper, we consider the problem of random access in wireless local area networks (WLANs) with each station generating either elastic or inelastic traffic. Elastic traffic is usually non-real-time, while inelastic traffic is usually coming from real-time applications. We formulate a network utility maximization (NUM) problem, where the optimization variables are the persistent probabilities of the stations and the utilities are either concave or sigmoidal functions. Sigmoidal utility functions can better represent inelastic traffic sources compared to concave utility functions commonly used in the existing random access literature. However, they lead to non-convex NUM problems which are not easy to solve in general. By applying the dual decomposition method, we propose a subgradient algorithm to solve the formulated NUM problem. We also develop closed-form solutions for the dual subproblems involving sigmoidal functions that have to be solved in each iteration of the proposed algorithm. Furthermore, we obtain a sufficient condition on the link capacities which guarantees achieving the global optimal solution when our proposed algorithm is being used. If this condition is not satisfied, then we can still guarantee that the optimal value of the objective function is within some lower and upper bounds. We perform various simulations to validate our analytical models when the available link capacities meet or do not meet the sufficient optimality condition.