We propose an optimization approach to flow control where the objective is to maximize the aggregate source utility over their transmission rates. We view network links and sources as processors of a distributed computation system to solve the dual problem using gradient projection algorithm. In this system sources select transmission rates that maximize their own benefits, utility minus bandwidth cost, and network links adjust bandwidth prices to coordinate the sources' decisions. We allow feedback delays to be different, substantial and time-varying, and links and sources to update at different times and with different frequencies. We provide asynchronous distributed algorithms and prove their convergence in a static environment. We present measurements obtained from a preliminary prototype to illustrate the convergence of the algorithm in a slowly time-varying environment.

We consider the problem of routing traffic to optimize the performance of a congested network. We are given a network, a rate of traffic between each pair of nodes, and a latency function for each edge specifying the time needed to traverse the edge given its congestion; the objective is to route traffic such that the sum of all travel times—the total latency—is minimized. In many settings, it may be expensive or impossible to regulate network traffic so as to implement an optimal assignment of routes. In the absence of regulation by some central authority, we assume that each network user routes its traffic on the minimum-latency path available to it, given the network congestion caused by the other users. In general such a “selfishly motivated ” assignment of traffic to paths will not minimize the total latency; hence, this lack of regulation carries the cost of decreased network performance. In this article, we quantify the degradation in network performance due to unregulated traffic. We prove that if the latency of each edge is a linear function of its congestion, then the total latency of the routes chosen by selfish network users is at most 4/3 times the minimum possible total latency (subject to the condition that all traffic must be routed). We also consider the more general setting in which edge latency functions are assumed only to be continuous and nondecreasing in the edge congestion. Here, the total

AbstractWe study the problem of optimizing the performance of a system shared by selfish, noncooperative users. We consider the concrete setting of scheduling jobs on a set of shared machines with load-dependent latency functions specifying the length of time necessary to complete a job; we measure system performance by the total latency of the system. Assigning jobs according to the selfish interests of individual users (who wish to minimize only the latency that their own jobs experience) typically results in suboptimal system performance. However, in many systems of this type there is a mixture of "selfishly controlled " and "centrally controlled " jobs; as the assignment of centrally controlled jobs will influence the subsequent actions by selfish users, we aspire to contain the degradation in system performance due to selfish behavior by scheduling the centrally controlled jobs in the best possible way. We formulate this goal as an optimization problem via Stackelberg games, games in which one player acts a leader (here, the centralized authority interested in optimizing system performance) and the rest as followers (the selfish users). The problem is then to compute a strategy for the leader (a Stackelberg strategy) that induces the followers to react in a way that (at least approximately) minimizes the total latency in the system. In this paper, we prove that it is NP-hard to compute the optimal Stackelberg strategy and present simple strategies with provable performance guarantees. More precisely, we give a simple algorithm that computes a strategy inducing a job assignment with total latency no more than a constant times that of the optimal assignment of all of the jobs; in the absence of centrally controlled jobs and a Stackelberg strategy, no result of this type is possible. We also prove stronger performance guarantees in the special case where every machine latency function is linear in the machine load.

Today's Internet is a massive, distributed network which continues to explode in size as ecommerce and related activities grow. The heterogeneous and largely unregulated structure of the Internet renders tasks such as dynamic routing, optimized service provision, service level verification, and detection of anomalous/malicious behavior increasingly challenging tasks. The problem is compounded by the fact that one cannot rely on the cooperation of individual servers and routers to aid in the collection of network traffic measurements vital for these tasks. In many ways, network monitoring and inference problems bear a strong resemblance to other "inverse problems" in which key aspects of a system are not directly observable. Familiar signal processing problems such as tomographic image reconstruction, system identification, and array processing all have interesting interpretations in the networking context. This article introduces the new field of network tomography, a field which we believe will benefit greatly from the wealth of signal processing theory and algorithms.

Future routers must not only forward packets at high speeds, but also deal with nontrivial issues such as scheduling support for differential services, heterogeneous link technologies, and backward compatibility with a wide range of packet formats and routing protocols. In this article, the authors outline the design issues facing the next generation of backbone, enterprise, and access routers. The authors also present a survey of recent advances in router design, identifying important trends, concluding with a selection of open issues. the bandwidths of the input ports, packets are queued only at the outputs, and outers knit together the constituent networks of R the global Internet, creating the illusion of a uni-the router is called an output-queued router. Otherwise, queues may build up at the inputs, and the router is called an input-queued router. An output port stores

Abstract. Mobile ad hoc networks are characterized by multi-hop wireless links, absence of any cellular infrastructure, and frequent host mobility. Design of efficient routing protocols in such networks is a challenging issue. A class of routing protocols called on-demand protocols has recently found attention because of their low routing overhead. We propose a technique that can reduce the routing overhead even further. The on-demand protocols depend on query floods to discover routes whenever a new route is needed. Our technique utilizes prior routing histories to localize the query flood to a limited region of the network. Simulation results demonstrate excellent reduction of routing overheads with this mechanism. This also contributes to a reduced level of network congestion and better end-to-end delay performance of data packets.

In this paper, we present surplus fair scheduling (SFS), a proportional-share CPU scheduler designed for symmetric multiprocessors. We first show that the infeasibility of certain weight assignments in multiprocessor environments results in unfairness or starvation in many existing proportional-share schedulers. We present a novel weight readjustment algorithm to translate infeasible weight assignments to a set of feasible weights. We show that weight readjustment enables existing proportional-share schedulers to significantly reduce, but not eliminate, the unfairness in their allocations. We then present surplus fair scheduling, a proportional-share scheduler that is designed explicitly for multiprocessor environments. We implement our scheduler in the Linux kernel and demonstrate its efficacy through an experimental evaluation. Our results show that SFS can achieve proportionate allocation, application isolation and good interactive performance, albeit at a slight increase in scheduling overhead. We conclude from our results that a proportionalshare scheduler such as SFS is not only practical but also desirable for server operating systems.

A simple approach, called PMP (Paris Metro Pricing), is suggested for dealing with congestion in packet networks such as the Internet. It is to partition a network into several logical networks, each of which would treat all packets equally on a best effort basis, just as the current Internet does. There would be no formal guarantees of quality of service. The separate networks would differ only in the prices paid for using them. Networks with higher prices would attract less traffic, and thereby provide better service. Price would be the primary tool of traffic management. 1. Introduction The Internet is the great success story of the 1990s. However, endemic congestion has led to wide dissatisfaction, and there is general agreement that new applications, especially real time ones such as packet telephony, will require higher quality of service. Various solutions to data network congestion are being developed, typically involving bandwidth reservation or priority setting. (See [Huit...

Can high quality be provided economically for all transmissions on the Internet? Current work assumes that it cannot, and concentrates on providing differentiated service levels. However, an examination of patterns of use and economics of data networks suggests that providing enough bandwidth for uniformly high quality transmission may be practical. If this turns out not to be possible, only the simplest schemes that require minimal involvement by end users and network administrators are likely to be accepted. On the other hand, there are substantial inefficiencies in the current data networks, inefficiencies that can be alleviated even without complicated pricing or network engineering systems.

Auto-configuration is a desirable goal in implementing mobile ad hoc networks. Specifically, automated dynamic assignment (without manual intervention) of IP addresses is desirable. In traditional networks, such dynamic address assignment is often performed using the Dynamic Host Configuration Protocol (DHCP). Implementing DHCP, however, requires access to a DHCP server. In mobile ad hoc networks, it is di#cult to guarantee access to a DHCP server, since ad hoc networks can become partitioned due to host mobility. Therefore, alternative mechanisms must be employed. One plausible approach is to allow a node to pick a tentative address randomly (or using some locally available information), and then use a "duplicate address detection" (DAD) procedure to detect duplicate addresses. The previously proposed DAD procedures make use of timeouts and do not always perform correctly in presence of partitions. In networks where message delays cannot be bounded, use of timeouts can lead to unreliability. Therefore, we propose an alternative approach (which can be used in conjunction with previously proposed schemes). We refer to the proposed approach as "weak" duplicate address detection. The goal of weak DAD is to prevent a packet from being routed to the "wrong" destination node, even if two nodes in the network happen to have chosen the same IP address. We also propose an enhanced version of the weak DAD scheme, which removes a potential shortcoming of the weak DAD approach.