<p>We study the server allocation problem for tandem queues in the absence of intermediate buffer space. Servers are assumed to be homogeneous and non-collaborative. We provide policies to maximize the throughput. We break down our work into four stages. First, we assume that all servers are dedicated. We propose an allocation algorithm that assigns servers to stations based on the mean service times and the current number of servers assigned to each station. The algorithm is proposed for stations with exponentially distributed service times, but where the service rate at each station may be different. We further study the impact on the proposed allocation method of including service time distributions with different coecients of variation. Second, we consider tandem queues with both dedicated and flexible servers. We examine policies to dynamically assign flexible servers. When there is one flexible server and two stations each with a dedicated server, we completely characterize the optimal policy. We use the insights gained from applying the Policy Iteration algorithm on systems with three, four, and five stations to devise heuristics for systems of arbitrary size. Third, we study cases where flexibility is constrained such that flexible servers can only service two adjacent stations. We provide optimal policies for tandem queues with three and four stations and compare them with optimal policies for corresponding non-constrained cases. Fourth, we consider two parallel tandem queues with both dedicated servers and vertical flexible servers - servers that can move between corresponding stations of the two tandem queues. The workload allocations are the same for each line and each vertical flexible server moves only between two corresponding stations. We examine policies for dynamic allocation of these vertical flexible servers. When each tandem queue has two stations, each station possesses a dedicated server, and a vertical flexible server exists for each pair of stations, we specify the optimal policy. For cases with more than two stations, heuristic assignments are proposed. We also analyze the throughput improvement gained from adding flexible servers within a tandem queue or between two parallel tandem queues. Numerical results are used to verify the heuristics provided in each of the stages.</p> / Doctor of Philosophy (PhD)

An ever increasing demand for instant and reliable information on modern communication networks forces codewords to operate in a non-asymptotic regime. To achieve reliability for imperfect channels in this regime, codewords need to be retransmitted from receiver to the transmit buffer, aided by a fast feedback mechanism. Large occupancy of this buffer results in longer communication delays. Therefore, codewords need to be designed carefully to reduce transmit queue-length and thus the delay experienced in this buffer. We first study the consequences of physical layer decisions on the transmit buffer occupancy. We develop an analytical framework to relate physical layer channel to the transmit buffer occupancy. We compute the optimal code-rate for finite-length codewords operating over a correlated channel, under certain communication service guarantees. We show that channel memory has a significant impact on this optimal code-rate. Next, we study the delay in small ad-hoc networks. In particular, we find out what rates can be supported on a small network, when each flow has a certain end-to-end service guarantee. To this end, service guarantee at each intermediate link is characterized. These results are applied to study the potential benefits of setting up a network suitable for network coding in multicast. In particular, we quantify the gains of network coding over classic routing for service provisioned multicast communication over butterfly networks. In the wireless setting, we study the trade-off between communications gains achieved by network coding and the cost to set-up a network enabling network coding. In particular, we show existence of scenarios where one should not attempt to create a network suitable for coding. Insights obtained from these studies are applied to design a distributed rate control algorithm in a large network. This algorithm maximizes sum-utility of all flows, while satisfying per-flow end-to-end service guarantees. We introduce a notion of effective-capacity per communication link that captures the service requirements of flows sharing this link. Each link maintains a price and effective-capacity, and each flow maintains rate and dissatisfaction. Flows and links update their respective variables locally, and we show that their decisions drive the system to an optimal point. We implemented our algorithm on a network simulator and studied its convergence behavior on few networks of practical interest.