It is well established that physical layer impairments significantly affect the performance of optical networks. The management of these impairments is critical for successful transmission, and may significantly affect network layer routing decisions. Hence, the traditional divide-and-conquer layered approach is sub-optimal, which has led to work on cross-layer techniques for routing in optical networks. Apart from fiber loss, one critical physical layer impairment that limits the capacity of optical networks is fiber nonlinearity. Handling nonlinearity introduces significant complexity to the traditional cross-layer approaches. We formulate and solve a joint routing and power control problem to optimize the system throughput that takes into consideration both fiber loss and nonlinearity. The joint power control and routing problem considered is a nonlinear integer programming problem. By characterizing the feasible solution space of the power control problem, we find a set of universal power settings that transform the complex power control and routing problem into a constrained path routing problem. We then propose an efficient fully polynomial time approximation scheme to solve the constrained path routing problem. Simulation results show that our proposed algorithm significantly improves network throughput and greatly outperforms greedy heuristics by providing a guaranteed performance bound.

In the past decade, mobile devices and applications have experienced an explosive growth, and users are expecting higher data rates and better quality services every year. In this paper, we propose several ideas to increase the functionality and capacity of wireless networks using software-defined networking (SDN) and cloud computing technologies. Connections between users and services in mobile networks typically have to pass through a required set of middleboxes. The complex routing is one of the major impetus for the SDN paradigm, which enables flexible policy-aware routing in the next generation mobile networks. In addition, the high costs of middleboxes and limited capabilities of mobile devices call for revolutionary virtualization technologies enabled by cloud computing. Based on these, we consider an online routing problem for mobile networks with SDN and cloud computing. In this problem, connection requests are given one at a time (as in a real mobile system), and the objective is to steer traffic flows to maximize the total amount of traffic accepted over time, subject to capacity, budget, policy, and quality of service constraints. A fast log-competitive approximation algorithm is developed based on time-dependent duals.

The advent and continued growth of large data centers has led to much interest in switch architectures that can economically meet the high capacities needed for interconnecting the thousands of servers in these data centers. Various multilayer architectures employing thousands of switches have been proposed in the literature. We make use of the observation that the traffic in a data center is a mixture of relatively static and rapidly fluctuating components, and develop a combined scheduler for both these components using a generalization of the load-balanced scheduler. The presence of the known static component introduces asymmetries in the ingress-egress capacities, which preclude the use of a load-balanced scheduler as is. We generalize the load-balanced scheduler and also incorporate an opportunistic scheduler that sends traffic on a direct path when feasible to enhance the overall switch throughput. Our evaluations show that this scheduler works very well despite avoiding the use of a central scheduler for making packet-by-packet scheduling decisions.

It is well established that physical layer impairments significantly affect the performance of optical networks. The management of these impairments is critical for successful transmission, and may significantly affect network layer routing decisions. Hence the traditional divide-and-conquer layered approach is sub-optimal, which has led to work on cross-layer techniques for routing in optical networks. Apart from fiber loss, one critical physical layer impairment that limits the capacity of optical networks is fiber nonlinearity. Handling nonlinearity introduces significant complexity to the traditional cross-layer approaches. We formulate and solve a joint routing and power control problem to optimize the system throughput that takes into consideration both fiber loss and nonlinearity. The joint power control and routing problem considered is a nonlinear integer programming problem. By characterizing the feasible solution space of the power control problem we find a set of universal power settings that transforms the complex power control and routing problem into a constrained path routing problem. We then propose an efficient Fully Polynomial Time Approximation Scheme (FPTAS) to solve the constrained path routing problem. Simulation results show that our proposed algorithm significantly improves network throughput and greatly outperforms greedy heuristics by providing a guaranteed performance bound.

The advent and continued growth of large data centers has led to much interest in switch architectures that can economically meet the high capacities needed for interconnecting the thousands of servers in these data centers. Various multilayer architectures employing thousands of switches have been proposed in the literature. We make use of the observation that the traffic in a data center is a mixture of relatively static and rapidly fluctuating components, and develop a combined scheduler for both these components using a generalization of the load-balanced scheduler. The presence of the known static component introduces asymmetries in the ingress-egress capacities, which preclude the use of a load-balanced scheduler as is. We generalize the load-balanced scheduler and also incorporate an opportunistic scheduler which sends traffic on a direct path when feasible to enhance the overall switch throughput. Our evaluations show that this scheduler works very well despite avoiding the use of a central scheduler for making packet-by-packet scheduling decisions.

The single-chip crosspoint-queued (CQ) switch is a compact switching architecture that has all its buffers placed at the crosspoints of input and output lines. Scheduling is also performed inside the switching core and does not rely on latency-limited communications with input or output line-cards. Compared with other legacy switching architectures, the CQ switch has the advantages of high throughput, minimal delay, low scheduling complexity, and no speedup requirement. However, the crosspoint buffers are small and segregated; thus, how to efficiently use the buffers and avoid packet drops remains a major problem that needs to be addressed. In this paper, we consider load balancing, deflection routing, and buffer pooling for efficient buffer sharing in the CQ switch. We also design scheduling algorithms to maintain the correct packet order even while employing multi-path switching and resolve contentions caused by multiplexing. All these techniques require modest hardware modifications and memory speedup in the switching core but can greatly boost the buffer utilizations by up to 10 times and reduce the packet drop rates by one to three orders of magnitude. Extensive simulations and analyses have been done to demonstrate the advantages of the proposed buffering and scheduling techniques. By pushing the on-chip memory to the limit of current ASIC technology, we show that a cell drop rate of 10-8, which is low enough for practical uses, can be achieved under real Internet traffic traces corresponding to a load of 0.9.

The single-chip crosspoint-queued (CQ) switch is a self-sufficient switching architecture enabled by state-of-art ASIC technology. Unlike the legacy input-queued or output-queued switches, this kind of switch has all its buffers placed at the crosspoints of input and output lines. Scheduling is also performed inside the switching core, and does not rely on instantaneous communications with input or output line-cards. Compared with other legacy switching architectures, the CQ switch has the advantages of high throughput, minimal delay, low scheduling complexity, and no speedup requirement. However, since the crosspoint buffers are small and segregated, packets may be dropped as soon as one of them becomes full. Thus how to efficiently use the crosspoint buffers and decrease the packet drop rate remains a major problem that needs to be addressed. In this paper, we propose a novel chained structure for the CQ switch, which supports load balancing and deflection routing. We also design scheduling algorithms to maintain the correct packet order caused by multi-path switching. All these techniques require modest hardware modifications and memory speedup in the switching core, but can greatly boost the overall buffer utilization and reduce the packet drop rate, especially for large switches with small crosspoint buffers under bursty and non-uniform traffic.

In this paper, we study the capacity and delay scaling laws for cognitive radio networks (CRN). The primary network consists of n static, randomly and evenly distributed primary users (PUs), which require high throughput with low delay. The secondary network consists of m = O(n1+δ) randomly and evenly distributed cognitive secondary users (SUs) with δ >; 0, which move in different area according to the hierarchical i.i.d. mobility model. The secondary network is carefully designed to support the primary network, so that PUs may achieve near-optimal performance in both capacity and delay aspects. Then by utilizing hierarchical cooperation among SUs with different mobility, a new hierarchical relay algorithm is proposed to improve the delay performance extensively. Under optimal condition, this algorithm may provide Ω(n-δ') per-node throughput and O(nδ") average delay for PU with δ', δ" >; 0, and significantly improve the performance of SU at the same time.