Intelligent mesh optical networks deployed today offer unparalleled capacity, flexibility, availability, and, inevitably, new challenges to master all these qualities in the most efficient and practical manner. More specifically, demands are routed according to the state of the network available at the moment. As the network and the traffic evolve, the lightpaths of the existing demands becomes sub-optimal. In this paper we study two algorithms to re-optimize lightpaths in resilient mesh optical networks. One is a complete re-optimization algorithm that re-routes both primary and backup paths, and the second is a partial re-optimization algorithm that re-routes the backup paths only. We show that on average, these algorithms allow bandwidth savings of 3% to 5% of the total capacity in scenarios where the backup path only is re-routed, and substantially larger bandwidth savings when both the working and backup paths are re-routed. We also prove that trying all possible demand permutations with an online algorithm does not guarantee optimality, and in certain cases does not achieve it, while for the same scenario optimality is achieved through re-optimization. This observation motivates the needs for a re-optimization approach that does not just simply look at different sequences, and we propose and experiment with such an approach. Re-optimization has actually been performed in a nationwide live optical mesh network and the resulting savings are reported in this paper, validating reality and the usefulness of re-optimization in real networks.

This paper presents a collection of approximation formulas that allow a network planner to quickly estimate the size of a mesh optical network with limited inputs.In particular, it provides a set of equations that relate number of sites, average fiber connectivity, demand load and capacity for various mesh protection architectures.These results can be used to easily and quickly estimate the amount of traffic that can be carried over a given network, or, conversely, given the traffic to be supported, to assess the characteristics of the topology required (in terms of number of nodes, connectivity).Finally, this analysis can be used to estimate the restoration performance that can be expected without requiring any extensive simulation studies.

Distributed, IP-based control architecture has been proposed for switched optical mesh networks, as a means to automate operations, enhance interoperability and facilitate the deployment of new applications. While distributed control in general enhances scalability and flexibility, it also offers challenges to path computation, especially for shared mesh restored paths, because of the summarization of link state information disseminated by the routing protocol. This paper discusses the tradeoffs between the path computation efficiency and the abstraction level of link state information. Several heuristic algorithms for computing shared mesh restored paths are described, which require different levels of abstraction and summarization of link resource sharing information. The performance of these algorithms is compared in term of the efficiency of network capacity utilization, the computation complexity, and the amount of required network information. We show that with appropriately aggregated link state information the proposed path computation algorithms are able to utilize the network resource very efficiently.

Efficient methods are needed to aggregate and disseminate the routing information, including the optical link resource availability and sharing, so that the amount advertised by the routing protocol is minimized and the information necessary for path computation is not lost. In this paper, the author proposed to extend the generalized multi-protocol label switching (GMPLS) OSPF-TE routing protocol to carry the necessary sharing information of the reserved resource on a TE link in support of computing the shared mesh restored paths. It is based on the OSPF routing extensions required to support traffic engineering (TE) and GMPLS. New optional sub-TLVs (type/length/value) are added to the link TLV of the TE link state advertisements (LSA) so that the sharing information of the restoration resource is disseminated.

Optical mesh network infrastructure has emerged as the technology of choice for next-generation transport networks. At the same time, distributed, IP-based, control architecture has been proposed for intelligent optical networks, as a means to automate operations, enhance interoperability, and facilitate the deployment of new applications. While distributed control in general enhances scalability and flexibility, it has also been observed that the requisite network topology and link-state information summarization may result in suboptimal path computation, especially for shared mesh restored paths. This paper presents a distributed control plane for optical mesh networks, focusing on distributed path computation and provisioning mechanisms. It discusses the tradeoffs between the path computation efficiency for shared mesh restored paths and the amount of network topology and link-state information that is disseminated via routing protocols. We show that with appropriately aggregated link resource availability and sharing information, the proposed distributed path computation algorithms are able to determine the shareability of restoration links with remarkable accuracy. A local channel assignment scheme, which is used in conjunction with the distributed path computation algorithms to assign shared channels when provisioning restoration paths, is also proposed. The additional information that signaling messages are required to carry in order to perform the local channel assignment at each node along the restoration path is discussed. Furthermore, we specify the extensions to the open shortest-path first (OSPF) routing protocol in support of shared mesh restoration. We analyze the performance of the proposed distributed path computation algorithms and the local channel assignment scheme, as well as the overhead of OSPF extensions. In particular, we study the tradeoffs between network capacity utilization, restoration path computation complexity, OSPF extension overhead, and memory requirements for storing the modified link-state database.

We assess the benefits of using statistical techniques to ascertain the shareability of protection channels when computing shared-mesh restored lightpaths in optical mesh networks. These optical networks support wavelength conversion everywhere as a byproduct of the electronic nature of the switching in the optical-electronic-optical optical cross connect used. Current deterministic approaches require a detailed level of information proportional to the number of active lightpaths. Although this is not an issue for good sized networks in the foreseeable future, these approaches are not practicable for distributed route computation involving larger networks. On the other hand, distributed approaches that do not make use of shareability information require a significant amount of additional capacity compared to a centralized approach with access to complete shareability information. With the proposed approach we show that even with less information, independent of the amount of traffic demand, it is possible to predict the shareability of protection channels with remarkable accuracy. In addition, we propose a local distributed channel assignment scheme that is used in conjunction with our distributed route computation proposal to assign shared channels when provisioning the backup path. This channel assignment scheme can also be used to further optimize capacity usage in individual links upon certain events or at regular intervals. Experiments are provided that demonstrate that our approach yields faster computation times with no significant penalty in terms of capacity usage than a centralized approach using complete information.

Clos networks, which are ubiquitous in large capacity switches, have been widely studied for unicast connection requests. But most of the results for unicast do not hold when the switch has to support multicast connections. Our interest is specifically in bicast connections which are required for setting up backup protected circuits in optical backbone networks. In this work we have proposed two approximation methods to estimate the blocking probability of a switch that is not strictly non-blocking in the presence of bicast connections. We have considered two ways of realizing a bicast connection - by splitting the circuit at the outer stage or at the middle stage. We have also carried out simulations to be compared with our analytical results and found that they closely match. Furthermore, we have compared two routing strategies - one randomly selects an available middle stage block and the other selects one of the highly loaded ones, and found that the latter significantly reduces blocking.

We assess the benefits of using statistical techniques to ascertain the shareability of protection channels when computing shared mesh restored lightpaths. Current deterministic approaches require a detailed level of information proportional to the number of active lightpaths, and do not scale well as traffic demands and network grow. With the proposed approach, we show that less information, independent of the amount of traffic demand, is sufficient to determine the shareability of protection channels with remarkable accuracy. Experiments also demonstrate that our approach yields faster computation times with no significant penalty in terms of capacity usage.

Rearrangeable multihop lightwave networks can be dynamically reconfigured to adapt the connectivity among network stations to prevailing traffic conditions. With no limitations on the tunability range of the transmitters and/or receivers allocated to each network station, all connection diagrams can be realized among network stations, within the constraints of the number of transmitters and receivers at each station. Since the number of wavelengths in use may be very large, the tunability range of transmitters/receivers will be restricted, in practice, to some limited set of contiguous wavelengths, or waveband. As a result, all connection diagrams might not be achievable and the network may loose some of its ability to adapt to traffic changes through reconfiguration. We derive bounds on the performance degradation experienced by the network as a function of the tunability restrictions. We then propose and analyze a waveband decomposition, illustrating how networks with good performance can be designed with tunability constraints on the transceivers. We also describe other architectures (subcarrier division multiplexing, multi-fiber physical topology) to which our model and analysis readily apply.

This paper describes a geographically distributed ATM switching architecture that exploits new possibilities offered by lightwave technology. Small modules that provide both an access and an ATM switching function are distributed over some extended geographical area and connected to a passive optical medium. Each module is equipped with some small number of electrooptic transmitters and receivers that provide access to the medium. Assignment of wavelengths to transmitter/receiver pairs create logical channels that are wavelength-multiplexed onto the medium, thus creating a logical connection diagram among the modules. Advantages of the lightwave-based distributed architecture are the huge bandwidth of the medium, a high degree of modularity to facilitate growth, high reliability, and the ability to provide "clear channels" among modules. On the other hand, if the externally offered flow of ATM cells among modules is too uniform, then each module may be capable of supporting only a fraction of the load that could be carried by any port of a fully connected centralized ATM switch with output queueing. Fortunately, under the much more realistic assumption of nonuniform traffic, the independence between the logical connection diagram and the physical topology of the medium can be exploited by reconfiguring the connection diagram to "match" the nonuniformity of the cell traffic. Simulation results show that, as the nonuniformity becomes larger, the reconfiguration technique allows the traffic-handling capability of a distributed switch to match that of a centralized switch.>

Some of today's telecommunications networks have the ability to superimpose some form of logical connectivity, or virtual topology, on top of the underlying physical infrastructure. According to the degree of independence between the logical connectivity and the physical topology, the network can dynamically adapt its virtual topology to track changing traffic conditions, and cope with failure of network equipment. This is particularly true for lightwave networks, where a logical connection diagram is achieved by assignment of transmitting and receiving wavelengths to the network stations that tap into, and communicate over, an infrastructure of fiber glass. Use of tunable transmitters and/or receivers allow the logical connectivity to be optimized to prevailing traffic conditions. With rearrangeability having thus emerged as a powerful network attribute, this paper discusses the reconfiguration phase which is the transition between the current logical connection diagram and a target diagram. We consider here an approach where the network reaches some target connectivity graph through a sequence of intermediate connection diagrams, so that two successive diagrams differ by a single branch-exchange operation. This is an attempt at logically reconfiguring the network in a way that is minimally disruptive to the traffic. We propose and compare three polynomial-time algorithms that search for "short" sequences of branch-exchange operations, so as to minimize the overall reconfiguration time. For networks made of up to 40 stations, theoretical and simulation results show that, when a randomly selected diagram is to be changed to another randomly chosen diagram, the average number of branch-exchange operations required grows linearly with the size of the network.>

A practical approach to the analysis and operation of medium to large-size distributed asynchronous transfer mode (ATM) switches based on an original optical reconfigurable architecture is described. The optical nature of the switch provides enormous bandwidth with input/output port rates on the order of gigabits/second, and the distributed approach is highly modular, creating an easily growable switch. The interconnection pattern between input and output ports is dynamically reconfigurable; the switch can thus exploit nonuniformities in the offered traffic and optimize its connectivity accordingly. For a 24*24 switch, this leads to performance that matches that of a fully connected output buffered ideal centralized switch. Simulation results for a switch of size 81*81 seem to indicate that the traffic-handling capability scales well with the size of the switch when nonuniformity prevails in the offered traffic, a realistic assumption. Clustering techniques would permit the optimization and operation of much larger reconfigurable distributed ATM switches.>

The authors propose a minimally disruptive approach that transitions the network through a sequence of branch exchange operations, so that only two links are disrupted at any given time. It is shown that the problem of finding the shortest sequence, so as to minimize the duration of the reconfiguration phase, is equivalent to the problem of finding a decomposition of an auxiliary graph into the largest number of vertex-disjoint cycles. The authors then propose and compare three different polynomial-time greedy algorithms, on the basis of performance and time complexity. Noticing that the length of a sequence increases at most linearly with the size of the network, the authors derived the average rate of growth from simulation results.>

It is known that, under any sharing policy, the state describing the number of calls established for each class of traffic in steady state has a product-form distribution when the connection time distribution has a rational Laplace transform. The product-form property further holds for arbitrary holding time distribution under coordinate convex sharing policies. For the complete sharing policy case, an aggregate state describing the number of occupied circuits is shown to maintain the product-form property under asymptotic behavior, when the capacity and traffic intensities go to infinity on a comparable scale. Two theorems relative to the asymptotic behavior of the blocking probabilities which provide some insight into the nature of the blocking phenomenon are given. An approximation which reduces the numerical complexity of evaluating the blocking probabilities for the different classes of service to the computation of a single Erlang formula and the determination of the root of a monotonous polynomial function is proposed.>

The optimization problem of rearrangeable multihop lightwave networks is considered. The authors formulate the flow and wavelength assignment problem, when minimizing the maximum flow in the network, as a mixed integer optimization problem subject to linear constraints. The problem is decomposed into two independent subproblems, the wavelength assignment (or connectivity problem) and the flow assignment (or routing problem). A simple heuristic provides a meaningful formulation to the connectivity problem, in a form similar to a transportation problem. An algorithm is then proposed which finds a heuristic initial logical connectivity diagram and the corresponding routing, and then iterates from that solution by applying branch-exchange operations to the connectivity diagram. The algorithm was tested on illustrative traffic matrices for an 8 node network with two transmitters and two receivers per node, and an improvement in achievable throughput over the Perfect Shuffle interconnection pattern was shown in all cases.>

The multihop architecture, which provides a way of tapping the capacity potential available in lightwave networks, is described. Within this architecture, each network node is equipped with some small number of transmitters and receivers, each of which can communicate on one wavelength. Transmitters and receivers are connected to an optical medium, which is physically configured in such a way that the entire spectrum of wavelengths in use is potentially accessible by each node. Then, an assignment of transmit and receive wavelengths to each node defines the logical connectivity among nodes. Furthermore, the use of optically agile transceivers (i.e. slowly tunable lasers or optical filters) permits the logical connectivity to be updated in response to changing traffic patterns and failure/recovery of nodal transmitters and receivers. The flow and wavelength assignment problem is studied. Solutions in which the traffic flows over a derived connectivity diagram such that the largest flow on any link is minimized are sought. Examples of the resulting connectivity diagram and traffic flow are presented for selected nonuniform point-to-point traffic matrices.>

This paper is concerned with performance models and approximations for very large, multi-media networks. Blocking is the traditional performance measure in circuit-switched networks, and will remain as such in multi-rate circuit-switched networks. It is also considered a likely performance measure candidate for resource management and dimensioning in broadband fast packet-switched networks, operated under virtual circuit mode.