Rearrangeable Nonblocking Research Articles

Integrated folding 4/spl times/4 optical matrix switch with total internal reflection mirrors on SOI by anisotropic chemical etching

A folding rearrangeable nonblocking 4×4 optical matrix switch was designed and fabricated on silicon-on-insulator wafer. To compress chip size, switch elements (SEs) were interconnected by total internal reflection (TIR) mirrors instead of conventional S-bends. For obtaining smooth interfaces, potassium hydroxide anisotropic chemical etching of silicon was utilized to make the matrix switch for the first time. The device has a compact size of 20×1.6 mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and a fast response of 7.5 μs. The power consumption of each 2×2 SE and the average excess loss per mirror were 145 mW and -1.1 dB, respectively. Low path dependence of /spl plusmn/0.7 dB in total excess loss was obtained because of the symmetry of propagation paths in this novel matrix switch.

Scheduling length for switching element disjoint multicasting in Banyan-type switching networks

Due to the stringent bit-error requirement in fiber optics, preventing the forthcoming crosstalk at switching elements (SEs) is very crucial in the large-scale photonic switches. In this paper, we consider the SE-disjoint multicasting for a photonic Banyan-type switching network. This ensures that at most, one connection holds each SE in a given time thus, neither photonic crosstalk nor link blocking will arise in the switching network implemented with optical devices such as directional couplers, splitters and combiners. Routing a set of connections under such constraint usually takes several routing rounds hence, it is desirable to keep the number of rounds (i.e., scheduling length) to a minimum. Unfortunately, finding the optimal length is NP-complete in general, we propose an algorithm that seeks an approximation solution less than double of the optimal upper bound. The bound permits the Banyan-type multicasting network to be rearrangeable nonblocking as well as crosstalk-free. It is given that the same bound guarantees wide-sense nonblocking for multicast connections, provided that the multicasting capability of the network is restricted to the second half of the whole stages, and strictly nonblocking for one-to-one connections, yet allowing to be free from the crosstalk. We also consider other crosstalk-free multicasting and the link-disjoint multicasting for the Banyan network. The theory developed in this paper gives a unified foundation on designing nonblocking and crosstalk-free photonic Banyan-type networks under the multicast connections.

A new conference network for group communication

A conference refers to a group of members in a network which communicate with each other within the group. In this paper, we propose a novel design for a conference network which supports multiple disjoint conferences. The major component of the network is a multistage network composed of switch modules with fan-in and fan-out capability. A fast self-routing algorithm is developed for setting up routing paths in the conference network. For an n/spl times/n conference network we design, the hardware cost is O(n log n), and the routing time and communication delay vary from O(1) to O(log n) depending on where the conference is allocated in the network. As can be seen, the new conference network is superior to existing designs in terms of hardware cost, routing time and communication delay. The conference network proposed is rearrangeable nonblocking in general, and is strictly nonblocking under some conference service policy. It can be used in applications that require efficient or real-time group communication.

Compact polarization-based all-optical interconnection systems with growth capability

All-optical communication requires all-optical interconnections, thus leading to reliable, fast, and flexible modular communication means in future systems. Free-space approaches are advantageous since they fully use the two dimensions optics offer. A folded architecture based on a polarization code is proposed for dynamic optical interconnection. The suggested systems are compact and appropriate for both intracomputer and intercomputer communication. The modularity of the proposed architecture is presented, and a growth rule for the fully connected versions of the system is introduced. The proposed approach significantly reduces both the price of the interconnection systems and their complexity. Presented are 4 x 4 and 8 x 8 fully connected switches, a rearrangeable nonblocking 4 x 4 switch, and a crossbar architecture.

Distributed routing protocols for ATM extended Banyan networks

It is well known that a multistage banyan network, which is a single-path blocking structure, becomes rearrangeable nonblocking in a circuit-switching environment if the number of its stages is increased so as to obtain a Benes network. Banyan networks, provided with a shared queue in each switching element, have often been proposed as the core of an interconnection network for an ATM packet switching environment. In this scenario, if the classical interstage backpressure protocols are used, adding stages to a banyan network can even degrade the banyan network performance, in spite of the multipath capability given by the additional stages. A class of new simple interstage protocols is here defined to operate in the added stages of the banyan network so that a sort of sharing of the queueing capability in each added stage is accomplished. Large improvements in the traffic performance of these extended banyan networks are obtained, especially in the region of offered loads providing a low packet loss probability.

Rearrangeable nonblocking polymer waveguide thermo-optic4×4 switching matrix with low power consumption at 1.55 µm

A rearrangeable nonblocking polymer waveguide thermo-optic 4×4 directional-coupler-type switching matrix with low power consumption operating at 1.55 µm is demonstrated for the first time. The rearrangeable nonblocking 4×4 matrix consists of eight 2×2 switches. The power consumption of each switching element is 30 mW. A fibre-to-fibre insertion loss of less than 9 dB was measured and the polarisation sensitivity is less than 0.5 dB. The crosstalk was found to be between –17.5 and –32.5 dB for different switching configurations. The response time of the device is less than 1 ms.

4×4 directional coupler switch matrix with an InGaAlAs/InAlAs multiquantum well structure

A 4×4 directional coupler switch matrix is developed which uses, for the first time, the quantum confined Stark effect of InGaAlAs/InAlAs multiquantum well structures. The rearrangeable nonblocking 4×4 network with six 2×2 switches is shown to be perfectly functional with switching voltages between 5 and 6 V and crosstalk below −17 dB in all the operation states.

N:1 connection switching networks suited for time division switching

Two types of n:1 non-blocking switching networks are proposed. One is the Cascade Clos Network, which is non-blocking under the condition of simultaneous origination of multiconnection calls. The other is the Cascade Benes Network, which is rearrangeable non-blocking. Then, both switching networks are applied to TSTST time division switching networks. Both networks can also be combined in TSTST configuration. This is very flexible and suitable for a multi-service switching network in broadband-ISDN.

Performance of rearrangeable nonblocking 4*4 switch matrices on LiNbO/sub 3/

The design, fabrication, and characterization of rearrangeable nonblocking 4*4 switch matrices and the development of a novel ITO (indium-tin-oxide)/Au multilayer electrode that leads to low switching voltages and low DC drift is reported. Results on electrode systems, insertion loss, crosstalk, tolerances in the coupling length, and stability obtained for eight fabricated matrices are given. In comparison to the SiO/sub 2/ buffer layers, a reduction in the switching voltage of a factor of 0.66 has been achieved. Insertion losses of fiber pigtailed modules are in the range between 4 and 7 dB. The crosstalk has still to be improved. The stability of the operating points of the switches has been analyzed, showing that the devices must be operated in closed dark housings with a passivation layer in order to avoid optical damage effects from ambient light and to protect them against physical and chemical influences.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>