A New Discrete-Time Multi-Constrained $K$-Winner-Take-All Recurrent Network and Its Application to Prioritized Scheduling.

In this paper, we propose a novel discrete-time recurrent neural network aiming to resolve a new class of multi-constrained K-winner-take-all (K-WTA) problems. By facilitating specially designed asymmetric neuron weights, the proposed model is capable of operating in a fully parallel manner, thereby allowing true digital implementation. This paper also provides theorems that delineate the theoretical upper bound of the convergence latency, which is merely O(K). Importantly, via simulations, the average convergence time is close to O(1) in most general cases. Moreover, as the multi-constrained K-WTA problem degenerates to a traditional single-constrained problem, the upper bound becomes exactly two parallel iterations, which significantly outperforms the existing K-WTA models. By associating the neurons and neuron weights with routing paths and path priorities, respectively, we then apply the model to a prioritized flow scheduler for the data center networks. Through extensive simulations, we demonstrate that the proposed scheduler converges to the equilibrium state within near-constant time for different scales of networks while achieving maximal throughput, quality-of-service priority differentiation, and minimum energy consumption, subject to the flow contention-free constraints.

Design and demonstration of a colorless WDM-OFDMA PON system architecture achieving symmetric 20-Gb/s transmissions with residual interference compensation.

In this paper, we propose a two-tiered colorless WDM-OFDMA PON system architecture that draws strengths from each individual WDM and OFDM PON systems. Specifically, the two-tiered architecture enables a colorless transceiver to be shared by a group of ONUs, resulting in drastic reduction of the system cost. For achieving colorlessness via reusing downstream light sources, we discover the residual power of downstream signal unexpectedly springs back after transmissions, causing severe interference to the upstream signal, and thus limiting the data rate of the upstream signal. We devise a method of adopting a common dispersion compensation module at OLT to reduce the residual power over all wavelengths. Experimental results show that, with an improvement of upstream signal's SNR up to 10 dB, the system successfully achieves 20-Gb/s bidirectional OFDM-signal transmissions on the same wavelength over a 20-km SMF.