TY - JOUR
T1 - A new discrete-time multi-constrained K-winner-take-all recurrent network and its application to prioritized scheduling
AU - Tien, Po-Lung
PY - 2017/11/1
Y1 - 2017/11/1
N2 - 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.
AB - 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.
KW - Energy saving
KW - K-winner take all
KW - Parallel computation
KW - Prioritized scheduling
KW - Quality of service (QoS)
KW - Recurrent neural network
UR - http://www.scopus.com/inward/record.url?scp=85037043560&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2016.2600410
DO - 10.1109/TNNLS.2016.2600410
M3 - Article
C2 - 28113608
AN - SCOPUS:85037043560
SN - 2162-237X
VL - 28
SP - 2674
EP - 2685
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 11
M1 - 7553490
ER -