Queue-aware Network Control Algorithm with a High Quantum Computing Readiness-Evaluated in Discrete-time Flow Simulator for Fat-Pipe Networks

TL;DR

The paper tackles NP-hard resource optimization in SDN-enabled wide-area optical networks under bursty traffic by introducing two ILP formulations: a long-term resource provisioning ILP and a short-term dynamic reoccupation ILP guided by queue lengths. These ILPs are designed to be solvable on quantum annealers via QUBO mappings, with evaluation conducted through a discrete-time flow simulator that models backlog and losses. Results show that the short-term reoccupation approach can reduce traffic losses by roughly a factor of two and distribute burstiness more evenly across paths, steering networks toward zero-margin operation under heavy load. The proposed framework demonstrates a path toward ultra-fast network reconfiguration in fat-pipe networks, leveraging SDN centralization and quantum accelerators, while noting latency considerations for practical deployment in large-scale or metro-based settings.

Abstract

The emerging technology of quantum computing has the potential to change the way how problems will be solved in the future. This work presents a centralized network control algorithm executable on already existing quantum computer which are based on the principle of quantum annealing like the D-Wave Advantage. We introduce a resource reoccupation algorithm for traffic engineering in wide-area networks. The proposed optimization algorithm changes traffic steering and resource allocation in case of overloaded transceivers. Settings of active components like fiber amplifiers and transceivers are not changed for the reason of stability. This algorithm is beneficial in situations when the network traffic is fluctuating in time scales of seconds or spontaneous bursts occur. Further, we developed a discrete-time flow simulator to study the algorithm's performance in wide-area networks. Our network simulator considers backlog and loss modeling of buffered transmission lines. Concurring flows are handled equally in case of a backlog. This work provides an ILP-based network configuring algorithm that is applicable on quantum annealing computers. We showcase, that traffic losses can be reduced significantly by a factor of 2 if a resource reoccupation algorithm is applied in a network with bursty traffic. As resources are used more efficiently by reoccupation in heavy load situations, overprovisioning of networks can be reduced. Thus, this new form of network operation leads toward a zero-margin network. We show that our newly introduced network simulator enables analyses of short-time effects like buffering within fat-pipe networks. As the calculation of network configurations in real-sized networks is typically time-consuming, quantum computing can enable the proposed network configuration algorithm for application in real-sized wide-area networks.

Figures (9)

• Figure 1: Conceptional architecture of SDN-based network control for wide-area networks with a quantum annealer as optimizer.
• Figure 2: Time discrete model of parallel circuits along optical circuit path c for aggregated traffic flows. Overloads are handled by lossy buffering, realized with a time discrete queue model.
• Figure 3: () Network nodes, () fiber links, () network demand of interest, () network demands that share circuit paths with the demand of interest, () circuit paths used to realize the demand of interest as traffic flow.
• Figure 4: () Data rate of a traffic demand with a well-defined burstiness. () Time instances of burst events with negative exponential distributed inter arrival times. () Mean value per burst, overlayed by short-term fluctuations. () Long-term mean value staying constant for minutes or changing slowly.
• Figure 5: The data rate of a demand, cf. Fig. \ref{['fig:data_rate_bursts']}, is normal distributed if traffic traces are analyzed over a long time duration. In short-time analyses the data rate shows a multi-modal distribution, which is caused by the traffic's burstiness.