Queuing delay is a critical part of end-to-end delay. Existing delay analysis methods in network devices either oversimplify switch scheduling models or are dependent on traffic statistics. To precisely analyze the queue delay, we propose a new analysis method, which has two features: (1) incorporating switch-specific scheduling architectures and algorithms and (2) combining deterministic and stochastic parameter analysis. We take network slicing as an example to test our method. Experiments show that our proposed method reduces the average delay estimation error by over 80% compared to the traditional delay analysis method for network slicing and captures the actual trend.

Network slicing is a promising technique to enable a physical network to support various applications with different demands for network services. In this paper, we propose a traffic scheduler for network soft slicing and evaluate it in a typical soft-slicing case.

Abstract Most existing cross-domain recommendation (CDR) systems apply the embedding and mapping idea to tackle the cold-start user problem and, to this end, they learn a common bridge function to transfer the user preferences from the source domain into the target domain. However, sharing a bridge function for all users inevitably leads to biased recommendations. This paper proposes a novel method, named CDR to cold-start users via categorized preference transfer (CDRCPT), to overcome the shortcomings of existing approaches. First, the embeddings of users and items in both the source and target domain are learned through pretraining and we utilize preference encoder to obtain the preference embeddings of users in the source domain. Second, mini-batch clustering is applied in the source domain to group users according to their preferences; here, each cluster identifies a specific class of users, and each cluster is represented by its center. Finally, the general representation is fed into a meta network to learn a bridge function for each available class of users. Experiments on two real data sets show that our CDRCPT method is effective in improving the accuracy and robustness of recommendations.

Software-Defined Networking (SDN) is introduced to Wide Area Networks (WANs) to facilitate network operations and management. One main advantage of SDN is path programmability, i.e., the ability to change forwarding path of flows by controlling underlying SDN switches to accommodate traffic variations. However, the SDN controllers may experience unexpected failure and thus lose its path programmability. The typical solution is to let active controllers control offline switches, which are controlled by failed controllers, by establishing the remapping between the offline switches and active controllers. However, existing remapping solutions do not consider the impact of controller failure on network performance and cannot exhibit predictable network performance under controller failure. In this paper, we take Traffic Engineering (TE) as a typical network scenario and propose Traffic Engineering-Aware Controller-switcH remapping rEcoveRy named TEACHER. We introduce Traffic-aware Path Programmability (TPP) as a new metric to describe the impact of controller failure on TE and design TEACHER based on this metric to smartly recover offline switches. Simulation results show that TEACHER can increase the overall TPP by up to 83.0% and improves the load balancing performance by up to 58.2% under Sprintlink topology with relatively low computation time, compared with baselines.

Due to the advantages of low cost and high-reliability, the bidirectional asymmetric power flow (BAPF) DC/DC converters are regarded as the competitive DC/DC candidate for power electronics transformers (PETs) in low-penetration renewable energy systems. For this converter, this paper researches the active operation mode and analyzes the circulating current caused by the parallel connection of two full bridges on the low-voltage (LV) side. Based on that, the circulating current suppression method based on extended-phase-shift (EPS) modulation is proposed in the BAFP converters. The simulation results clearly verify the correctness of theoretical analysis and the effectiveness of the proposed method.