Search

As modern communication networks are growing more complicated and dynamic, designing a good Traffic Engineering (TE) policy becomes difficult due to the complexity of solving the optimal traffic scheduling problem. Deep Reinforcement Learning (DRL) provides us with a chance to design a model-free TE scheme through machine learning. However, existing DRL-based TE solutions cannot be applied to large networks. In this article, we propose to combine the control theory and DRL to design a TE scheme. Our proposed scheme ScaleDRL employs the idea from the pinning control theory to select a subset of links in the network and name them critical links. Based on the traffic distribution information, we use a DRL algorithm to dynamically adjust the link weights for the critical links. Through a weighted shortest path algorithm, the forwarding paths of the flows can be dynamically adjusted. The packet-level simulation shows that ScaleDRL reduces the average end-to-end transmission delay by up to 39% compared to the state-of-the-art in different network topologies.

Network Function Virtualization (NFV) technology utilizes software to implement network function as virtual instances, which reduces the cost on various middlebox hardware. A Virtual Network Function (VNF) instance requires multiple resource types in the network (e.g., CPU, memory). Therefore, an efficient VNF placement policy should consider both the resource utilization problem and the Quality of Service (QoS) of flows, which is proved NP-hard. Recent studies employ Deep Reinforcement Learning (DRL) to solve the VNF placement problem, but existing DRL-based solutions cannot generalize well to different topologies. In this letter, we propose to combine the advantage of DRL and Graph Neural Network (GNN) to design our VNF placement scheme DeepOpt. Simulation results show that DeepOpt outperforms the state-of-the-art VNF placement schemes and shows a much better generalization ability in different network topologies.

In this letter, we model the dynamic instance switching problem based on the fact that some routing instances could have common vulnerabilities. We propose the correlation-aware dynamic instance switching (CDIS) algorithm to solve the problem. The simulation results show that, compared with baseline algorithms, CDIS improves the network compromised ratio by at least 10%.

Many existing works assign diverse variants to routing nodes in the network to prevent security threat (e.g., worm attack). However, the works assume no common vulnerabilities among diverse variants, which is not always satisfied in the real world. In this letter, we consider that some variants have common vulnerabilities and propose the common vulnerability-aware diverse variant placement problem. We formulate the problem as an integer programming optimization problem with NP-hard complexity based on a new metric named the Infected Ratio Expectation. Furthermore, we devise algorithms to solve the problem for the static network and the network for extension. The simulation results show that compared with the baseline algorithms, our algorithms effectively restrain the worm spread by about 42%.

This letter proposes a smart inter- and intra-datacenter workload dispatching scheme, Joint Electricity price-aware and Cooling efficiency-aware load balancing (JEC), to cut the electricity cost of distributed datacenters. Evaluation shows JEC outperforms existing schemes and achieves significant reduction on the total electricity cost of distributed datacenters.