Remote Direct Memory Access (RDMA) has been widely deployed in datacenters for its high performance. Large-scale high performance cloud services built on geographically distributed datacenters require long-range RDMA for performance requirements. However, existing RDMA solutions can hardly satisfy the stringent requirements of the emerging large-scale high-performance cloud services built on geo-distributed datacenters in terms of throughput and delay. On the one hand, lossless RDMA suffers from a deep buffer and potential suboptimal throughput for inter-datacenter traffic due to delayed response to Priority Flow Control (PFC) messages. On the other hand, lossy RDMA with selective retransmissions suffers from poor performance when multiple flows with different round-trip times (RTTs) coexist in cross-datacenter scenarios. This article proposesSwing, which expands the high-performance lossless RDMA to long-distance links through PFC-Relay.Swingensures the throughput of long-distance links while minimizing the buffer requirement for long-range RDMA. It enables long-range RDMA without making any modifications to existing in-datacenter networks. The evaluation shows thatSwingcan reduce the average flow completion time (FCT) by 14%-66% in a variety of traffic scenarios.

Datacenter networks enable multiple paths between hosts to provide large bisection bandwidth. It requires load balancers to cope with network uncertainties such as traffic dynamics and topology asymmetry. Existing edge-based load balancing schemes are usually faced with the problem of limited network visibility. This article proposesMeet, a rack-level pooling based load-balancer deployed at the edge that can handle the aformentioned uncertainties.Meetutilizes both passive information as well as active probing to comprehensively sense the network conditions with relatively low cost.Meetdynamically reroutes flows effectively based on the visibility of the network condition.Meethas been tested with extensive flow-level simulations against state-of-the-art load balancers. It outperforms Hermes by up to 10% in the experiments, and outperforms others solutions such as DRILL by up to 50%.Meetrequires no modifications to the switches and is feasible to deploy at the edge.

Campus networks are widely deployed for organizations like universities and large companies. Applications and network-based services require campus networks to guarantee short queue and provide low latency and large bandwidth. However, the widely adopted packet-loss-based congestion control mechanism in client hosts builds up long queues in the switch buffer, which is prone to packet loss in burst scenarios, resulting in great network delay. Therefore, a scheme for efficiently controlling queue length of shallow buffer switches in campus networks is urgently needed. Explicit Congestion Notification(ECN) as an explicit feedback mechanism is widely adopted in data center networks to build lossless networks. In this paper, we propose Clean, an efficient queue length control scheme based on transparent ECN-proxy for campus networks. Clean is able to exert fine-grained control over arbitrary client TCP stacks by enforcing per-flow congestion control in the access point(AP). It allows the campus network switches to maintain a low queue length, resulting in high throughput, low latency and zero packet loss. Evaluation results demonstrate that Clean reduces the maximum queue length of the switch by 86% and reduces the 99th percentile latency by 85%. Clean also achieves zero packet loss in burst scenarios.

The Internet of Things (IoT) increases the number of connected devices and supports the ever-growing complexity of applications. Owing to the constrained physical size, the IoT devices can significantly enhance the computational capacity by offloading computation-intensive tasks to the resource-rich edge servers deployed at the base station (BS) via wireless networks. However, how to achieve optimal resource scheduling remains a challenge due to stochastic task arrivals, time-varying wireless channels, and imperfect estimation of channel state information (CSI). In this article, by virtue of the Lyapunov optimization technique, we propose the toward optimal resource scheduling algorithm under imperfect CSI (TORS) to optimize resource scheduling in an IoT environment. A convex transmit power and subchannel allocation problem in TORS is formulated. This problem is then solved via the Lagrangian dual decomposition method. We derive analytical bounds for the time-averaged system throughput and queue backlog. We show that TORS can arbitrarily approach the optimal system throughput by simply tuning an introduced control parameter $\beta $ without prior knowledge of stochastic task arrivals and the CSI of wireless channels. Extensive simulation results confirm the theoretical analysis on the performance of TORS.

With the rapid development of Internet of Things (IoT), mobile crowdsensing (MCS), i.e., outsourcing sensing tasks to mobile devices or vehicles, has been proposed to address the problem of data collection in the scenarios such as smart city. Despite its benefits for a wide range of applications, MCS lacks an efficient incentive mechanism, restricting the development of IoT applications, especially for Internet of Vehicles (IoV)-a typical example of IoT applications; this is because vehicles are usually reluctant to participate these sensing tasks. Moreover, in practice, some sensing tasks may arrive suddenly (called an emergent task) in the IoV environment, but the resources of a single vehicle may be insufficient to handle, and thus multivehicles collaboration is required. In this case, the incentive mechanisms for the participation of multiple vehicles and the task scheduling for their collaborations are collectively needed. To address this important problem, we first propose a new model for the scenario of two vehicles collaboration, considering the situation of the emergent appearance of a task. In this model, for a general sensing task, we propose a bidding mechanism to better encourage vehicles to contribute their resources, and the tasks for those vehicles are scheduled accordingly. Second, for an emergent task, a novel time-window-based method is devised to manage the tasks among vehicles and to incent the vehicles to participate. Finally, we develop a blockchain framework to achieve the secured information exchange through smart contract for the proposed models in IoV.

Modern data centers are the host for multitude of large-scale distributed applications. These applications generate tremendous amount of network flows to complete their tasks. At this scale, efficient network control manages the network traffic at the level of flow aggregates (or slices ) who need to share the network with respect to operator’s proportionality policy. Existing slice scheduling mechanisms can not meet this goal in multi-path data center networks. Hence, in this paper, we aim to fulfil this goal and satisfy the congestion proportionality policy for network sharing. The policy is applied to the traffic traversing congested links in the network. We propose Uranus, a novel slice scheduler based on a combination of flow-level control mechanisms. The scheduler implements two-tier weight allocation to individual flows. Then, relying on a non-blocking big switch abstraction, slice weights are allocated at the inter-rack level by aggregating the weights of rack-to-rack flows. Finally, Uranus can dynamically divide the rack-level weight to its constituent flows. We also implement Weighted Virtual Congestion Control (WVCC), an end-host shim-layer that enforces weighted bandwidth sharing among competing flows. Trace-driven NS3 simulations demonstrate that Uranus closely approximates the congestion-proportionality and is able to improve the proportional fairness by 31.49% compared to the state-of-the-art mechanisms. The results also prove Uranus’s capability of intra-slice scheduling optimization. Moreover, Uranus’s throughput in Clos fabrics outperforms the state-of-the-art mechanisms by 10%.