Containers have become the de facto choice for major cloud services. Meanwhile, with demands for extremely high performance, data centers have widely adopted RDMA for their online services. RDMA virtualization is the critical technology that enables RDMA for containers. Hybrid RDMA virtualization leverages the software flexibility in the control path, and keeps the native performance in the data path. Thus, it is the best choice for RDMA virtualization. State-of-the-art hybrid RDMA virtualization cannot address containerspecific problems. This paper proposes DockRDMA, the first hybrid RDMA virtualization solution for containerized clouds. DockRDMA develops several mechanisms, including embedding physical addresses in virtual ones to provide efficient address translation, hybrid network policy enforcement at scale, a general virtual RDMA NIC initialization method to be compatible with all container platforms, and namespace checking to protect the RDMA NIC instances. Evaluation results show that DockRDMA provides bare-metal RDMA performance in the data path, and almost native communication setup time in the control path. Compared with the state-of-the-art hybrid virtualization technology, DockRDMA reduces Hadoop job completion time by 6%. It offers seamless integration with existing container platforms, protects critical information of RDMA NIC instances, and exhibits excellent scalability to meet diverse network policies required by different containers.

Nonlinear spiking neural P (NSNP) systems are a class of neural-like computational models inspired from the nonlinear mechanism of spiking neurons. NSNP systems have a distinguishing feature: nonlinear spiking mechanism. To handle edge detection of images, this paper proposes a variant, nonlinear spiking neural P (NSNP) systems with two outputs (TO), termed as NSNP-TO systems. Based on NSNP-TO system, an edge detection framework is developed, termed as ED-NSNP detector. The detection ability of ED-NSNP detector relies on two convolutional kernels. To obtain good detection performance, particle swarm optimization (PSO) is used to optimize the parameters of the two convolutional kernels. The proposed ED-NSNP detector is evaluated on several open benchmark images and compared with seven baseline edge detection methods. The comparison results indicate the availability and effectiveness of the proposed ED-NSNP detector.

Nonlinear spiking neural P (NSNP) systems are a recently developed theoretical model, which is abstracted by nonlinear spiking mechanism of biological neurons. NSNP systems have a nonlinear structure and the potential to describe nonlinear dynamic systems. Based on NSNP systems, a novel time series forecasting approach is developed in this paper. During the training phase, a time series is first converted to frequency domain by using a redundant wavelet transform, and then according to the frequency data, an NSNP system is automatically constructed and adaptively trained in frequency domain. Then, the well-trained NSNP system can automatically generate sequence data for future time as the prediction results. Eight benchmark time series data sets and two real-life time series data sets are utilized to compare the proposed approach with several state-of-the-art forecasting approaches. The comparison results demonstrate availability and effectiveness of the proposed forecasting approach.

Coupled neural P (CNP) systems are a recently developed Turing-universal, distributed and parallel computing model, combining the spiking and coupled mechanisms of neurons. This paper focuses on how to apply CNP systems to handle the fusion of multi-modality medical images and proposes a novel image fusion method. Based on two CNP systems with local topology, an image fusion framework in nonsubsampled shearlet transform (NSST) domain is designed, where the two CNP systems are used to control the fusion of low-frequency NSST coefficients. The proposed fusion method is evaluated on 20 pairs of multi-modality medical images and compared with seven previous fusion methods and two deep-learning-based fusion methods. Quantitative and qualitative experimental results demonstrate the advantage of the proposed fusion method in terms of visual quality and fusion performance.

Today, considerable Internet traffic is sent from datacenter and heads for users. The network characteristics of connections served by servers in datacenters are usually diverse. As a result, a specific congestion control algorithm hardly accommodates the heterogeneity and performs well in various scenarios. In this work, we present Rein — a novel framework for Internet congestion control. With Rein, diverse congestion control algorithms can be assigned purposely to connections in one server to adapt to heterogeneity. We design and implement Rein in Linux, and the experiments validate that Rein is capable of smoothly switching among various candidate algorithms on the fly to achieve potential performance gain. Meanwhile, the overheads introduced by Rein are moderate and acceptable.

Conventional feature detection algorithms are largely based on clustered two-dimensional (2D) blocks of information. However, corners located at the centre of gradually greying blocks of information cannot be extracted using these algorithms. The edge feature points described by the algorithms are often affected by background changes, leading to significant differences in the descriptors for the same feature. These issues are detrimental to subsequent matching processes. Therefore, we propose a new feature detection method that will provide more useful corner information for subsequent tracking and detection processes, particularly for edge features. The edge information of corners is used to search for points that satisfy the requirements for inner greyscale consistency. The points are then used to construct point-symmetric structures. The zeroth-order inner greyscale data, first-order gradient orientation differences, and angular directions of the point-symmetric connections of the structures are considered structural attributes, which help search for feature points. Similar feature points are then clustered using a hierarchical clustering algorithm, followed by extracting the feature points from point pair features of the same type. It was experimentally demonstrated that the proposed point-symmetric structural features would help increase the number of valid feature points that can be extracted from an image.

This paper proposes a new variant of spiking neural P systems (in short, SNP systems), nonlinear spiking neural P systems (in short, NSNP systems). In NSNP systems, the state of each neuron is denoted by a real number, and a real configuration vector is used to characterize the state of the whole system. A new type of spiking rules, nonlinear spiking rules, is introduced to handle the neuron's firing, where the consumed and generated amounts of spikes are often expressed by the nonlinear functions of the state of the neuron. NSNP systems are a class of distributed parallel and nondeterministic computing systems. The computational power of NSNP systems is discussed. Specifically, it is proved that NSNP systems as number-generating/accepting devices are Turing-universal. Moreover, we establish two small universal NSNP systems for function computing and number generator, containing 117 neurons and 164 neurons, respectively.

In recent years, the growth in popularity of mobile video streaming services is unbroken. There are tremendous demands for video streaming over wireless networks. Currently, most video streaming is over HTTP. Up to now, HTTP-based adaptive video streaming is standardized as DASH, where a client-side video player can dynamically pick the bitrate level according to the perceived network conditions. Actually, not only the available bandwidth drastically varies due to wireless network properties, but also the chunk sizes in the same bitrate level significantly fluctuate, which also influences the bitrate adaptation. However, existing bitrate adaptation algorithms mostly focus on available bandwidth but do not involve chunk size variation, leading to performance losses. In this paper, we theoretically analyze the influence of chunk size variation on bitrate adaptation performance in wireless networks. Based on DASH system features, we build a general model describing playback buffer evolution. Applying stochastic theories, we respectively analyze the influence of the chunk size variation on rebuffering probability, average bitrate, and bitrate switching interval. Furthermore, based on theoretical insights, we provide several suggestions for algorithm designing and rate encoding, and also design a simple bitrate adaptation algorithm. Extensive simulations verify our insights, suggestions, and designed algorithm effectiveness.

As a manifold learning algorithm, unsupervised large graph embedding (ULGE) has been proposed to deal with large-scale dataset for clustering. This paper improves ULGE and proposes a graph embedding-based ensemble learning (GEEL) algorithm. We take the dimensionality reduction algorithm in ULGE and the K-means clustering algorithm as an individual learner in our ensemble learning. For each individual learner, the K-means clustering method is first used to generate anchors. Then, the low-dimensional embedding of the sample data is obtained. Finally, the K-means clustering method is used again and performed on the low-dimensional data, which results in a clustering. The diversity of ensemble learning lies on the unstable of K-means. To combine multiple clusterings, we first match these clusterings with a reference clustering using the bestMap method, where the reference clustering is randomly chosen from multiple ones. A majority voting rule is adopted to these matched clusterings to generate the final clustering. A large number of experiments show the efficiency and effectiveness of the proposed method.

Network applications are widely distributed nowadays, most of which have steep demand on response time. Deploying multi-threaded design on multicore systems is beneficial of scaling applications' performance, but also requires an efficient TCP stack to support. mTCP is a highly scalable userlevel TCP stack fruitful in promoting scalability and improving performance, therefore adopted by more and more applications. However, the original mTCP APIs are not compatible with the in-kernel function calls in form, thus impeding the transparent employment as well as the convenient transplant of mTCP stack for users. To overcome the deficiency, we propose a transparent socket layer for mTCP (mTSL), which overrides the native mTCP APIs and redirects original system calls to our customized versions. Finally, mTSL not only achieves mTCP stack's thorough transparency to applications, but maintains the high performance of mTCP and outperforms Linux kernel stack by 8.9× with respect to throughput on a message benchmark as well as 1.44×~6.49× in terms of transaction rate for a real application.

Recent academic and industrial work is exploring the challenges of using RDMA over Ethernet, to support highly reliable, latency-sensitive services in today's datacenters. Previous work on the high-speed packet I/O like netmap, DPDK, etc., and high-performance user-level stacks like mTCP, IX etc., rekindles our inspirations to implement a high-performance software RDMA over commodity Ethernet devices.

More and more commercial video players use bitrate adaptation to adjust video quality according to varying network conditions. Optimization-based approaches are widely used for bitrate adaptation in Dynamic Adaptive Streaming over HTTP (DASH). Essentially, the optimization problem is solved based on the prediction of buffer dynamics. However, stochastic chunk size deviates observably the buffer occupancy from the expected value, making the evolution hard to predict. In order to get rid of this effect and improve the prediction accuracy for buffer occupancy, we propose an algorithm based on markov decision process with incorporating chunk size information so that only the network capacity variation need to be considered in the decision-making process. Experiment results show that our solution can effectively eliminate performance oscillation induced by variable chunk size and achieve a good QoE.

Recently, HTTP-based adaptive video streaming has been widely adopted in the Internet. Up to now, HTTP-based adaptive video streaming is standardized as Dynamic Adaptive Streaming over HTTP (DASH), where a client-side video player can dynamically pick the bitrate level according to the perceived network conditions. Actually, not only the available bandwidth is varying, but also the chunk sizes in the same bitrate level significantly fluctuate, which also influences the bitrate adaptation. However, existing bitrate adaptation algorithms do not accurately involve the chunk size variation, leading to performance losses. In this paper, we theoretically analyze the influence of chunk size variation on bitrate adaptation performance. Based on DASH system features, we build a general model describing the playback buffer evolution. Applying stochastic theories, we respectively analyze the influence of the chunk size variation on rebuffering probability and average bitrate level. Furthermore, based on theoretical insights, we provide several recommendations for algorithm designing and rate encoding, and also propose a simple bitrate adaptation algorithm. Extensive simulations verify our insights as well as the efficiency of the proposed recommendations and algorithm.

Today's data center servers are equipped with high speed and complex network adaptors, featuring an array of functions, e.g. hardware TX/RX queues, packet filters, rate limiters, etc. Recent work like IX, Arrakis, MultiStack has made us rekindle the user-level network stacks' innovation utilizing these commodity network adaptors. In this paper, we revisit the idea to move stacks' design from in-kernel shared space into user-level application-specific dedicated one, for high performance and ease of development and deployment. We provide an unified control plane TAPM to exploit and manage the hardware adaptors' resources, and a dedicated data plane hwTAP to support different user-level stacks. TAPM and hwTAP highlight the utilization of hardware features from commodity network adaptors, to support the innovation of different user-level stacks. Experiments show that the hardware switching module can keep the input rate without any overheads and costs. TAPM could configure the hwTAP dynamically. Our run-to-completion user-level stack also achieves high throughput and low latency.