In the data center network, traffic has a distinct heavy-tailed distribution characteristic, with the minority of throughput-sensitive elephant flows occupy most of the bandwidth and the majority of latency-sensitive mice flows require low latency. Therefore, it is very important to predict the network flow size and make a reasonable balanced scheduling. Currently, the traditional elephant flow detection schemes based on thresholds have poor accuracy and low granularity, while the intelligent detection schemes based on SDN has a certain flow scheduling response delay. For this reason, a two-stage online elephant flow prediction method for load balancing (OPLB) is proposed. Based on the programmable data plane, OPLB first pre-identifies the elephant flow by extracting the stateless features of the first packet of the network flow arriving at the switch. Secondly, the size of the elephant flow is predicted by extracting the features of the first${n}$packets of the flow. Finally, the detected elephant and mice flows are balanced to high throughput and low latency paths. Combined with the computing and storage capabilities of the programmable switch, the models and parameters in OPLB can be updated online by mapping the trained classification and prediction decision tree models to the matching-action pipelines of the programmable switch, thus achieving dynamic load balancing. We prototype OPLB in P4 software simulation environment and evaluate it with packet traces from the university data centers (UNI). The experiment shows that the accuracy of classification and prediction reached 89.3% when the proportion of elephant flow was 20%. At the same time, compared to the scheme that only uses single stage elephant flow prediction, OPLB reduces the amount of information collected by the switch by about 40% when the elephant flow proportion is 20%.

Compared with traditional machine learning model, graph neural networks (GNNs) have distinct advantages in processing unstructured data. However, the vulnerability of GNNs cannot be ignored. Graph universal adversarial attack is a special type of attack on graph which can attack any targeted victim by flipping edges connected to anchor nodes. In this paper, we propose the forward-derivative-based graph universal adversarial attack (FDGUA). Firstly, we point out that one node as training data is sufficient to generate an effective continuous attack vector. Then we discretize the continuous attack vector based on forward derivative. FDGUA can achieve impressive attack performance that three anchor nodes can result in attack success rate higher than 80% for the dataset Cora. Moreover, we propose the first graph universal adversarial training (GUAT) to defend against universal adversarial attack. Experiments show that GUAT can effectively improve the robustness of the GNNs without degrading the accuracy of the model.

IN THE above article[1], in(5), the allocated bandwidth is corrected as

Searching for active modules, i.e., regions showing striking changes in molecular activity in biological networks is important to reveal regulatory and signaling mechanisms of biological systems. Most existing active modules identification methods are based on protein-protein interaction networks or metabolic networks, which require comprehensive and accurate prior knowledge. On the other hand, weighted gene co-expression networks (WGCNs) are purely constructed from gene expression profiles. However, existing WGCN analysis methods are designed for identifying functional modules but not capable of identifying active modules. There is an urgent need to develop an active module identification algorithm for WGCNs to discover regulatory and signaling mechanism associating with a given cellular response. To address this urgent need, we propose a novel algorithm called active modules on the multi-layer weighted (co-expression gene) network, based on a continuous optimization approach (AMOUNTAIN). The algorithm is capable of identifying active modules not only from single-layer WGCNs but also from multilayer WGCNs such as cross-species and dynamic WGCNs. We first validate AMOUNTAIN on a synthetic benchmark dataset. We then apply AMOUNTAIN to WGCNs constructed from Th17 differentiation gene expression datasets of human and mouse, which include a single layer, a cross-species two-layer and a multilayer dynamic WGCNs. The identified active modules from WGCNs are enriched by known protein-protein interactions, and more importantly, they reveal some interesting and important regulatory and signaling mechanisms of Th17 cell differentiation.

With the emerging paradigm of Virtual Network and Network Function Virtualization (NFV), the data center operator can flexibly manage the network to reduce Operating Expenditures (OPEX) and Capital Expenditures (CAPEX). Some new issues including the assignment of Virtual Network Functions (VNFs) and Service Function Chain (SFC) scheduling should be considered to apply in the communication. Mathematically, the SFC scheduling process can be formulated as a queuing system, and every server installed with VNF instances can be regarded as a service node, where batched requests are parallel submitted and processed one after another. In the management of SFC, the cloud service provider needs to resolve the problem of network congestion. Latency and throughput are two important but contradictory indexes in the network management, and both of them are deserved to be optimized during the scheduling of SFC requests. In this paper, different from most existing studies, we focus on the service rate control problem in the scheduling of SFC requests. Firstly, we formulate this problem as an integer programming problem. Through a cooperative game approach, a Nash bargaining based model is proposed to jointly optimize the latency and throughput, which is proven to provide fair performance guarantees by both theoretical analysis and simulation. To improve the scalability of the proposed algorithm, we also design a polynomial two-phase heuristic to perform Pareto optimization. Simulation evaluation shows that the proposed algorithm can implement balanced traffic scheduling and avoid excessive server latency caused by network congestion.

Community structure, a foundational concept in understanding networks, is one of the most important properties of dynamic networks. A large number of dynamic community detection methods proposed are based on the temporal smoothness framework that the abrupt change of clustering within a short perio d is undesirable. However, how to improve the community detection performance by combining network topology information in a short period is a challenging problem. Additionally, previous efforts on utilizing such properties are insufficient. In this paper, we introduce the geometric structure of a network to represent the temporal smoothness in a short time and propose a novel Dynamic Graph Regularized Symmetric NMF method (DGR-SNMF) to detect the community in dynamic networks. This method combines geometric structure information sufficiently in current detecting process by Symmetric Non-negative Matrix Factorization (SNMF). We also prove the convergence of the iterative update rules by constructing auxiliary functions. Extensive experiments on multiple synthetic networks and two real-world datasets demonstrate that the proposed DGR-SNMF method outperforms the state-of-the-art algorithms on detecting dynamic community.

Network representation learning aims at learning a low-dimensional vector for each node in a network, which has attracted increasing research interests recently. However, most existing approaches only use topology information of each node and ignore its attributes information. In this paper, we pro pose an Improved Attributed Node Random Walks(IANRW) framework, which constructs the neighborhood of an attributed node and then leverages the skip-gram model to perform node embeddings. The method can be able to flexibly incorporate both the topology and attribute information. Additionally, it can easily deal with missing data and be applied to large networks. Extensive experiments on six datasets show that IANRW outperforms many state-of-the-art embedding models and can improve various attributed networks mining tasks.

Deduplication has become a widely deployed technology in cloud data centers to improve IT resources efficiency. However, traditional techniques face a great challenge in big data deduplication to strike a sensible tradeoff between the conflicting goals of scalable deduplication throughput and high duplicate elimination ratio. We propose AppDedupe, an application-aware scalable inline distributed deduplication framework in cloud environment, to meet this challenge by exploiting application awareness, data similarity and locality to optimize distributed deduplication with inter-node two-tiered data routing and intra-node application-aware deduplication. It first dispenses application data at file level with an application-aware routing to keep application locality, then assigns similar application data to the same storage node at the super-chunk granularity using a handprinting-based stateful data routing scheme to maintain high global deduplication efficiency, meanwhile balances the workload across nodes. AppDedupe builds application-aware similarity indices with super-chunk handprints to speedup the intra-node deduplication process with high efficiency. Our experimental evaluation of AppDedupe against state-of-the-art, driven by real-world datasets, demonstrates that AppDedupe achieves the highest global deduplication efficiency with a higher global deduplication effectiveness than the high-overhead and poorly scalable traditional scheme, but at an overhead only slightly higher than that of the scalable but low duplicate-elimination-ratio approaches.

With the development of big data and multi-core processors technology, DRAM-only based main memory cannot satisfy the requirements of in-memory computing in high memory capacity and low energy consumption. The emerging memory technology-phase change memory (PCM) is proposed to break the bottleneck of the current memory system. However, its weaknesses in write endurance and long access latency make it cannot fully replace DRAM. Consequently, researchers presented the architectural design aimed at DRAM/ PCM hybrids and the corresponding page migration scheme to give full play to their merits. The urgent challenges facing by existed page migration schemes are poor performed under weak locality in data streams and further improvement need in prediction of future access tendency. In this paper, we propose an efficient page migration policy called DualStack which features dynamic page management according to global read and write information and temporal locality. It is designed to keep write-intensive pages to DRAM and read-intensive pages to PCM, and specially avoid frequent and unnecessary migration between hybrid memory media. Compared to the state-of-the-art of hybrid main memory, our experimental results indicate that DualStack can effectively improve the system I/O latency by 38%~58% on the premise of reducing the system power consumption by 20%~30%.

Setting up a multidimensional network is an important problem in complex networks and has become a future development trend in the fields of biological gene networks, social networks and so on. A multidimensional network comprises connections and attributes. Community detection in heterogeneous dat asets in different dimensions is more difficult than that in a single network. Traditional methods for dealing with multidimensional networks are ineffective, because of using supervised information or applying strategies for adjusting the graph structure of a single network. In this paper, we propose a semi-supervised community detection method for multidimensional heterogeneous networks. First, we generate a single network by integrating the multidimensional heterogeneous networks. The robust semi-supervised link adjustment strategy is then iteratively applied to the single network to make full use of dynamic supervised information for adding or removing links based on node entropy. Experimental results are obtained by five real multidimensional social datasets. The results show that the proposed method can effectively integrate heterogeneous data. The average accuracy rate and standard mutual information were 90.50% and 93.99%, respectively, representing improvements of 28.97% and 35.06%, respectively, over existing methods.

Low earth orbit (LEO) satellite networks are capable of providing global or regional mobile services for a large number of users. Since the user's service duration may be greater than the coverage time of a LEO satellite, the user may be handed over to another visible satellite to prevent interruption of the ongoing communication. On the other hand, a mobile user may be covered by more than one satellite at the instant of connection handover. When the user is about to be handed over to another satellite, the serving satellite minimizing the number of handovers would in general be the one that provides the largest service time which is not necessarily equal to the coverage time of the very satellite. In this paper, we propose a new handover algorithm which exploits both the Global Positioning System (GPS) infrastructure and satellite diversity to provide a simple and real-time handover management in LEO satellite networks. The proposed algorithm not only minimizes the expected number of satellite handover, but is also efficient and easy to be implemented in hand-held devices, thus facilitating the mobile users' access to the satellite networks. Numerical simulations performed for two typical mobile satellite networks, viz. Iridium and Globalstar, corroborate the advantages gained by the proposed algorithm.

Machine-learning algorithms are widely applied in traffic classification and anomaly detection. Due to the tremendous traffic on the network, an extremely challenging question arises: how to efficiently and accurately detect the anomalous flow from the backbone network. One solution is proposed, online anomaly-detection scheme, which is based on the sparse feature selection method, Lasso. The sparse feature selection can be efficiently solved by reformulating the problem as an optimization problem with an ℓ1-ball constraint. At the evaluation stage, the authors preprocessed the raw data trace from the trans-Pacific backbone link between Japan and the United States and generated an evaluation data set. Their empirical study shows that the feature selection step can be solved quickly by applying the efficient Euclidean projection method; indeed, doing so resolves the feature selection step faster than using three classical ℓ1-min solvers. In terms of overall accuracy, true positive rate, false positive rate, precision, and F-measure, the proposed scheme improves the quality of detection. Copyright © 2015 John Wiley & Sons, Ltd.

ABSTRACT This paper presents a realistic ray casting model on a curved surface. Guided by the model, we derive an analytical solution for spherical surfaces and propose a mathematical model by solving one problem in two spaces. By using the solution, we introduce a novel framework for spherical height field rendering. We have successfully implemented a spherical height field rendering framework on the graphics processing unit and obtained real‐time rendering rates with screen error below 1 pixel. Copyright © 2013 John Wiley & Sons, Ltd.

This paper presents a novel algorithm (We call it Spherical Projective Displacement Mesh algorithm)for large scale spherical terrain visualization. The algorithm generates terrain meshes by rotating, displaces mesh vertices from height field atlas, and then projects a texture atlas onto the mesh vertices to create images. We successfully implement the spherical terrain visualization on a personal computer, obtain high quality images and reach a very fast rendering-rate.

Intrusion detection technology is an effective approach to dealing with the problems of network security. In this paper, it presents an intrusion detection model based on neural network and expert system. The key idea is to aim at taking advantage of classification abilities of neural network for unknown attacks and the expert-based system for the known attacks. We employ data from the third international knowledge discovery and data mining tools competition (KDDcup'99) to train and test the feasibility of our proposed neural network component. According to the results of our experiment, our model achieves 96.6 percent detection rate for DOS and probing intrusions, and less than 0.04 percent false alarm rate. Expert system can detect R2L and U2R intrusions more accurately than neural network. Therefore, hybrid model improves the performance to detect intrusions.