Search

Recently, the advancement of machine learning (ML) techniques, especially deep learning, reinforcement learning, and federated learning, has led to remarkable breakthroughs in a variety of application domains. The success of ML benefits from the advancement of the Internet, mobile networks, data center networks, and the Internet of Things (IoT) that facilitate data creation and sharing. On the other hand, we have also witnessed a fast growing trend in the networking community toward using ML to tackle challenging problems in network design, management, and optimization, which are traditionally addressed using mathematical optimization theory or human-generated heuristics. ML is also an essential ingredient in the realization of autonomous or self-driving networks. [ABSTRACT FROM AUTHOR]

Load balancing in datacenter networks (DCNs) is an important and challenging task for datacenter managers. A number of sophisticated technologies have been proposed to improve load balancing performance in a complicated circumstance, i.e., with various traffic characteristics. Many approaches need a high cost to implement, such as changing switch hardware. The efficiency problem has not been well addressed. MPTCP was proposed as a low-cost approach to improve data transmission in DCNs, which uses subflows to balance workloads across multiple paths. However, current MPTCP is not satisfying, especially when there are rack-local flows or many-to-one short flows. In this article, we propose DCMPTCP to improve the efficacy of MPTCP. We gradually develop three mechanisms. First, DCMPTCP identifies rack-local traffic and eliminates unnecessary subflows to reduce the overhead. Second, DCMPTCP estimates flow length and establishes subflows in a smarter way. Third, DCMPTCP strengthens explicit congestion notification to improve the congestion control performance on inter-rack many-to-one short flows. We have implemented DCMPTCP in both the Linux kernel and ns-3 simulator. Our comprehensive testbed experiments and simulations show that DCMPTCP outperforms MPTCP in both 1 Gbps testbed, and 10 Gbps large-scale simulation network. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the authors discusses various reports within the issue on topics including data networking, data encryption, and security monitoring for named data networking.

Mobile Cloud Computing refers to an infrastructure where both the data storage and the data processing occur outside of the mobile device. Mobile cloud applications move the computing power and data storage away from mobile devices and into the cloud, bringing applications and mobile computing not only to smartphone users but also to a much broader range of mobile subscribers. [ABSTRACT FROM PUBLISHER]

Computation offloading is a proven successful paradigm for enabling resource-intensive applications on mobile devices. Moreover, in view of emerging mobile collaborative application, the offloaded tasks can be duplicated when multiple users are in the same proximity. This motivates us to design a collaborative offloading scheme and cache the popular computation results that are likely to be reused by other mobile users. In this paper, we consider the scenario where multiple mobile users offload duplicated computation tasks to the network edge, and share the computation results among them. Our goal is to develop the optimal fine-grained collaborative offloading strategies with caching enhancements to minimize the overall execution delay at the mobile terminal side. To this end, we propose an optimal offloading with caching-enhancement scheme (OOCS) for femto-cloud scenario and mobile edge computing scenario, respectively. Simulation results show that compared to six alternative solutions in literature, our single-user OOCS can reduce execution delay up to $42.83$ % and $33.28$ % for single-user femto-cloud and single-user mobile edge computing, respectively. Our multi-user OOCS can further reduce $11.71$ % delay compared to single-user OOCS through users’ cooperation. [ABSTRACT FROM AUTHOR]

Quantum entanglement brings high-speed and inherently privacy-preserving transmission for information communication in quantum networks. The qubit scarcity is an important issue that cannot be ignored in quantum networks due to the limited storage capacity of quantum devices, the short lifespan of qubits, and so on. In this article, we first formulate the qubit competition problem as the Cooperative-Qubit-Allocation-Problem (CQAP) by taking into account both the waiting time and the fidelity of end-to-end entanglement with the given transmission link set. We then model the CQAP as a Markov Decision Process (MDP) and adopt a Reinforcement Learning (RL) algorithm to self-adaptively and cooperatively allocate qubits among quantum repeaters. Further, we introduce an Active Learning (AL) algorithm to improve the efficiency of the RL algorithm by reducing its trial-error times. Simulation results demonstrate that our proposed algorithm outperforms the benchmark algorithms, with 23.5 ms reduction on the average waiting time and 19.2 improvement on the average path maturity degree, respectively. [ABSTRACT FROM AUTHOR]

Disruption-tolerant networks (DTNs) are sparse mobile ad hoc networks where nodes connect with each other intermittently and end-to-end communication paths do not exist. Data routing in DTNs is challenging and has drawn much attention from research communities recently. Although many DTN routing strategies have been proposed in the past, they confront problems such as blind spots and dead ends and lack efficient implementation in a decentralized, large-scale, mobile, and dynamic environment. To overcome these difficulties, we introduce a new solution for DTNs that leverages the social properties and mobility characteristics of users. Our observation of the mobile trajectories of three data sets collected from real DTNs reveals that user movements appear locally and they tend to form communities correlated to geographic locations. Based on these findings, we propose a social- and mobile-aware routing strategy (SMART). It exploits a distributed community partitioning algorithm to divide the DTN into smaller communities regarding user locations and interaction routines. For intracommunity communications, a decayed routing metric convoluting social similarity and social centrality is calculated, which is used to decide forwarding node efficiently while avoiding the blind-spot and dead-end problems. To enable efficient intercommunity communications, we choose the fringe nodes that travel remotely as relays, and we propose the node-to-community utilities for routing decision across communities. We present empirical analysis to show that SMART reduces the occurrence of blind spots and dead ends to a level below 1%. The efficiency of SMART is evaluated by extensive trace-driven experiments, which illustrate that it outperforms other routing strategies in various real DTN traces. [ABSTRACT FROM PUBLISHER]

With the rapid development of autonomous driving, collision avoidance has attracted attention from both academia and industry. Many collision avoidance strategies have emerged in recent years, but the dynamic and complex nature of driving environment poses a challenge to develop robust collision avoidance algorithms. Therefore, in this paper, we propose a decentralized framework named RACE: Reinforced Cooperative Autonomous Vehicle Collision AvoidancE. Leveraging a hierarchical architecture we develop an algorithm named Co-DDPG to efficiently train autonomous vehicles. Through a security abiding channel, the autonomous vehicles distribute their driving policies. We use the relative distances obtained by the opponent sensors to build the VANET instead of locations, which ensures the vehicle's location privacy. With a leader-follower architecture and parameter distribution, RACE accelerates the learning of optimal policies and efficiently utilizes the remaining resources. We implement the RACE framework in the widely used TORCS simulator and conduct various experiments to measure the performance of RACE. Evaluations show that RACE quickly learns optimal driving policies and effectively avoids collisions. Moreover, RACE also scales smoothly with varying number of participating vehicles. We further compared RACE with existing autonomous driving systems and show that RACE outperforms them by experiencing 65% less collisions in the training process and exhibits improved performance under varying vehicle density. [ABSTRACT FROM AUTHOR]

Our daily lives have been immersed in widespread location-based social networks (LBSNs). As an open platform, LBSNs typically allow all kinds of users to register accounts. Malicious attackers can easily join and post misleading information, often with the intention of influencing users' decisions in urban computing environments. To provide reliable information and improve the experience for legitimate users, we design and implement DeepScan, a malicious account detection system for LBSNs. Different from existing approaches, DeepScan leverages emerging deep learning technologies to learn users' dynamic behavior. In particular, we introduce the long short-term memory (LSTM) neural network to conduct time series analysis of user activities. DeepScan combines newly introduced time series features and a set of conventional features extracted from user activities, and exploits a supervised machine-learning-based model for detection. Using real traces collected from Dianping, a representative LBSN, we demonstrate that DeepScan can achieve excellent prediction performance with an F1-score of 0.964. We also find that the time series features play a critical role in the detection system. [ABSTRACT FROM AUTHOR]

Mobile-edge cloud computing is a new paradigm to provide cloud computing capabilities at the edge of pervasive radio access networks in close proximity to mobile users. Aiming at provisioning flexible on-demand mobile-edge cloud service, in this paper we propose a comprehensive framework consisting of a resource-efficient computation offloading mechanism for users and a joint communication and computation (JCC) resource allocation mechanism for network operator. Specifically, we first study the resource-efficient computation offloading problem for a user, in order to reduce user's resource occupation by determining its optimal communication and computation resource profile with minimum resource occupation and meanwhile satisfying the QoS constraint. We then tackle the critical problem of user admission control for JCC resource allocation, in order to properly select the set of users for resource demand satisfaction. We show the admission control problem is NP-hard, and hence develop an efficient approximation solution of a low complexity by carefully designing the user ranking criteria and rigourously derive its performance guarantee. To prevent the manipulation that some users may untruthfully report their valuations in acquiring mobile-edge cloud service, we further resort to the powerful tool of critical value approach to design truthful pricing scheme for JCC resource allocation. Extensive performance evaluation demonstrates that the proposed schemes can achieve superior performance for on-demand mobile-edge cloud computing. [ABSTRACT FROM AUTHOR]

In current cloud computing systems, when leveraging virtualization technology, the customer’s requested data computing or storing service is accommodated by a set of communicated virtual machines (VM) in a scalable and elastic manner. These VMs are placed in one or more server nodes according to the node capacities or failure probabilities. The VM placement availability refers to the probability that at least one set of all customer’s requested VMs operates during the requested lifetime. In this paper, we first study the problem of placing at most $H$ groups of $k$ requested VMs on a minimum number of nodes, such that the VM placement availability is no less than $\delta$ , and that the specified communication delay and connection availability for each VM pair under the same placement group are not violated. We consider this problem with and without Shared-Risk Node Group (SRNG) failures, and prove this problem is NP-hard in both cases. We subsequently propose an exact Integer Nonlinear Program (INLP) and an efficient heuristic to solve this problem. We conduct simulations to compare the proposed algorithms with two existing heuristics in terms of performance. Finally, we study the related reliable routing problem of establishing a connection over at most $w$ link-disjoint paths from a source to a destination, such that the connection availability requirement is satisfied and each path delay is no more than a given value. We devise an exact algorithm and two heuristics to solve this NP-hard problem, and evaluate them via simulations. [ABSTRACT FROM PUBLISHER]

We study the problem of group formation in online social networks. In particular, we focus on one of the most important human groups—the triad—and try to understand how closed triads are formed in dynamic networks, by employing data from a large microblogging network as the basis of our study. We formally define the problem of triadic closure prediction and conduct a systematic investigation. The study reveals how user demographics, network characteristics, and social properties influence the formation of triadic closure. We also present a probabilistic graphical model to predict whether three persons will form a closed triad in a dynamic network. Different kernel functions are incorporated into the proposed graphical model to quantify the similarity between triads. Our experimental results with the large microblogging dataset demonstrate the effectiveness (+10 percent over alternative methods in terms of F1-Score) of the proposed model for the prediction of triadic closure formation. [ABSTRACT FROM PUBLISHER]

New applications based on cloud computing, such as data synchronization for large chain departmental stores and bank transaction records, require very high-speed data transport. Although a number of high-bandwidth networks have been built, existing transport protocols or their variants over such networks cannot fully exploit the network bandwidth. Our experiments show that the fixed-size application level buffer employed in the receiver side is a major cause of this deficiency. A buffer that is either too small or too large impairs the transfer performance. Due to the varied natures of network conditions and of real-time packet processing (i.e., consuming) speed at the receiver, it is important to ensure that the buffer size is dynamically adjusted according to the perceived execution situation during runtime. In this paper, we propose Rada, a dynamic receiving buffer adaptation scheme for high-speed data transfer. Rada employs an exponential moving average aided scheme to quantify the data arrival rate and consumption rate in the buffer. Based on these two rates, we develop a linear aggressive increase conservative decrease scheme to adjust the buffer size dynamically. Moreover, a weighted mean function is employed to make the adjustment adaptive to the available memory in the receiver. Theoretical analysis is provided to demonstrate the rationale and parameter bounds of Rada. The performance of Rada is also theoretically compared with potential alternatives. We implement Rada in a Linux platform and extensively evaluate its performance in a variety of scenarios. Experimental results conform to the theoretical results, and show that Rada outperforms the static buffer scheme in terms of throughput, memory footprint, and fairness. [ABSTRACT FROM AUTHOR]